tools v4.8

New calibre plugin interface (0.7.55)
Dropped unswindle.pyw
Added Android patch

Adobe_PDF_Tools/ineptpdf.pyw

@@ -1,5 +1,5 @@
 #! /usr/bin/env python
-# ineptpdf.pyw, version 7.7
+# ineptpdf.pyw, version 7.9
 
 from __future__ import with_statement
 
@@ -33,6 +33,7 @@ from __future__ import with_statement
 #   7.6 - backported AES and other fixes from version 8.4.48
 #   7.7 - On Windows try PyCrypto first and OpenSSL next
 #   7.8 - Modify interface to allow use of import
+#   7.9 - Bug fix for some session key errors when len(bookkey) > length required
 
 """
 Decrypts Adobe ADEPT-encrypted PDF files.
@@ -156,6 +157,7 @@ def _load_crypto_libcrypto():
             return out.raw
 
     class AES(object):
+        MODE_CBC = 0
         @classmethod
         def new(cls, userkey, mode, iv):
             self = AES()
@@ -1531,16 +1533,30 @@ class PDFDocument(object):
         bookkey = bookkey[index:]
         ebx_V = int_value(param.get('V', 4))
         ebx_type = int_value(param.get('EBX_ENCRYPTIONTYPE', 6))
-        # added because of the booktype / decryption book session key error
-        if ebx_V == 3:
-            V = 3        
-        elif ebx_V < 4 or ebx_type < 6:
-            V = ord(bookkey[0])
-            bookkey = bookkey[1:]
+        # added because of improper booktype / decryption book session key errors
+        if length > 0:
+            if len(bookkey) == length:
+                if ebx_V == 3:
+                    V = 3        
+                else:
+                    V = 2
+            elif len(bookkey) == length + 1:  
+                V = ord(bookkey[0])
+                bookkey = bookkey[1:]
+            else:
+                print "ebx_V is %d  and ebx_type is %d" % (ebx_V, ebx_type)
+                print "length is %d and len(bookkey) is %d" % (length, len(bookkey))
+                print "bookkey[0] is %d" % ord(bookkey[0])
+                raise ADEPTError('error decrypting book session key - mismatched length')
         else:
-            V = 2
-        if length and len(bookkey) != length:
-            raise ADEPTError('error decrypting book session key')
+            # proper length unknown try with whatever you have
+            print "ebx_V is %d  and ebx_type is %d" % (ebx_V, ebx_type)
+            print "length is %d and len(bookkey) is %d" % (length, len(bookkey))
+            print "bookkey[0] is %d" % ord(bookkey[0])
+            if ebx_V == 3:
+                V = 3        
+            else:
+                V = 2
         self.decrypt_key = bookkey
         self.genkey = self.genkey_v3 if V == 3 else self.genkey_v2
         self.decipher = self.decrypt_rc4

Calibre_Plugins/K4MobiDeDRM_plugin/__init__.py

@@ -0,0 +1,119 @@
+#!/usr/bin/env python
+
+from __future__ import with_statement
+
+from calibre.customize import FileTypePlugin
+from calibre.gui2 import is_ok_to_use_qt
+# from calibre.ptempfile import PersistentTemporaryDirectory
+
+from calibre_plugins.k4mobidedrm import kgenpids
+from calibre_plugins.k4mobidedrm import topazextract
+from calibre_plugins.k4mobidedrm import mobidedrm
+
+import sys
+import os
+import re
+
+class K4DeDRM(FileTypePlugin):
+    name                = 'K4PC, K4Mac, Kindle Mobi and Topaz DeDRM' # Name of the plugin
+    description         = 'Removes DRM from Mobipocket, Kindle/Mobi, Kindle/Topaz and Kindle/Print Replica files. Provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc.'
+    supported_platforms = ['osx', 'windows', 'linux'] # Platforms this plugin will run on
+    author              = 'DiapDealer, SomeUpdates' # The author of this plugin
+    version             = (0, 3, 8)   # The version number of this plugin
+    file_types          = set(['prc','mobi','azw','azw1','azw4','tpz']) # The file types that this plugin will be applied to
+    on_import           = True # Run this plugin during the import
+    priority            = 210  # run this plugin before mobidedrm, k4pcdedrm, k4dedrm
+    minimum_calibre_version = (0, 7, 55)
+
+    def run(self, path_to_ebook):
+        plug_ver = '.'.join(str(self.version).strip('()').replace(' ', '').split(','))
+        k4 = True
+        if sys.platform.startswith('linux'):
+            k4 = False
+        pids = []
+        serials = []
+        kInfoFiles = []
+        # Get supplied list of PIDs to try from plugin customization.
+        customvalues = self.site_customization.split(',')
+        for customvalue in customvalues:
+            customvalue = str(customvalue)
+            customvalue = customvalue.strip()
+            if len(customvalue) == 10 or len(customvalue) == 8:
+                pids.append(customvalue)
+            else :
+                if len(customvalue) == 16 and customvalue[0] == 'B':
+                    serials.append(customvalue)
+                else:
+                    print "%s is not a valid Kindle serial number or PID." % str(customvalue)
+                        
+        # Load any kindle info files (*.info) included Calibre's config directory.
+        try:
+            # Find Calibre's configuration directory.
+            confpath = os.path.split(os.path.split(self.plugin_path)[0])[0]
+            print 'K4MobiDeDRM v%s: Calibre configuration directory = %s' % (plug_ver, confpath)
+            files = os.listdir(confpath)
+            filefilter = re.compile("\.info$|\.kinf$", re.IGNORECASE)
+            files = filter(filefilter.search, files)
+            if files:
+                for filename in files:
+                    fpath = os.path.join(confpath, filename)
+                    kInfoFiles.append(fpath)
+                print 'K4MobiDeDRM v%s: Kindle info/kinf file %s found in config folder.' % (plug_ver, filename)
+        except IOError:
+            print 'K4MobiDeDRM v%s: Error reading kindle info/kinf files from config directory.' % plug_ver
+            pass
+
+        mobi = True
+        magic3 = file(path_to_ebook,'rb').read(3)
+        if magic3 == 'TPZ':
+            mobi = False
+
+        bookname = os.path.splitext(os.path.basename(path_to_ebook))[0]
+
+        if mobi:
+            mb = mobidedrm.MobiBook(path_to_ebook)
+        else:
+            mb = topazextract.TopazBook(path_to_ebook)
+
+        title = mb.getBookTitle()
+        md1, md2 = mb.getPIDMetaInfo()
+        pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
+
+        try:
+            mb.processBook(pidlst)
+
+        except mobidedrm.DrmException, e:
+            #if you reached here then no luck raise and exception
+            if is_ok_to_use_qt():
+                from PyQt4.Qt import QMessageBox
+                d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM v%s Plugin" % plug_ver, "Error: " + str(e) + "... %s\n" %  path_to_ebook)
+                d.show()
+                d.raise_()
+                d.exec_()
+            raise Exception("K4MobiDeDRM plugin v%s Error: %s" % (plug_ver, str(e)))
+        except topazextract.TpzDRMError, e:
+            #if you reached here then no luck raise and exception
+            if is_ok_to_use_qt():
+                    from PyQt4.Qt import QMessageBox
+                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM v%s Plugin" % plug_ver, "Error: " + str(e) + "... %s\n" % path_to_ebook)
+                    d.show()
+                    d.raise_()
+                    d.exec_()
+            raise Exception("K4MobiDeDRM plugin v%s Error: %s" % (plug_ver, str(e)))
+
+        print "Success!"
+        if mobi:
+            if mb.getPrintReplica():
+                of = self.temporary_file(bookname+'.azw4')
+                print 'K4MobiDeDRM v%s: Print Replica format detected.' % plug_ver
+            else:
+                of = self.temporary_file(bookname+'.mobi')
+            mb.getMobiFile(of.name)
+        else:
+            of = self.temporary_file(bookname+'.htmlz')
+            mb.getHTMLZip(of.name)
+            mb.cleanup()
+        return of.name
+
+    def customization_help(self, gui=False):
+        return 'Enter 10 character PIDs and/or Kindle serial numbers, use a comma (no spaces) to separate each PID or SerialNumber from the next.'

Calibre_Plugins/K4MobiDeDRM_plugin/convert2xml.py

@@ -20,6 +20,8 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # Get a 7 bit encoded number from string. The most 
 # significant byte comes first and has the high bit (8th) set
@@ -138,7 +140,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside of string table limits')
+            # sys.exit(-1)
 
     def getSize(self):
         return self.size
@@ -258,6 +261,11 @@ class PageParser(object):
         'paragraph.class'     : (1, 'scalar_text', 0, 0),
         'paragraph.firstWord' : (1, 'scalar_number', 0, 0),
         'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridSize'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridTopCenter' : (1, 'scalar_number', 0, 0),
+
 
         'word_semantic'           : (1, 'snippets', 1, 1),
         'word_semantic.type'      : (1, 'scalar_text', 0, 0),
@@ -272,11 +280,17 @@ class PageParser(object):
 
         '_span'           : (1, 'snippets', 1, 0),
         '_span.firstWord' : (1, 'scalar_number', 0, 0),
-        '-span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.gridSize'  : (1, 'scalar_number', 0, 0),
+        '_span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        '_span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'span'           : (1, 'snippets', 1, 0),
         'span.firstWord' : (1, 'scalar_number', 0, 0),
         'span.lastWord'  : (1, 'scalar_number', 0, 0),
+        'span.gridSize'  : (1, 'scalar_number', 0, 0),
+        'span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'extratokens'            : (1, 'snippets', 1, 0),
         'extratokens.type'       : (1, 'scalar_text', 0, 0),

Calibre_Plugins/K4MobiDeDRM_plugin/flatxml2html.py

@@ -271,6 +271,9 @@ class DocParser(object):
 
         pclass = self.getClass(pclass)
 
+        # if paragraph uses extratokens (extra glyphs) then make it fixed
+        (pos, extraglyphs) = self.findinDoc('paragraph.extratokens',start,end)
+
         # build up a description of the paragraph in result and return it
         # first check for the  basic - all words paragraph
         (pos, sfirst) = self.findinDoc('paragraph.firstWord',start,end)
@@ -280,6 +283,7 @@ class DocParser(object):
             last = int(slast)
             
             makeImage = (regtype == 'vertical') or (regtype == 'table')
+            makeImage = makeImage or (extraglyphs != None) 
             if self.fixedimage:
                 makeImage = makeImage or (regtype == 'fixed')
 
@@ -353,6 +357,8 @@ class DocParser(object):
 
         word_class = ''
 
+        word_semantic_type = ''
+
         while (line < end) :
 
             (name, argres) = self.lineinDoc(line)
@@ -512,6 +518,72 @@ class DocParser(object):
         return parares
 
 
+    def buildTOCEntry(self, pdesc) :
+        parares = ''
+        sep =''
+        tocentry = ''
+        handle_links = len(self.link_id) > 0
+
+        lstart = 0
+
+        cnt = len(pdesc)
+        for j in xrange( 0, cnt) :
+
+            (wtype, num) = pdesc[j]
+
+            if wtype == 'ocr' :
+                word = self.ocrtext[num]
+                sep = ' '
+
+                if handle_links:
+                    link = self.link_id[num]
+                    if (link > 0):
+                        linktype = self.link_type[link-1]
+                        title = self.link_title[link-1]
+                        title = title.rstrip('. ')
+                        alt_title = parares[lstart:]
+                        alt_title = alt_title.strip()
+                        # now strip off the actual printed page number
+                        alt_title = alt_title.rstrip('01234567890ivxldIVXLD-.')
+                        alt_title = alt_title.rstrip('. ')
+                        # skip over any external links - can't have them in a books toc
+                        if linktype == 'external' :
+                            title = ''
+                            alt_title = ''
+                            linkpage = ''
+                        else : 
+                            if len(self.link_page) >= link :
+                                ptarget = self.link_page[link-1] - 1
+                                linkpage = '%04d' % ptarget
+                            else :
+                                # just link to the current page
+                                linkpage = self.id[4:]
+                        if len(alt_title) >= len(title):
+                            title = alt_title
+                        if title != '' and linkpage != '':
+                            tocentry += title + '|' + linkpage + '\n'
+                        lstart = len(parares)
+                        if word == '_link_' : word = ''
+                    elif (link < 0) :
+                        if word == '_link_' : word = ''
+
+                if word == '_lb_':
+                    word = ''
+                    sep = ''
+
+                if num in self.dehyphen_rootid :
+                    word = word[0:-1]
+                    sep = ''
+
+                parares += word + sep
+
+            else :
+                continue
+
+        return tocentry
+
+
+
     
     # walk the document tree collecting the information needed
     # to build an html page using the ocrText
@@ -519,6 +591,7 @@ class DocParser(object):
     def process(self):
 
         htmlpage = ''
+        tocinfo = ''
 
         # get the ocr text
         (pos, argres) = self.findinDoc('info.word.ocrText',0,-1)
@@ -644,9 +717,9 @@ class DocParser(object):
                         ptype = 'end'
                         first_para_continued = False
                     (pclass, pdesc) = self.getParaDescription(start,end, regtype)
+                    tocinfo += self.buildTOCEntry(pdesc)
                     htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
 
-
                 elif (regtype == 'vertical') or (regtype == 'table') :
                     ptype = 'full'
                     if inGroup:
@@ -704,12 +777,11 @@ class DocParser(object):
                 htmlpage = htmlpage[0:-4]
             last_para_continued = False
 
-        return htmlpage
-
+        return htmlpage, tocinfo
 
 
 def convert2HTML(flatxml, classlst, fileid, bookDir, gdict, fixedimage):
     # create a document parser
     dp = DocParser(flatxml, classlst, fileid, bookDir, gdict, fixedimage)
-    htmlpage = dp.process()
-    return htmlpage
+    htmlpage, tocinfo = dp.process()
+    return htmlpage, tocinfo

Calibre_Plugins/K4MobiDeDRM_plugin/flatxml2svg.py

@@ -10,17 +10,94 @@ from struct import unpack
 
 
 class PParser(object):
-    def __init__(self, gd, flatxml):
+    def __init__(self, gd, flatxml, meta_array):
         self.gd = gd
         self.flatdoc = flatxml.split('\n')
+        self.docSize = len(self.flatdoc)
         self.temp = []
-        foo = self.getData('page.h') or self.getData('book.h')
-        self.ph = foo[0]
-        foo = self.getData('page.w') or self.getData('book.w')
-        self.pw = foo[0]
-        self.gx = self.getData('info.glyph.x')
-        self.gy = self.getData('info.glyph.y')
-        self.gid = self.getData('info.glyph.glyphID')
+        
+        self.ph = -1
+        self.pw = -1
+        startpos = self.posinDoc('page.h') or self.posinDoc('book.h')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.ph = max(self.ph, int(argres))
+        startpos = self.posinDoc('page.w') or self.posinDoc('book.w')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.pw = max(self.pw, int(argres))
+        
+        if self.ph <= 0:
+            self.ph = int(meta_array.get('pageHeight', '11000'))
+        if self.pw <= 0:
+            self.pw = int(meta_array.get('pageWidth', '8500'))
+
+        res = []
+        startpos = self.posinDoc('info.glyph.x')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.x', p)
+            res.extend(argres)
+        self.gx = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.y')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.y', p)
+            res.extend(argres)
+        self.gy = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.glyphID')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.glyphID', p)
+            res.extend(argres)
+        self.gid = res
+
+
+    # return tag at line pos in document
+    def lineinDoc(self, pos) :
+        if (pos >= 0) and (pos < self.docSize) :
+            item = self.flatdoc[pos]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+        return name, argres
+
+    # find tag in doc if within pos to end inclusive
+    def findinDoc(self, tagpath, pos, end) :
+        result = None
+        if end == -1 :
+            end = self.docSize
+        else:
+            end = min(self.docSize, end)
+        foundat = -1
+        for j in xrange(pos, end):
+            item = self.flatdoc[j]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+            if name.endswith(tagpath) :
+                result = argres
+                foundat = j
+                break
+        return foundat, result
+
+    # return list of start positions for the tagpath
+    def posinDoc(self, tagpath):
+        startpos = []
+        pos = 0
+        res = ""
+        while res != None :
+            (foundpos, res) = self.findinDoc(tagpath, pos, -1)
+            if res != None :
+                startpos.append(foundpos)
+            pos = foundpos + 1
+        return startpos
+
     def getData(self, path):
         result = None
         cnt = len(self.flatdoc)
@@ -39,6 +116,23 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
+    def getDataatPos(self, path, pos):
+        result = None
+        item = self.flatdoc[pos]
+        if item.find('=') >= 0:
+            (name, argt) = item.split('=')
+            argres = argt.split('|')
+        else:
+            name = item
+            argres = []
+        if (len(argres) > 0) :
+            for j in xrange(0,len(argres)):
+                argres[j] = int(argres[j])
+        if (name.endswith(path)):
+            result = argres
+        return result
+
     def getDataTemp(self, path):
         result = None
         cnt = len(self.temp)
@@ -58,6 +152,7 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
     def getImages(self):
         result = []
         self.temp = self.flatdoc
@@ -69,6 +164,7 @@ class PParser(object):
             src = self.getDataTemp('img.src')[0]
             result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
         return result
+
     def getGlyphs(self):
         result = []
         if (self.gid != None) and (len(self.gid) > 0):
@@ -84,25 +180,25 @@ class PParser(object):
         return result
 
 
-def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi):
+def convert2SVG(gdict, flat_xml, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi):
     ml = ''
-    pp = PParser(gdict, flat_xml)
+    pp = PParser(gdict, flat_xml, meta_array)
     ml += '<?xml version="1.0" standalone="no"?>\n'
     if (raw):
         ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
         ml += '<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1)
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
     else:
         ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
         ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
         ml += '<script><![CDATA[\n'
         ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
         ml += 'var dpi=%d;\n' % scaledpi
-        if (counter) :
-            ml += 'var prevpage="page%04d.xhtml";\n' % (counter - 1)
-        if (counter < numfiles-1) :
-            ml += 'var nextpage="page%04d.xhtml";\n' % (counter + 1)
+        if (previd) :
+            ml += 'var prevpage="page%04d.xhtml";\n' % (previd)
+        if (nextid) :
+            ml += 'var nextpage="page%04d.xhtml";\n' % (nextid)
         ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
         ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
         ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
@@ -115,10 +211,11 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         ml += '</head>\n'
         ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
         ml += '<div style="white-space:nowrap;">\n'
-        if (counter == 0) :
+        if previd == None:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n'
+        
         ml += '<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph)
     if (pp.gid != None): 
         ml += '<defs>\n'
@@ -134,12 +231,14 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         for j in xrange(0,len(pp.gid)):
             ml += '<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j])
     if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
-        ml += '<text x="10" y="10" font-family="Helvetica" font-size="100" stroke="black">This page intentionally left blank.</text>\n<text x="10" y="110" font-family="Helvetica" font-size="50" stroke="black">Until this notice unintentionally gave it content.  (gensvg.py)</text>\n'
+        xpos = "%d" % (pp.pw // 3)
+        ypos = "%d" % (pp.ph // 3)
+        ml += '<text x="' + xpos + '" y="' + ypos + '" font-size="' + meta_array['fontSize'] + '" font-family="Helvetica" stroke="black">This page intentionally left blank.</text>\n'
     if (raw) :
         ml += '</svg>'
     else :
         ml += '</svg></a>\n'
-        if (counter == numfiles - 1) :
+        if nextid == None:
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else :
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n'

Calibre_Plugins/K4MobiDeDRM_plugin/genbook.py

@@ -19,12 +19,25 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # local support routines
-import convert2xml
-import flatxml2html
-import flatxml2svg
-import stylexml2css
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre :
+    from calibre_plugins.k4mobidedrm import convert2xml
+    from calibre_plugins.k4mobidedrm import flatxml2html
+    from calibre_plugins.k4mobidedrm import flatxml2svg
+    from calibre_plugins.k4mobidedrm import stylexml2css
+else :
+    import convert2xml
+    import flatxml2html
+    import flatxml2svg
+    import stylexml2css
 
 
 # Get a 7 bit encoded number from a file
@@ -103,7 +116,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside or string table limits')
+            # sys.exit(-1)
     def getSize(self):
         return self.size
     def getPos(self):
@@ -360,10 +374,34 @@ def generateBook(bookDir, raw, fixedimage):
     (ph, pw) = getPageDim(flat_xml)
     if (ph == '-1') or (ph == '0') : ph = '11000'
     if (pw == '-1') or (pw == '0') : pw = '8500'
+    meta_array['pageHeight'] = ph
+    meta_array['pageWidth'] = pw
+    if 'fontSize' not in meta_array.keys():
+        meta_array['fontSize'] = fontsize
 
-    # print '     ', 'other0000.dat'
+    # process other.dat for css info and for map of page files to svg images
+    # this map is needed because some pages actually are made up of multiple
+    # pageXXXX.xml files
     xname = os.path.join(bookDir, 'style.css')
     flat_xml = convert2xml.fromData(dict, otherFile)
+
+    # extract info.original.pid to get original page information
+    pageIDMap = {}
+    pageidnums = stylexml2css.getpageIDMap(flat_xml)
+    if len(pageidnums) == 0:
+        filenames = os.listdir(pageDir)
+        numfiles = len(filenames)
+        for k in range(numfiles):
+            pageidnums.append(k)
+    # create a map from page ids to list of page file nums to process for that page
+    for i in range(len(pageidnums)):
+        id = pageidnums[i]
+        if id in pageIDMap.keys():
+            pageIDMap[id].append(i)
+        else:
+            pageIDMap[id] = [i]
+
+    # now get the css info
     cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
     file(xname, 'wb').write(cssstr)
     xname = os.path.join(xmlDir, 'other0000.xml')
@@ -403,6 +441,9 @@ def generateBook(bookDir, raw, fixedimage):
     glyfile.close()
     print " "
 
+    # build up tocentries while processing html
+    tocentries = ''
+
     # start up the html
     htmlFileName = "book.html"
     htmlstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -425,6 +466,77 @@ def generateBook(bookDir, raw, fixedimage):
     # readability when rendering to the screen.  
     scaledpi = 1440.0
 
+    filenames = os.listdir(pageDir)
+    filenames = sorted(filenames)
+    numfiles = len(filenames)
+
+    xmllst = []
+
+    for filename in filenames:
+        # print '     ', filename
+        print ".",
+        fname = os.path.join(pageDir,filename)
+        flat_xml = convert2xml.fromData(dict, fname)
+
+        # keep flat_xml for later svg processing
+        xmllst.append(flat_xml)
+
+        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
+        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
+
+        # first get the html
+        pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
+        tocentries += tocinfo 
+        htmlstr += pagehtml
+
+    # finish up the html string and output it
+    htmlstr += '</body>\n</html>\n'
+    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
+    
+    print " "
+    print 'Extracting Table of Contents from Amazon OCR'
+
+    # first create a table of contents file for the svg images
+    tochtml = '<?xml version="1.0" encoding="utf-8"?>\n'
+    tochtml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
+    tochtml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
+    tochtml += '<head>\n'
+    tochtml += '<title>' + meta_array['Title'] + '</title>\n'
+    tochtml += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
+    tochtml += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
+    if 'ASIN' in meta_array:
+        tochtml += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
+    if 'GUID' in meta_array:
+        tochtml += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
+    tochtml += '</head>\n'
+    tochtml += '<body>\n'
+
+    tochtml += '<h2>Table of Contents</h2>\n'
+    start = pageidnums[0]
+    if (raw):
+        startname = 'page%04d.svg' % start
+    else:
+        startname = 'page%04d.xhtml' % start
+
+    tochtml += '<h3><a href="' + startname + '">Start of Book</a></h3>\n'
+    # build up a table of contents for the svg xhtml output
+    toclst = tocentries.split('\n')
+    toclst.pop()
+    for entry in toclst:
+        print entry
+        title, pagenum = entry.split('|')
+        id = pageidnums[int(pagenum)]
+        if (raw):
+            fname = 'page%04d.svg' % id
+        else:
+            fname = 'page%04d.xhtml' % id
+        tochtml += '<h3><a href="'+ fname + '">' + title + '</a></h3>\n'
+    tochtml += '</body>\n'
+    tochtml += '</html>\n'
+    file(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
+
+
+    # now create index_svg.xhtml that points to all required files
     svgindex = '<?xml version="1.0" encoding="utf-8"?>\n'
     svgindex += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
     svgindex += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
@@ -439,50 +551,42 @@ def generateBook(bookDir, raw, fixedimage):
     svgindex += '</head>\n'
     svgindex += '<body>\n'
 
-    filenames = os.listdir(pageDir)
-    filenames = sorted(filenames)
-    numfiles = len(filenames)
-    counter = 0
-
-    for filename in filenames:
-        # print '     ', filename
-        print ".",
-
-        fname = os.path.join(pageDir,filename)
-        flat_xml = convert2xml.fromData(dict, fname)
-
-        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
-        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
-
-        # first get the html
-        htmlstr += flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
-
-        # now get the svg image of the page
-        svgxml = flatxml2svg.convert2SVG(gd, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi)
-
+    print "Building svg images of each book page"
+    svgindex += '<h2>List of Pages</h2>\n'
+    svgindex += '<div>\n'
+    idlst = sorted(pageIDMap.keys())
+    numids = len(idlst)
+    cnt = len(idlst)
+    previd = None
+    for j in range(cnt):
+        pageid = idlst[j]
+        if j < cnt - 1:
+            nextid = idlst[j+1]
+        else:
+            nextid = None
+        print '.',
+        pagelst = pageIDMap[pageid]
+        flat_svg = ''
+        for page in pagelst:
+            flat_svg += xmllst[page]
+        svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
         if (raw) :
-            pfile = open(os.path.join(svgDir,filename.replace('.dat','.svg')), 'w')
-            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (counter, counter)
+            pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
+            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid)
         else :
-            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % counter), 'w')
-            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (counter, counter)
-
-
+            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
+            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid)
+        previd = pageid
         pfile.write(svgxml)
         pfile.close()
-
         counter += 1
-
-    print " "
-
-    # finish up the html string and output it
-    htmlstr += '</body>\n</html>\n'
-    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
-
-    # finish up the svg index string and output it
+    svgindex += '</div>\n'
+    svgindex += '<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n'
     svgindex += '</body>\n</html>\n'
     file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
 
+    print " "
+
     # build the opf file
     opfname = os.path.join(bookDir, 'book.opf')
     opfstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -504,7 +608,7 @@ def generateBook(bookDir, raw, fixedimage):
     opfstr += '   </metadata>\n'
     opfstr += '<manifest>\n'
     opfstr += '   <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n'
-    opfstr += '   <item id="stylesheet" href="style.css" media-type="text.css"/>\n'
+    opfstr += '   <item id="stylesheet" href="style.css" media-type="text/css"/>\n'
     # adding image files to manifest
     filenames = os.listdir(imgDir)
     filenames = sorted(filenames)
@@ -562,7 +666,7 @@ def main(argv):
         return 1 
 
     raw = 0
-    fixedimage = False
+    fixedimage = True
     for o, a in opts:
         if o =="-h":
             usage()

Calibre_Plugins/K4MobiDeDRM_plugin/k4mobidedrm_orig.py

@@ -0,0 +1,208 @@
+#!/usr/bin/env python
+
+from __future__ import with_statement
+
+# engine to remove drm from Kindle for Mac and Kindle for PC books
+# for personal use for archiving and converting your ebooks
+
+# PLEASE DO NOT PIRATE EBOOKS! 
+
+# We want all authors and publishers, and eBook stores to live
+# long and prosperous lives but at the same time  we just want to 
+# be able to read OUR books on whatever device we want and to keep 
+# readable for a long, long time
+
+#  This borrows very heavily from works by CMBDTC, IHeartCabbages, skindle, 
+#    unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates 
+#    and many many others
+
+
+__version__ = '3.9'
+
+class Unbuffered:
+    def __init__(self, stream):
+        self.stream = stream
+    def write(self, data):
+        self.stream.write(data)
+        self.stream.flush()
+    def __getattr__(self, attr):
+        return getattr(self.stream, attr)
+
+import sys
+import os, csv, getopt
+import string
+import re
+import traceback
+
+class DrmException(Exception):
+    pass
+
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import mobidedrm
+    from calibre_plugins.k4mobidedrm import topazextract
+    from calibre_plugins.k4mobidedrm import kgenpids
+else:
+    import mobidedrm
+    import topazextract
+    import kgenpids
+        
+
+# cleanup bytestring filenames
+# borrowed from calibre from calibre/src/calibre/__init__.py
+# added in removal of non-printing chars
+# and removal of . at start
+# convert spaces to underscores
+def cleanup_name(name):
+    _filename_sanitize = re.compile(r'[\xae\0\\|\?\*<":>\+/]')
+    substitute='_'
+    one = ''.join(char for char in name if char in string.printable)
+    one = _filename_sanitize.sub(substitute, one)
+    one = re.sub(r'\s', ' ', one).strip()
+    one = re.sub(r'^\.+$', '_', one)
+    one = one.replace('..', substitute)
+    # Windows doesn't like path components that end with a period
+    if one.endswith('.'):
+        one = one[:-1]+substitute
+    # Mac and Unix don't like file names that begin with a full stop
+    if len(one) > 0 and one[0] == '.':
+        one = substitute+one[1:]
+    one = one.replace(' ','_')
+    return one
+
+def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
+    # handle the obvious cases at the beginning
+    if not os.path.isfile(infile):
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: Input file does not exist"
+        return 1
+
+    mobi = True
+    magic3 = file(infile,'rb').read(3)
+    if magic3 == 'TPZ':
+        mobi = False
+
+    bookname = os.path.splitext(os.path.basename(infile))[0]
+
+    if mobi:
+        mb = mobidedrm.MobiBook(infile)
+    else:
+        mb = topazextract.TopazBook(infile)
+
+    title = mb.getBookTitle()
+    print "Processing Book: ", title
+    filenametitle = cleanup_name(title)
+    outfilename = bookname
+    if len(outfilename)<=8 or len(filenametitle)<=8:
+        outfilename = outfilename + "_" + filenametitle
+    elif outfilename[:8] != filenametitle[:8]:
+        outfilename = outfilename[:8] + "_" + filenametitle
+        
+    # avoid excessively long file names
+    if len(outfilename)>150:
+        outfilename = outfilename[:150]
+
+    # build pid list
+    md1, md2 = mb.getPIDMetaInfo()
+    pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
+
+    try:
+        mb.processBook(pidlst)
+
+    except mobidedrm.DrmException, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+    except topazextract.TpzDRMError, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+    except Exception, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+
+    if mobi:
+        if mb.getPrintReplica():
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.azw4')
+        else:
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.mobi')
+        mb.getMobiFile(outfile)
+        return 0            
+
+    # topaz: 
+    print "   Creating NoDRM HTMLZ Archive"
+    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.htmlz')
+    mb.getHTMLZip(zipname)
+
+    print "   Creating SVG ZIP Archive"
+    zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
+    mb.getSVGZip(zipname)
+
+    print "   Creating XML ZIP Archive"
+    zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
+    mb.getXMLZip(zipname)
+
+    # remove internal temporary directory of Topaz pieces
+    mb.cleanup()
+
+    return 0
+
+
+def usage(progname):
+    print "Removes DRM protection from K4PC/M, Kindle, Mobi and Topaz ebooks"
+    print "Usage:"
+    print "    %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir>  " % progname
+
+#
+# Main
+#   
+def main(argv=sys.argv):
+    progname = os.path.basename(argv[0])
+
+    k4 = False
+    kInfoFiles = []
+    serials = []
+    pids = []
+    
+    print ('K4MobiDeDrm v%(__version__)s '
+	   'provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc .' % globals())
+
+    try:
+        opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
+    except getopt.GetoptError, err:
+        print str(err)
+        usage(progname)
+        sys.exit(2)
+    if len(args)<2:
+        usage(progname)
+        sys.exit(2)
+        
+    for o, a in opts:
+        if o == "-k":
+            if a == None :
+                raise DrmException("Invalid parameter for -k")
+            kInfoFiles.append(a)
+        if o == "-p":
+            if a == None :
+                raise DrmException("Invalid parameter for -p")
+            pids = a.split(',')
+        if o == "-s":
+            if a == None :
+                raise DrmException("Invalid parameter for -s")
+            serials = a.split(',')
+
+    # try with built in Kindle Info files
+    k4 = True
+    if sys.platform.startswith('linux'):
+	k4 = False
+	kInfoFiles = None
+    infile = args[0]
+    outdir = args[1]
+    return decryptBook(infile, outdir, k4, kInfoFiles, serials, pids)
+
+
+if __name__ == '__main__':
+    sys.stdout=Unbuffered(sys.stdout)
+    sys.exit(main())
+

Calibre_Plugins/K4MobiDeDRM_plugin/kgenpids.py

@@ -11,16 +11,28 @@ from struct import pack, unpack, unpack_from
 class DrmException(Exception):
     pass
 
-global kindleDatabase
 global charMap1
-global charMap2
 global charMap3
 global charMap4
 
-if sys.platform.startswith('win'):
-    from k4pcutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
-if sys.platform.startswith('darwin'):
-    from k4mutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre:
+    if sys.platform.startswith('win'):
+        from calibre_plugins.k4mobidedrm.k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from calibre_plugins.k4mobidedrm.k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+else:
+    if sys.platform.startswith('win'):
+        from k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
 
 charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
 charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
@@ -66,50 +78,7 @@ def decode(data,map):
         value = (((high * len(map)) ^ 0x80) & 0xFF) + low
         result += pack("B",value)
     return result
-
-# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForHash(hashedKey):
-    global kindleDatabase
-    global charMap1
-    global charMap2
-    encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
-    if sys.platform.startswith('win'):
-        return CryptUnprotectData(encryptedValue,"")
-    else:
-        cleartext = CryptUnprotectData(encryptedValue)
-        return decode(cleartext, charMap1)
- 
-# Get a record from the Kindle.info file for the string in "key" (plaintext). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForKey(key):
-    global charMap2
-    return getKindleInfoValueForHash(encodeHash(key,charMap2))
-
-# Find if the original string for a hashed/encoded string is known. 
-# If so return the original string othwise return an empty string.
-def findNameForHash(hash):
-    global charMap2
-    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
-    result = ""
-    for name in names:
-        if hash == encodeHash(name, charMap2):
-           result = name
-           break
-    return result
     
-# Print all the records from the kindle.info file (option -i)
-def printKindleInfo():
-    for record in kindleDatabase:
-        name = findNameForHash(record)
-        if name != "" :
-            print (name)
-            print ("--------------------------")
-        else :
-            print ("Unknown Record")
-        print getKindleInfoValueForHash(record)
-        print "\n"
-
 #
 # PID generation routines
 #
@@ -222,15 +191,15 @@ def getKindlePid(pidlst, rec209, token, serialnum):
     return pidlst
 
 
-# Parse the EXTH header records and parse the Kindleinfo
-# file to calculate the book pid.
+# parse the Kindleinfo file to calculate the book pid.
+
+keynames = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
 
 def getK4Pids(pidlst, rec209, token, kInfoFile):
-    global kindleDatabase
     global charMap1
     kindleDatabase = None
     try:
-        kindleDatabase = parseKindleInfo(kInfoFile)
+        kindleDatabase = getDBfromFile(kInfoFile)
     except Exception, message:
         print(message)
         kindleDatabase = None
@@ -241,22 +210,22 @@ def getK4Pids(pidlst, rec209, token, kInfoFile):
         
     try:
         # Get the Mazama Random number
-        MazamaRandomNumber = getKindleInfoValueForKey("MazamaRandomNumber")
+        MazamaRandomNumber = kindleDatabase["MazamaRandomNumber"]
 
         # Get the kindle account token
-        kindleAccountToken = getKindleInfoValueForKey("kindle.account.tokens")
+        kindleAccountToken = kindleDatabase["kindle.account.tokens"]
     except KeyError:
         print "Keys not found in " + kInfoFile
         return pidlst
         
-    # Get the HDD serial
-    encodedSystemVolumeSerialNumber = encodeHash(GetVolumeSerialNumber(),charMap1)
+    # Get the ID string used
+    encodedIDString = encodeHash(GetIDString(),charMap1)
 
     # Get the current user name
     encodedUsername = encodeHash(GetUserName(),charMap1)
 
     # concat, hash and encode to calculate the DSN
-    DSN = encode(SHA1(MazamaRandomNumber+encodedSystemVolumeSerialNumber+encodedUsername),charMap1)
+    DSN = encode(SHA1(MazamaRandomNumber+encodedIDString+encodedUsername),charMap1)
        
     # Compute the device PID (for which I can tell, is used for nothing).
     table =  generatePidEncryptionTable()

Calibre_Plugins/K4MobiDeDRM_plugin/stylexml2css.py

@@ -81,6 +81,14 @@ class DocParser(object):
             pos = foundpos + 1
         return startpos
 
+    # returns a vector of integers for the tagpath
+    def getData(self, tagpath, pos, end):
+        argres=[]
+        (foundat, argt) = self.findinDoc(tagpath, pos, end)
+        if (argt != None) and (len(argt) > 0) :
+            argList = argt.split('|')
+            argres = [ int(strval) for strval in argList]
+        return argres
 
     def process(self):
 
@@ -237,7 +245,11 @@ def convert2CSS(flatxml, fontsize, ph, pw):
 
     # create a document parser
     dp = DocParser(flatxml, fontsize, ph, pw)
-
     csspage = dp.process()
-
     return csspage
+
+
+def getpageIDMap(flatxml):
+    dp = DocParser(flatxml, 0, 0, 0)
+    pageidnumbers = dp.getData('info.original.pid', 0, -1)
+    return pageidnumbers

Calibre_Plugins/K4MobiDeDRM_plugin/topazextract.py

@@ -10,7 +10,12 @@ class Unbuffered:
         return getattr(self.stream, attr)
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
+
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
 import os, csv, getopt
 import zlib, zipfile, tempfile, shutil
 from struct import pack
@@ -18,10 +23,32 @@ from struct import unpack
 
 class TpzDRMError(Exception):
     pass
+
     
 # local support routines
-import kgenpids
-import genbook
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import kgenpids
+    from calibre_plugins.k4mobidedrm import genbook
+else:
+    import kgenpids
+    import genbook
+
+
+# recursive zip creation support routine
+def zipUpDir(myzip, tdir, localname):
+    currentdir = tdir
+    if localname != "":
+        currentdir = os.path.join(currentdir,localname)
+    list = os.listdir(currentdir)
+    for file in list:
+        afilename = file
+        localfilePath = os.path.join(localname, afilename)
+        realfilePath = os.path.join(currentdir,file)
+        if os.path.isfile(realfilePath):
+            myzip.write(realfilePath, localfilePath)
+        elif os.path.isdir(realfilePath):
+            zipUpDir(myzip, tdir, localfilePath)
+
 #
 # Utility routines
 #
@@ -110,9 +137,10 @@ def decryptDkeyRecords(data,PID):
 
 
 class TopazBook:
-    def __init__(self, filename, outdir):
+    def __init__(self, filename):
         self.fo = file(filename, 'rb')
-        self.outdir = outdir
+        self.outdir = tempfile.mkdtemp()
+        # self.outdir = 'rawdat'
         self.bookPayloadOffset = 0
         self.bookHeaderRecords = {}
         self.bookMetadata = {}
@@ -317,21 +345,34 @@ class TopazBook:
                         file(outputFile, 'wb').write(record)
         print " "
 
+    def getHTMLZip(self, zipname):
+        htmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        htmlzip.write(os.path.join(self.outdir,'book.html'),'book.html')
+        htmlzip.write(os.path.join(self.outdir,'book.opf'),'book.opf')
+        if os.path.isfile(os.path.join(self.outdir,'cover.jpg')):
+            htmlzip.write(os.path.join(self.outdir,'cover.jpg'),'cover.jpg')
+        htmlzip.write(os.path.join(self.outdir,'style.css'),'style.css')
+        zipUpDir(htmlzip, self.outdir, 'img')
+        htmlzip.close()
 
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
+    def getSVGZip(self, zipname):
+        svgzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        svgzip.write(os.path.join(self.outdir,'index_svg.xhtml'),'index_svg.xhtml')
+        zipUpDir(svgzip, self.outdir, 'svg')
+        zipUpDir(svgzip, self.outdir, 'img')
+        svgzip.close()
 
+    def getXMLZip(self, zipname):
+        xmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        targetdir = os.path.join(self.outdir,'xml')
+        zipUpDir(xmlzip, targetdir, '')
+        zipUpDir(xmlzip, self.outdir, 'img')
+        xmlzip.close()
+
+    def cleanup(self):
+        if os.path.isdir(self.outdir):
+            pass
+            # shutil.rmtree(self.outdir, True)
 
 def usage(progname):
     print "Removes DRM protection from Topaz ebooks and extract the contents"
@@ -383,58 +424,46 @@ def main(argv=sys.argv):
         return 1
 
     bookname = os.path.splitext(os.path.basename(infile))[0]
-    tempdir = tempfile.mkdtemp()
 
-    tb = TopazBook(infile, tempdir)
+    tb = TopazBook(infile)
     title = tb.getBookTitle()
     print "Processing Book: ", title
     keysRecord, keysRecordRecord = tb.getPIDMetaInfo()
     pidlst = kgenpids.getPidList(keysRecord, keysRecordRecord, k4, pids, serials, kInfoFiles) 
 
     try:
+        print "Decrypting Book"
         tb.processBook(pidlst)
+
+        print "   Creating HTML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_nodrm' + '.htmlz')
+        tb.getHTMLZip(zipname)
+
+        print "   Creating SVG ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
+        tb.getSVGZip(zipname)
+
+        print "   Creating XML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
+        tb.getXMLZip(zipname)
+
+        # removing internal temporary directory of pieces
+        tb.cleanup()
+
     except TpzDRMError, e:
         print str(e)
-        print "   Creating DeBug Full Zip Archive of Book"
-        zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-        myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-        zipUpDir(myzip, tempdir, '')
-        myzip.close()
-        shutil.rmtree(tempdir, True)
+        # tb.cleanup()
         return 1
 
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
-
-    print "   Creating SVG ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
-
-    print "   Creating XML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
-
-    shutil.rmtree(tempdir, True)
+    except Exception, e:
+        print str(e)
+        # tb.cleanup
+        return 1
 
     return 0
                 
 
 if __name__ == '__main__':
+    sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 

Calibre_Plugins/README-Ineptpdf-plugin.txt

@@ -8,7 +8,7 @@ This plugin is meant to decrypt Adobe Digital Edition PDFs that are protected wi
 
 I had the much easier job of converting them to a Calibre plugin.
 
-
+
 
 This plugin is meant to decrypt Adobe Digital Edition PDFs that are protected with Adobe's Adept encryption. It is meant to function without having to install any dependencies... other than having Calibre installed, of course. It will still work if you have Python, PyCrypto and/or OpenSSL already installed, but they aren't necessary.
 

Calibre_Plugins/README-K4MobiDeDRM-plugin.txt

@@ -5,12 +5,11 @@ This plugin supersedes MobiDeDRM, K4DeDRM, and K4PCDeDRM and K4X plugins.  If yo
 
 
 This plugin is meant to remove the DRM from .prc, .azw, .azw1, and .tpz ebooks.   Calibre can then convert them to whatever format you desire. It is meant to function without having to install any  dependencies except for Calibre being on your same machine and in the same account as your "Kindle for PC" or "Kindle for Mac" application if you are going to remove the DRM from those types of books.
-
+
+
 
-
-Installation:
 Installation:
-Go to Calibre's Preferences page... click on the Plugins button. Use the file dialog button to select the plugin's zip file  (K4MobiDeDRM_vXX_plugin.zip) and click the 'Add' button. You're done.
+
 Go to Calibre's Preferences page.  Do **NOT** select "Get Plugins to enhance calibre" as this is reserved for official calibre plugins", instead select "Change calibre behavior". Under "Advanced" click on the on the Plugins button. Click on the "Load plugin from file" button at the bottom of the screen.  Use the file dialog button to select the plugin's zip file  (K4MobiDeDRM_vXX_plugin.zip) and click the "Add" (or it may say "Open" button.  Then click on the "Yes" button in the warning dialog that appears.  A Confirmation dialog appears that says the plugin has been installed.
 
 

Calibre_Plugins/README-eReaderPDB2PML-plugin.txt

@@ -5,7 +5,7 @@ All credit given to The Dark Reverser for the original standalone script. I had
 All credit given to The Dark Reverser for the original standalone script. I had the much easier job of converting it to a Calibre plugin.
 
 
-
+
 This plugin is meant to convert secure Ereader files (PDB) to unsecured PMLZ files. Calibre can then convert it to whatever format you desire. It is meant to function without having to install any  dependencies... other than having Calibre installed, of course. I've included the psyco libraries (compiled for each platform) for speed. If your system can use them, great! Otherwise, they won't be used and things will just work slower.
 
 

Calibre_Plugins/README-ignobleepub-plugin.txt

@@ -9,7 +9,7 @@ with Adobe's Adept encryption. It is meant to function without having to install
 I had the much easier job of converting them to a Calibre plugin.
 
 
-
+
 This plugin is meant to decrypt Barnes & Noble Epubs that are protected
 
 with Adobe's Adept encryption. It is meant to function without having to install any dependencies... other than having Calibre installed, of course. It will still work if you have Python and PyCrypto already installed, but they aren't necessary.

Calibre_Plugins/README-ineptepub-plugin.txt

@@ -8,7 +8,7 @@ This plugin is meant to decrypt Adobe Digital Edition Epubs that are protected w
 
 I had the much easier job of converting them to a Calibre plugin.
 
-
+
 
 This plugin is meant to decrypt Adobe Digital Edition Epubs that are protected with Adobe's Adept encryption. It is meant to function without having to install any dependencies... other than having Calibre installed, of course. It will still work if you have Python and PyCrypto already installed, but they aren't necessary.
 

Calibre_Plugins/eReaderPDB2PML_plugin/__init__.py

@@ -31,10 +31,15 @@
 #   0.0.1 - Initial release
 #   0.0.2 - updated to distinguish it from earlier non-openssl version
 #   0.0.3 - removed added psyco code as it is not supported under Calibre's Python 2.7
+#   0.0.4 - minor typos fixed
+#   0.0.5 - updated to the new calibre plugin interface
 
 import sys, os
 
 from calibre.customize import FileTypePlugin
+from calibre.ptempfile import PersistentTemporaryDirectory
+from calibre.constants import iswindows, isosx
+from calibre_plugins.erdrpdb2pml import erdr2pml
 
 class eRdrDeDRM(FileTypePlugin):
     name                = 'eReader PDB 2 PML' # Name of the plugin
@@ -42,16 +47,14 @@ class eRdrDeDRM(FileTypePlugin):
                             Credit given to The Dark Reverser for the original standalone script.'
     supported_platforms = ['linux', 'osx', 'windows'] # Platforms this plugin will run on
     author              = 'DiapDealer' # The author of this plugin
-    version             = (0, 0, 4)   # The version number of this plugin
+    version             = (0, 0, 6)   # The version number of this plugin
     file_types          = set(['pdb']) # The file types that this plugin will be applied to
     on_import           = True # Run this plugin during the import
+    minimum_calibre_version = (0, 7, 55)
 
     def run(self, path_to_ebook):
-        from calibre.ptempfile import PersistentTemporaryDirectory
-        from calibre.constants import iswindows, isosx
         
         global bookname, erdr2pml
-        import erdr2pml
         
         infile = path_to_ebook
         bookname = os.path.splitext(os.path.basename(infile))[0]
@@ -111,7 +114,7 @@ class eRdrDeDRM(FileTypePlugin):
 
         print "   Decoding File"
         sect = erdr2pml.Sectionizer(infile, 'PNRdPPrs')
-        er = erdr2pml.EreaderProcessor(sect.loadSection, name, cc)
+        er = erdr2pml.EreaderProcessor(sect, name, cc)
 
         if er.getNumImages() > 0:
             print "   Extracting images"

Calibre_Plugins/eReaderPDB2PML_plugin/erdr2pml.py

@@ -58,8 +58,12 @@
 #  0.17 - added support for pycrypto's DES as well
 #  0.18 - on Windows try PyCrypto first and OpenSSL next
 #  0.19 - Modify the interface to allow use of import
+#  0.20 - modify to allow use inside new interface for calibre plugins
+#  0.21 - Support eReader (drm) version 11. 
+#       - Don't reject dictionary format. 
+#       - Ignore sidebars for dictionaries (different format?)
 
-__version__='0.19'
+__version__='0.21'
 
 class Unbuffered:
     def __init__(self, stream):
@@ -71,32 +75,50 @@ class Unbuffered:
         return getattr(self.stream, attr)
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
-
 import struct, binascii, getopt, zlib, os, os.path, urllib, tempfile
 
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
 Des = None
 if sys.platform.startswith('win'):
     # first try with pycrypto
-    import pycrypto_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import pycrypto_des
+    else:
+        import pycrypto_des
     Des = pycrypto_des.load_pycrypto()
     if Des == None:
         # they try with openssl
-        import openssl_des
+        if inCalibre:
+            from calibre_plugins.erdrpdb2pml import openssl_des
+        else:
+            import openssl_des
         Des = openssl_des.load_libcrypto()
 else:
     # first try with openssl
-    import openssl_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import openssl_des
+    else:
+        import openssl_des
     Des = openssl_des.load_libcrypto()
     if Des == None:
         # then try with pycrypto
-        import pycrypto_des
+        if inCalibre:
+            from calibre_plugins.erdrpdb2pml import pycrypto_des
+        else:
+            import pycrypto_des
         Des = pycrypto_des.load_pycrypto()
 
 # if that did not work then use pure python implementation
 # of DES and try to speed it up with Psycho
 if Des == None:
-    import python_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import python_des
+    else:
+        import python_des
     Des = python_des.Des
     # Import Psyco if available
     try:
@@ -121,12 +143,18 @@ logging.basicConfig()
 
 
 class Sectionizer(object):
+    bkType = "Book"
+
     def __init__(self, filename, ident):
         self.contents = file(filename, 'rb').read()
         self.header = self.contents[0:72]
         self.num_sections, = struct.unpack('>H', self.contents[76:78])
+        # Dictionary or normal content (TODO: Not hard-coded)
         if self.header[0x3C:0x3C+8] != ident:
-            raise ValueError('Invalid file format')
+            if self.header[0x3C:0x3C+8] == "PDctPPrs":
+                self.bkType = "Dict"
+            else:
+                raise ValueError('Invalid file format')
         self.sections = []
         for i in xrange(self.num_sections):
             offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.contents[78+i*8:78+i*8+8])
@@ -163,15 +191,15 @@ def deXOR(text, sp, table):
     return r
 
 class EreaderProcessor(object):
-    def __init__(self, section_reader, username, creditcard):
-        self.section_reader = section_reader
-        data = section_reader(0)
+    def __init__(self, sect, username, creditcard):
+        self.section_reader = sect.loadSection
+        data = self.section_reader(0)
         version,  = struct.unpack('>H', data[0:2])
         self.version = version
         logging.info('eReader file format version %s', version)
         if version != 272 and version != 260 and version != 259:
             raise ValueError('incorrect eReader version %d (error 1)' % version)
-        data = section_reader(1)
+        data = self.section_reader(1)
         self.data = data
         des = Des(fixKey(data[0:8]))
         cookie_shuf, cookie_size = struct.unpack('>LL', des.decrypt(data[-8:]))
@@ -200,11 +228,17 @@ class EreaderProcessor(object):
         self.num_text_pages = struct.unpack('>H', r[2:4])[0] - 1
         self.num_image_pages = struct.unpack('>H', r[26:26+2])[0]
         self.first_image_page = struct.unpack('>H', r[24:24+2])[0]
+        # Default values
+        self.num_footnote_pages = 0
+        self.num_sidebar_pages = 0
+        self.first_footnote_page = -1
+        self.first_sidebar_page = -1
         if self.version == 272:
             self.num_footnote_pages = struct.unpack('>H', r[46:46+2])[0]
             self.first_footnote_page = struct.unpack('>H', r[44:44+2])[0]
-            self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
-            self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
+            if (sect.bkType == "Book"):
+                self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
+                self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
             # self.num_bookinfo_pages = struct.unpack('>H', r[34:34+2])[0]
             # self.first_bookinfo_page = struct.unpack('>H', r[32:32+2])[0]
             # self.num_chapter_pages = struct.unpack('>H', r[22:22+2])[0]
@@ -220,10 +254,8 @@ class EreaderProcessor(object):
             self.xortable_size = struct.unpack('>H', r[42:42+2])[0]
             self.xortable = self.data[self.xortable_offset:self.xortable_offset + self.xortable_size]
         else:
-            self.num_footnote_pages = 0
-            self.num_sidebar_pages = 0
-            self.first_footnote_page = -1
-            self.first_sidebar_page = -1
+            # Nothing needs to be done
+            pass
             # self.num_bookinfo_pages = 0
             # self.num_chapter_pages = 0
             # self.num_link_pages = 0
@@ -248,10 +280,14 @@ class EreaderProcessor(object):
             encrypted_key_sha = r[44:44+20]
             encrypted_key = r[64:64+8]
         elif version == 260:
-            if drm_sub_version != 13:
+            if drm_sub_version != 13 and drm_sub_version != 11:
                 raise ValueError('incorrect eReader version %d (error 3)' % drm_sub_version)
-            encrypted_key = r[44:44+8]
-            encrypted_key_sha = r[52:52+20]
+            if drm_sub_version == 13:
+                encrypted_key = r[44:44+8]
+                encrypted_key_sha = r[52:52+20]
+            else:
+                encrypted_key = r[64:64+8]
+                encrypted_key_sha = r[44:44+20]
         elif version == 272:
             encrypted_key = r[172:172+8]
             encrypted_key_sha = r[56:56+20]
@@ -337,6 +373,12 @@ class EreaderProcessor(object):
                 r += fmarker
                 fnote_ids = fnote_ids[id_len+4:]
 
+        # TODO: Handle dictionary index (?) pages - which are also marked as
+        # sidebar_pages (?). For now dictionary sidebars are ignored
+        # For dictionaries - record 0 is null terminated strings, followed by
+        # blocks of around 62000 bytes and a final block. Not sure of the
+        # encoding
+
         # now handle sidebar pages
         if self.num_sidebar_pages > 0:
             r += '\n'
@@ -349,7 +391,7 @@ class EreaderProcessor(object):
                 id_len = ord(sbar_ids[2])
                 id = sbar_ids[3:3+id_len]
                 smarker = '<sidebar id="%s">\n' % id
-                smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_footnote_page + i)))
+                smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_sidebar_page + i)))
                 smarker += '\n</sidebar>\n'
                 r += smarker
                 sbar_ids = sbar_ids[id_len+4:]
@@ -370,7 +412,7 @@ def convertEreaderToPml(infile, name, cc, outdir):
     bookname = os.path.splitext(os.path.basename(infile))[0]
     print "   Decoding File"
     sect = Sectionizer(infile, 'PNRdPPrs')
-    er = EreaderProcessor(sect.loadSection, name, cc)
+    er = EreaderProcessor(sect, name, cc)
 
     if er.getNumImages() > 0:
         print "   Extracting images"
@@ -480,5 +522,6 @@ def main(argv=None):
 
 
 if __name__ == "__main__":
+    sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 

Calibre_Plugins/ignobleepub_plugin/ignobleepub_plugin.py

@@ -4,7 +4,7 @@
 # Released under the terms of the GNU General Public Licence, version 3 or
 # later.  <http://www.gnu.org/licenses/>
 #
-# Requires Calibre version 0.6.44 or higher.
+# Requires Calibre version 0.7.55 or higher.
 #
 # All credit given to I <3 Cabbages for the original standalone scripts.
 # I had the much easier job of converting them to Calibre a plugin.
@@ -48,6 +48,7 @@
 #   0.1.3 - Try PyCrypto on Windows first
 #   0.1.4 - update zipfix to deal with mimetype not in correct place
 #   0.1.5 - update zipfix to deal with completely missing mimetype files
+#   0.1.6 - update ot the new calibre plugin interface 
 
 """
 Decrypt Barnes & Noble ADEPT encrypted EPUB books.
@@ -266,6 +267,7 @@ def plugin_main(userkey, inpath, outpath):
     return 0
 
 from calibre.customize import FileTypePlugin
+from calibre.constants import iswindows, isosx
 
 class IgnobleDeDRM(FileTypePlugin):
     name                    = 'Ignoble Epub DeDRM'
@@ -273,8 +275,8 @@ class IgnobleDeDRM(FileTypePlugin):
                                 Credit given to I <3 Cabbages for the original stand-alone scripts.'
     supported_platforms     = ['linux', 'osx', 'windows']
     author                  = 'DiapDealer'
-    version                 = (0, 1, 5)
-    minimum_calibre_version = (0, 6, 44)  # Compiled python libraries cannot be imported in earlier versions.
+    version                 = (0, 1, 6)
+    minimum_calibre_version = (0, 7, 55)  # Compiled python libraries cannot be imported in earlier versions.
     file_types              = set(['epub'])
     on_import               = True
 
@@ -282,10 +284,6 @@ class IgnobleDeDRM(FileTypePlugin):
         global AES
         global AES2
         
-        from calibre.gui2 import is_ok_to_use_qt
-        from PyQt4.Qt import QMessageBox
-        from calibre.constants import iswindows, isosx
-        
         AES, AES2 = _load_crypto()
         
         if AES == None or AES2 == None:
@@ -341,7 +339,7 @@ class IgnobleDeDRM(FileTypePlugin):
         for userkey in userkeys:
             # Create a TemporaryPersistent file to work with.
             # Check original epub archive for zip errors.
-            import zipfix
+            from calibre_plugins.ignobleepub import zipfix
             inf = self.temporary_file('.epub')
             try:
                 fr = zipfix.fixZip(path_to_ebook, inf.name)

Calibre_Plugins/ineptepub_plugin/__init__.py

@@ -4,7 +4,7 @@
 # Released under the terms of the GNU General Public Licence, version 3 or
 # later.  <http://www.gnu.org/licenses/>
 #
-# Requires Calibre version 0.6.44 or higher.
+# Requires Calibre version 0.7.55 or higher.
 #
 # All credit given to I <3 Cabbages for the original standalone scripts.
 # I had the much easier job of converting them to a Calibre plugin.
@@ -49,6 +49,7 @@
 #   0.1.4 - default to try PyCrypto first on Windows
 #   0.1.5 - update zipfix to handle out of position mimetypes
 #   0.1.6 - update zipfix to handle completely missing mimetype files
+#   0.1.7 - update to new calibre plugin interface
 
 """
 Decrypt Adobe ADEPT-encrypted EPUB books.
@@ -365,6 +366,7 @@ def plugin_main(userkey, inpath, outpath):
     return 0
 
 from calibre.customize import FileTypePlugin
+from calibre.constants import iswindows, isosx
 
 class IneptDeDRM(FileTypePlugin):
     name                    = 'Inept Epub DeDRM'
@@ -372,8 +374,8 @@ class IneptDeDRM(FileTypePlugin):
                                 Credit given to I <3 Cabbages for the original stand-alone scripts.'
     supported_platforms     = ['linux', 'osx', 'windows']
     author                  = 'DiapDealer'
-    version                 = (0, 1, 6)
-    minimum_calibre_version = (0, 6, 44)  # Compiled python libraries cannot be imported in earlier versions.
+    version                 = (0, 1, 7)
+    minimum_calibre_version = (0, 7, 55)  # Compiled python libraries cannot be imported in earlier versions.
     file_types              = set(['epub'])
     on_import               = True
     priority                = 100
@@ -382,10 +384,6 @@ class IneptDeDRM(FileTypePlugin):
         global AES
         global RSA
         
-        from calibre.gui2 import is_ok_to_use_qt
-        from PyQt4.Qt import QMessageBox
-        from calibre.constants import iswindows, isosx
-        
         AES, RSA = _load_crypto()
         
         if AES == None or RSA == None:
@@ -418,7 +416,7 @@ class IneptDeDRM(FileTypePlugin):
             # Calibre's configuration directory for future use.
             if iswindows or isosx:
                 # ADE key retrieval script included in respective OS folder.
-                from ade_key import retrieve_key
+                from calibre_plugins.ineptepub.ade_key import retrieve_key
                 try:
                     keydata = retrieve_key()
                     userkeys.append(keydata)
@@ -439,7 +437,7 @@ class IneptDeDRM(FileTypePlugin):
         for userkey in userkeys:
             # Create a TemporaryPersistent file to work with.
             # Check original epub archive for zip errors.
-            import zipfix
+            from calibre_plugins.ineptepub import zipfix
             inf = self.temporary_file('.epub')
             try:
                 fr = zipfix.fixZip(path_to_ebook, inf.name)

Calibre_Plugins/ineptpdf_plugin/__init__.py

@@ -1,6 +1,6 @@
 #! /usr/bin/env python
 
-# ineptpdf_plugin.py
+# ineptpdf plugin  __init__.py
 # Released under the terms of the GNU General Public Licence, version 3 or
 # later.  <http://www.gnu.org/licenses/>
 
@@ -11,7 +11,7 @@
 # be able to read OUR books on whatever device we want and to keep 
 # readable for a long, long time
 
-# Requires Calibre version 0.6.44 or higher.
+# Requires Calibre version 0.7.55 or higher.
 #
 # All credit given to I <3 Cabbages for the original standalone scripts.
 # I had the much easier job of converting them to a Calibre plugin.
@@ -51,6 +51,7 @@
 #   0.1.1 - back port ineptpdf 8.4.X support for increased number of encryption methods
 #   0.1.2 - back port ineptpdf 8.4.X bug fixes
 #   0.1.3 - add in fix for improper rejection of session bookkeys with len(bookkey) = length + 1 
+#   0.1.4 - update to the new calibre plugin interface
 
 """
 Decrypts Adobe ADEPT-encrypted PDF files.
@@ -174,6 +175,7 @@ def _load_crypto_libcrypto():
             return out.raw
 
     class AES(object):
+        MODE_CBC = 0
         @classmethod
         def new(cls, userkey, mode, iv):
             self = AES()
@@ -2126,6 +2128,7 @@ def plugin_main(keypath, inpath, outpath):
 
 
 from calibre.customize import FileTypePlugin
+from calibre.constants import iswindows, isosx
 
 class IneptPDFDeDRM(FileTypePlugin):
     name                    = 'Inept PDF DeDRM'
@@ -2133,17 +2136,14 @@ class IneptPDFDeDRM(FileTypePlugin):
                                 Credit given to I <3 Cabbages for the original stand-alone scripts.'
     supported_platforms     = ['linux', 'osx', 'windows']
     author                  = 'DiapDealer'
-    version                 = (0, 1, 3)
-    minimum_calibre_version = (0, 6, 44)  # Compiled python libraries cannot be imported in earlier versions.
+    version                 = (0, 1, 4)
+    minimum_calibre_version = (0, 7, 55)  # for the new plugin interface
     file_types              = set(['pdf'])
     on_import               = True
     
     def run(self, path_to_ebook):
         global ARC4, RSA, AES
         
-        from calibre.gui2 import is_ok_to_use_qt
-        from PyQt4.Qt import QMessageBox
-        from calibre.constants import iswindows, isosx
         
         ARC4, RSA, AES = _load_crypto()
         
@@ -2177,7 +2177,7 @@ class IneptPDFDeDRM(FileTypePlugin):
             # Calibre's configuration directory for future use.
             if iswindows or isosx:
                 # ADE key retrieval script.
-                from ade_key import retrieve_key
+                from calibre_plugins.ineptpdf.ade_key import retrieve_key
                 try:
                     keydata = retrieve_key()
                     userkeys.append(keydata)

Calibre_Plugins/k4mobidedrm_plugin/k4mobidedrm_plugin.py

@@ -1,374 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import with_statement
-
-# engine to remove drm from Kindle for Mac and Kindle for PC books
-# for personal use for archiving and converting your ebooks
-
-# PLEASE DO NOT PIRATE EBOOKS! 
-
-# We want all authors and publishers, and eBook stores to live
-# long and prosperous lives but at the same time  we just want to 
-# be able to read OUR books on whatever device we want and to keep 
-# readable for a long, long time
-
-#  This borrows very heavily from works by CMBDTC, IHeartCabbages, skindle, 
-#    unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates 
-#    and many many others
-
-# It can run standalone to convert K4M/K4PC/Mobi files, or it can be installed as a
-# plugin for Calibre (http://calibre-ebook.com/about) so that importing
-# K4 or Mobi with DRM is no londer a multi-step process.
-#
-# ***NOTE*** If you are using this script as a calibre plugin for a K4M or K4PC ebook
-# then calibre must be installed on the same machine and in the same account as K4PC or K4M
-# for the plugin version to function properly.
-#
-# To create a Calibre plugin, rename this file so that the filename
-# ends in '_plugin.py', put it into a ZIP file with all its supporting python routines
-# and import that ZIP into Calibre using its plugin configuration GUI.
-
-
-__version__ = '2.8'
-
-class Unbuffered:
-    def __init__(self, stream):
-        self.stream = stream
-    def write(self, data):
-        self.stream.write(data)
-        self.stream.flush()
-    def __getattr__(self, attr):
-        return getattr(self.stream, attr)
-
-import sys
-import os, csv, getopt
-import string
-import binascii
-import zlib
-import re
-import zlib, zipfile, tempfile, shutil
-from struct import pack, unpack, unpack_from
-
-class DrmException(Exception):
-    pass
-
-if 'calibre' in sys.modules:
-    inCalibre = True
-else:
-    inCalibre = False
-
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
-
-# cleanup bytestring filenames
-# borrowed from calibre from calibre/src/calibre/__init__.py
-# added in removal of non-printing chars
-# and removal of . at start
-# convert spaces to underscores
-def cleanup_name(name):
-    _filename_sanitize = re.compile(r'[\xae\0\\|\?\*<":>\+/]')
-    substitute='_'
-    one = ''.join(char for char in name if char in string.printable)
-    one = _filename_sanitize.sub(substitute, one)
-    one = re.sub(r'\s', ' ', one).strip()
-    one = re.sub(r'^\.+$', '_', one)
-    one = one.replace('..', substitute)
-    # Windows doesn't like path components that end with a period
-    if one.endswith('.'):
-        one = one[:-1]+substitute
-    # Mac and Unix don't like file names that begin with a full stop
-    if len(one) > 0 and one[0] == '.':
-        one = substitute+one[1:]
-    one = one.replace(' ','_')
-    return one
-
-def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
-    import mobidedrm
-    import topazextract
-    import kgenpids
-
-    # handle the obvious cases at the beginning
-    if not os.path.isfile(infile):
-        print "Error: Input file does not exist"
-        return 1
-
-    mobi = True
-    magic3 = file(infile,'rb').read(3)
-    if magic3 == 'TPZ':
-        mobi = False
-
-    bookname = os.path.splitext(os.path.basename(infile))[0]
-
-    if mobi:
-        mb = mobidedrm.MobiBook(infile)
-    else:
-        tempdir = tempfile.mkdtemp()
-        mb = topazextract.TopazBook(infile, tempdir)
-
-    title = mb.getBookTitle()
-    print "Processing Book: ", title
-    filenametitle = cleanup_name(title)
-    outfilename = bookname
-    if len(bookname)>4 and len(filenametitle)>4 and bookname[:4] != filenametitle[:4]:
-        outfilename = outfilename + "_" + filenametitle
-
-    # build pid list
-    md1, md2 = mb.getPIDMetaInfo()
-    pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
-
-    try:
-        if mobi:
-            unlocked_file = mb.processBook(pidlst)
-        else:
-            mb.processBook(pidlst)
-
-    except mobidedrm.DrmException, e:
-        print "Error: " + str(e) + "\nDRM Removal Failed.\n"
-        return 1
-    except Exception, e:
-        if not mobi:
-            print "Error: " + str(e) + "\nDRM Removal Failed.\n"
-            print "   Creating DeBug Full Zip Archive of Book"
-            zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-            myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-            zipUpDir(myzip, tempdir, '')
-            myzip.close()
-            shutil.rmtree(tempdir, True)
-            return 1
-        pass
-
-    if mobi:
-        outfile = os.path.join(outdir,outfilename + '_nodrm' + '.mobi')
-        file(outfile, 'wb').write(unlocked_file)
-        return 0            
-
-    # topaz:  build up zip archives of results
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
-
-    print "   Creating SVG ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
-
-    print "   Creating XML ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
-
-    shutil.rmtree(tempdir, True)
-    return 0
-
-
-def usage(progname):
-    print "Removes DRM protection from K4PC/M, Kindle, Mobi and Topaz ebooks"
-    print "Usage:"
-    print "    %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir>  " % progname
-
-#
-# Main
-#   
-def main(argv=sys.argv):
-    progname = os.path.basename(argv[0])
-
-    k4 = False
-    kInfoFiles = []
-    serials = []
-    pids = []
-    
-    print ('K4MobiDeDrm v%(__version__)s '
-	   'provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc .' % globals())
-
-    print ' '
-    try:
-        opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
-    except getopt.GetoptError, err:
-        print str(err)
-        usage(progname)
-        sys.exit(2)
-    if len(args)<2:
-        usage(progname)
-        sys.exit(2)
-        
-    for o, a in opts:
-        if o == "-k":
-            if a == None :
-                raise DrmException("Invalid parameter for -k")
-            kInfoFiles.append(a)
-        if o == "-p":
-            if a == None :
-                raise DrmException("Invalid parameter for -p")
-            pids = a.split(',')
-        if o == "-s":
-            if a == None :
-                raise DrmException("Invalid parameter for -s")
-            serials = a.split(',')
-
-    # try with built in Kindle Info files
-    k4 = True
-    if sys.platform.startswith('linux'):
-	k4 = False
-	kInfoFiles = None
-    infile = args[0]
-    outdir = args[1]
-
-    return decryptBook(infile, outdir, k4, kInfoFiles, serials, pids)
-
-
-if __name__ == '__main__':
-    sys.stdout=Unbuffered(sys.stdout)
-    sys.exit(main())
-
-if not __name__ == "__main__" and inCalibre:
-    from calibre.customize import FileTypePlugin
-
-    class K4DeDRM(FileTypePlugin):
-        name                = 'K4PC, K4Mac, Kindle Mobi and Topaz DeDRM' # Name of the plugin
-        description         = 'Removes DRM from K4PC and Mac, Kindle Mobi and Topaz files. \
-                                Provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc.'
-        supported_platforms = ['osx', 'windows', 'linux'] # Platforms this plugin will run on
-        author              = 'DiapDealer, SomeUpdates' # The author of this plugin
-        version             = (0, 2, 8)   # The version number of this plugin
-        file_types          = set(['prc','mobi','azw','azw1','tpz']) # The file types that this plugin will be applied to
-        on_import           = True # Run this plugin during the import
-        priority            = 210  # run this plugin before mobidedrm, k4pcdedrm, k4dedrm
-
-        def run(self, path_to_ebook):
-            from calibre.gui2 import is_ok_to_use_qt
-            from PyQt4.Qt import QMessageBox
-            from calibre.ptempfile import PersistentTemporaryDirectory
-
-            import kgenpids
-            import zlib
-            import zipfile
-            import topazextract
-            import mobidedrm
-
-            k4 = True
-	    if sys.platform.startswith('linux'):
-		k4 = False
-            pids = []
-            serials = []
-            kInfoFiles = []
-
-            # Get supplied list of PIDs to try from plugin customization.
-            customvalues = self.site_customization.split(',')
-            for customvalue in customvalues:
-                customvalue = str(customvalue)
-                customvalue = customvalue.strip()
-            	if len(customvalue) == 10 or len(customvalue) == 8:
-                    pids.append(customvalue)
-            	else :
-                    if len(customvalue) == 16 and customvalue[0] == 'B':
-                        serials.append(customvalue)
-                    else:
-                        print "%s is not a valid Kindle serial number or PID." % str(customvalue)
-            		
-            # Load any kindle info files (*.info) included Calibre's config directory.
-            try:
-                # Find Calibre's configuration directory.
-                confpath = os.path.split(os.path.split(self.plugin_path)[0])[0]
-                print 'K4MobiDeDRM: Calibre configuration directory = %s' % confpath
-                files = os.listdir(confpath)
-                filefilter = re.compile("\.info$", re.IGNORECASE)
-                files = filter(filefilter.search, files)
-    
-                if files:
-                    for filename in files:
-                        fpath = os.path.join(confpath, filename)
-                        kInfoFiles.append(fpath)
-                        print 'K4MobiDeDRM: Kindle info file %s found in config folder.' % filename
-            except IOError:
-                print 'K4MobiDeDRM: Error reading kindle info files from config directory.'
-                pass
-
-
-            mobi = True
-            magic3 = file(path_to_ebook,'rb').read(3)
-            if magic3 == 'TPZ':
-                mobi = False
-
-            bookname = os.path.splitext(os.path.basename(path_to_ebook))[0]
-
-            if mobi:
-                mb = mobidedrm.MobiBook(path_to_ebook)
-            else:
-                tempdir = PersistentTemporaryDirectory()
-                mb = topazextract.TopazBook(path_to_ebook, tempdir)
-
-            title = mb.getBookTitle()
-            md1, md2 = mb.getPIDMetaInfo()
-            pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
-
-            try:
-                if mobi:
-                    unlocked_file = mb.processBook(pidlst)
-                else:
-                    mb.processBook(pidlst)
-
-            except mobidedrm.DrmException:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-            except topazextract.TpzDRMError:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-
-            print "Success!"
-            if mobi:
-                of = self.temporary_file(bookname+'.mobi')
-                of.write(unlocked_file)
-                of.close()
-                return of.name
-
-            # topaz:  build up zip archives of results
-            print "   Creating HTML ZIP Archive"
-            of = self.temporary_file(bookname + '.zip')
-            myzip = zipfile.ZipFile(of.name,'w',zipfile.ZIP_DEFLATED, False)
-            myzip.write(os.path.join(tempdir,'book.html'),'book.html')
-            myzip.write(os.path.join(tempdir,'book.opf'),'book.opf')
-            if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-                myzip.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-            myzip.write(os.path.join(tempdir,'style.css'),'style.css')
-            zipUpDir(myzip, tempdir, 'img')
-            myzip.close()
-            return of.name
-
-        def customization_help(self, gui=False):
-            return 'Enter 10 character PIDs and/or Kindle serial numbers, separated by commas.'

Calibre_Plugins/k4mobidedrm_plugin/k4mutils.py

@@ -1,10 +1,13 @@
-# standlone set of Mac OSX specific routines needed for K4DeDRM
+# standlone set of Mac OSX specific routines needed for KindleBooks
 
 from __future__ import with_statement
+
 import sys
 import os
-import subprocess
+import os.path
 
+import subprocess
+from struct import pack, unpack, unpack_from
 
 class DrmException(Exception):
     pass
@@ -66,12 +69,9 @@ def _load_crypto_libcrypto():
                 raise DrmException('AES decryption failed')
             return out.raw
 
-        def keyivgen(self, passwd):
-            salt = '16743'
-            saltlen = 5
+        def keyivgen(self, passwd, salt, iter, keylen):
+            saltlen = len(salt)
             passlen = len(passwd)
-            iter = 0x3e8
-            keylen = 80
             out = create_string_buffer(keylen)
             rv = PKCS5_PBKDF2_HMAC_SHA1(passwd, passlen, salt, saltlen, iter, keylen, out)
             return out.raw
@@ -91,13 +91,79 @@ LibCrypto = _load_crypto()
 # Utility Routines
 #
 
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA256(message):
+    ctx = hashlib.sha256()
+    ctx.update(message)
+    return ctx.digest()
 
 # Various character maps used to decrypt books. Probably supposed to act as obfuscation
 charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
 charMap2 = "ZB0bYyc1xDdW2wEV3Ff7KkPpL8UuGA4gz-Tme9Nn_tHh5SvXCsIiR6rJjQaqlOoM" 
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
 
+# For kinf approach of K4PC/K4Mac
+# On K4PC charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
+# For Mac they seem to re-use charMap2 here
+charMap5 = charMap2
+
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+# For .kinf approach of K4PC and now K4Mac
+# generate table of prime number less than or equal to int n
+def primes(n):
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
 
 
 # uses a sub process to get the Hard Drive Serial Number using ioreg
@@ -129,47 +195,223 @@ def GetVolumeSerialNumber():
                 foundIt = True
                 break
     if not foundIt:
-        sernum = '9999999999'
+        sernum = ''
     return sernum
 
+def GetUserHomeAppSupKindleDirParitionName():
+    home = os.getenv('HOME')
+    dpath =  home + '/Library/Application Support/Kindle'
+    cmdline = '/sbin/mount'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    disk = ''
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.startswith('/dev'):
+            (devpart, mpath) = resline.split(' on ')
+            dpart = devpart[5:]
+            pp = mpath.find('(')
+            if pp >= 0:
+                mpath = mpath[:pp-1]
+            if dpath.startswith(mpath):
+                disk = dpart
+    return disk
+
+# uses a sub process to get the UUID of the specified disk partition using ioreg
+def GetDiskPartitionUUID(diskpart):
+    uuidnum = os.getenv('MYUUIDNUMBER')
+    if uuidnum != None:
+        return uuidnum
+    cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    bsdname = None
+    uuidnum = None
+    foundIt = False
+    nest = 0
+    uuidnest = -1
+    partnest = -2
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.find('{') >= 0:
+            nest += 1
+        if resline.find('}') >= 0:
+            nest -= 1
+        pp = resline.find('"UUID" = "')
+        if pp >= 0:
+            uuidnum = resline[pp+10:-1]
+            uuidnum = uuidnum.strip()
+            uuidnest = nest
+            if partnest == uuidnest and uuidnest > 0:
+                foundIt = True
+                break
+        bb = resline.find('"BSD Name" = "')
+        if bb >= 0:
+            bsdname = resline[bb+14:-1]
+            bsdname = bsdname.strip()
+            if (bsdname == diskpart):
+                partnest = nest
+            else :
+                partnest = -2
+            if partnest == uuidnest and partnest > 0:
+                foundIt = True
+                break
+        if nest == 0:
+            partnest = -2
+            uuidnest = -1
+            uuidnum = None
+            bsdname = None
+    if not foundIt:
+        uuidnum = ''
+    return uuidnum
+    
+def GetMACAddressMunged():
+    macnum = os.getenv('MYMACNUM')
+    if macnum != None:
+        return macnum
+    cmdline = '/sbin/ifconfig en0'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    macnum = None
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        pp = resline.find('ether ')
+        if pp >= 0:
+            macnum = resline[pp+6:-1]
+            macnum = macnum.strip()
+            # print "original mac", macnum
+            # now munge it up the way Kindle app does
+            # by xoring it with 0xa5 and swapping elements 3 and 4
+            maclst = macnum.split(':')
+            n = len(maclst)
+            if n != 6:
+                fountIt = False
+                break
+            for i in range(6):
+                maclst[i] = int('0x' + maclst[i], 0)
+            mlst = [0x00, 0x00, 0x00, 0x00, 0x00, 0x00]
+            mlst[5] = maclst[5] ^ 0xa5
+            mlst[4] = maclst[3] ^ 0xa5
+            mlst[3] = maclst[4] ^ 0xa5
+            mlst[2] = maclst[2] ^ 0xa5
+            mlst[1] = maclst[1] ^ 0xa5
+            mlst[0] = maclst[0] ^ 0xa5
+            macnum = "%0.2x%0.2x%0.2x%0.2x%0.2x%0.2x" % (mlst[0], mlst[1], mlst[2], mlst[3], mlst[4], mlst[5])
+            foundIt = True
+            break
+    if not foundIt:
+        macnum = ''
+    return macnum
+
+
 # uses unix env to get username instead of using sysctlbyname 
 def GetUserName():
     username = os.getenv('USER')
     return username
 
 
-def encode(data, map):
-    result = ""
-    for char in data:
-        value = ord(char)
-        Q = (value ^ 0x80) // len(map)
-        R = value % len(map)
-        result += map[Q]
-        result += map[R]
-    return result
-
-import hashlib
-
-def SHA256(message):
-    ctx = hashlib.sha256()
-    ctx.update(message)
-    return ctx.digest()
-
 # implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used by Kindle for Mac versions < 1.6.0
 def CryptUnprotectData(encryptedData):
-    sp = GetVolumeSerialNumber() + '!@#' + GetUserName()
+    sernum = GetVolumeSerialNumber()
+    if sernum == '':
+        sernum = '9999999999'
+    sp = sernum + '!@#' + GetUserName()
     passwdData = encode(SHA256(sp),charMap1)
+    salt = '16743'
+    iter = 0x3e8
+    keylen = 0x80
     crp = LibCrypto()
-    key_iv = crp.keyivgen(passwdData)
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
     key = key_iv[0:32]
     iv = key_iv[32:48]
     crp.set_decrypt_key(key,iv)
     cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext,charMap1)
+    return cleartext
+
+
+def isNewInstall():
+    home = os.getenv('HOME')
+    # soccer game fan anyone
+    dpath = home + '/Library/Application Support/Kindle/storage/.pes2011'
+    # print dpath, os.path.exists(dpath)
+    if os.path.exists(dpath):
+        return True
+    return False
+    
+
+def GetIDString():
+    # K4Mac now has an extensive set of ids strings it uses
+    # in encoding pids and in creating unique passwords
+    # for use in its own version of CryptUnprotectDataV2
+
+    # BUT Amazon has now become nasty enough to detect when its app
+    # is being run under a debugger and actually changes code paths
+    # including which one of these strings is chosen, all to try 
+    # to prevent reverse engineering
+
+    # Sad really ... they will only hurt their own sales ...
+    # true book lovers really want to keep their books forever
+    # and move them to their devices and DRM prevents that so they 
+    # will just buy from someplace else that they can remove 
+    # the DRM from
+
+    # Amazon should know by now that true book lover's are not like
+    # penniless kids that pirate music, we do not pirate books
+
+    if isNewInstall():
+        mungedmac = GetMACAddressMunged()
+        if len(mungedmac) > 7:
+            return mungedmac
+    sernum = GetVolumeSerialNumber()
+    if len(sernum) > 7:
+        return sernum
+    diskpart = GetUserHomeAppSupKindleDirParitionName()
+    uuidnum = GetDiskPartitionUUID(diskpart)
+    if len(uuidnum) > 7:
+        return uuidnum
+    mungedmac = GetMACAddressMunged()
+    if len(mungedmac) > 7:
+        return mungedmac
+    return '9999999999'
+
+
+# implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used for Kindle for Mac Versions >= 1.6.0
+def CryptUnprotectDataV2(encryptedData):
+    sp = GetUserName() + ':&%:' + GetIDString()
+    passwdData = encode(SHA256(sp),charMap5)
+    # salt generation as per the code
+    salt = 0x0512981d * 2 * 1 * 1
+    salt = str(salt) + GetUserName()
+    salt = encode(salt,charMap5)
+    crp = LibCrypto()
+    iter = 0x800
+    keylen = 0x400
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
+    key = key_iv[0:32]
+    iv = key_iv[32:48]
+    crp.set_decrypt_key(key,iv)
+    cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext, charMap5)
     return cleartext
 
 
 # Locate the .kindle-info files
 def getKindleInfoFiles(kInfoFiles):
+    # first search for current .kindle-info files
     home = os.getenv('HOME')
     cmdline = 'find "' + home + '/Library/Application Support" -name ".kindle-info"'
     cmdline = cmdline.encode(sys.getfilesystemencoding())
@@ -178,23 +420,132 @@ def getKindleInfoFiles(kInfoFiles):
     reslst = out1.split('\n')
     kinfopath = 'NONE'
     found = False
-    cnt = len(reslst)
+    for resline in reslst:
+        if os.path.isfile(resline):
+            kInfoFiles.append(resline)
+            found = True
+    # add any .kinf files 
+    cmdline = 'find "' + home + '/Library/Application Support" -name ".rainier*-kinf"'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p1.communicate()
+    reslst = out1.split('\n')
     for resline in reslst:
         if os.path.isfile(resline):
             kInfoFiles.append(resline)
             found = True
     if not found:
-        print('No .kindle-info files have been found.')
+        print('No kindle-info files have been found.')
     return kInfoFiles
 
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
     DB = {}
+    cnt = 0
     infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
+    hdr = infoReader.read(1)
     data = infoReader.read()
-    items = data.split('[')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
+
+    if data.find('[') != -1 :
+        # older style kindle-info file
+        items = data.split('[')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                cleartext = CryptUnprotectData(encryptedValue)
+                DB[keyname] = cleartext
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file used by K4Mac >= 1.6.0
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+    
+        # get the first item record
+        item = items.pop(0)
+    
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+        keyname = "unknown"
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        # "entropy" not used for K4Mac only K4PC
+        # entropy = SHA1(keyhash)
+    
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+    
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+    
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+    
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+    
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+    
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        noffset = contlen - primes(int(contlen/3))[-1]
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+    
+        # decode using charMap5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        cleartext = CryptUnprotectDataV2(encryptedValue)
+        # Debugging
+        # print keyname
+        # print cleartext
+        # print cleartext.encode('hex')
+        # print
+        DB[keyname] = cleartext
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
     return DB

Calibre_Plugins/k4mobidedrm_plugin/k4pcutils.py

@@ -1,8 +1,10 @@
+#!/usr/bin/env python
 # K4PC Windows specific routines
 
 from __future__ import with_statement
 
 import sys, os
+from struct import pack, unpack, unpack_from
 
 from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
     create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
@@ -10,25 +12,86 @@ from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
 
 import _winreg as winreg
 
-import traceback
-
 MAX_PATH = 255
 
 kernel32 = windll.kernel32
 advapi32 = windll.advapi32
 crypt32 = windll.crypt32
 
+import traceback
 
-# Various character maps used to decrypt books. Probably supposed to act as obfuscation
-charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+
+# simple primes table (<= n) calculator
+def primes(n): 
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
+
+
+# Various character maps used to decrypt kindle info values.
+# Probably supposed to act as obfuscation
 charMap2 = "AaZzB0bYyCc1XxDdW2wEeVv3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_"
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
+charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
 
 class DrmException(Exception):
     pass
-    
 
+# Encode the bytes in data with the characters in map
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+  
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+
+# interface with Windows OS Routines
 class DataBlob(Structure):
     _fields_ = [('cbData', c_uint),
                 ('pbData', c_void_p)]
@@ -59,59 +122,187 @@ def GetVolumeSerialNumber():
     return GetVolumeSerialNumber
 GetVolumeSerialNumber = GetVolumeSerialNumber()
 
+def GetIDString():
+    return GetVolumeSerialNumber()
+
+def getLastError():
+    GetLastError = kernel32.GetLastError
+    GetLastError.argtypes = None
+    GetLastError.restype = c_uint
+    def getLastError():
+        return GetLastError()
+    return getLastError
+getLastError = getLastError()
 
 def GetUserName():
     GetUserNameW = advapi32.GetUserNameW
     GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
     GetUserNameW.restype = c_uint
     def GetUserName():
-        buffer = create_unicode_buffer(32)
+        buffer = create_unicode_buffer(2)
         size = c_uint(len(buffer))
         while not GetUserNameW(buffer, byref(size)):
+            errcd = getLastError()
+            if errcd == 234:
+                # bad wine implementation up through wine 1.3.21
+                return "AlternateUserName"
             buffer = create_unicode_buffer(len(buffer) * 2)
             size.value = len(buffer)
         return buffer.value.encode('utf-16-le')[::2]
     return GetUserName
 GetUserName = GetUserName()
 
-
 def CryptUnprotectData():
     _CryptUnprotectData = crypt32.CryptUnprotectData
     _CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
                                    c_void_p, c_void_p, c_uint, DataBlob_p]
     _CryptUnprotectData.restype = c_uint
-    def CryptUnprotectData(indata, entropy):
+    def CryptUnprotectData(indata, entropy, flags):
         indatab = create_string_buffer(indata)
         indata = DataBlob(len(indata), cast(indatab, c_void_p))
         entropyb = create_string_buffer(entropy)
         entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
         outdata = DataBlob()
         if not _CryptUnprotectData(byref(indata), None, byref(entropy),
-                                   None, None, 0, byref(outdata)):
+                                   None, None, flags, byref(outdata)):
             raise DrmException("Failed to Unprotect Data")
         return string_at(outdata.pbData, outdata.cbData)
     return CryptUnprotectData
 CryptUnprotectData = CryptUnprotectData()
 
-# Locate the .kindle-info files
+
+# Locate all of the kindle-info style files and return as list
 def getKindleInfoFiles(kInfoFiles):
     regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders\\")
     path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
+
+    # first look for older kindle-info files
     kinfopath = path +'\\Amazon\\Kindle For PC\\{AMAwzsaPaaZAzmZzZQzgZCAkZ3AjA_AY}\\kindle.info'
     if not os.path.isfile(kinfopath):
-        print('The kindle.info files has not been found.')
+        print('No kindle.info files have not been found.')
     else:
         kInfoFiles.append(kinfopath)
+
+    # now look for newer (K4PC 1.5.0 and later rainier.2.1.1.kinf file
+
+    kinfopath = path +'\\Amazon\\Kindle For PC\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.5.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
+    # now look for even newer (K4PC 1.6.0 and later) rainier.2.1.1.kinf file
+    kinfopath = path +'\\Amazon\\Kindle\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.6.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
     return kInfoFiles
 
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
+
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
     DB = {}
+    cnt = 0
     infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
+    hdr = infoReader.read(1)
     data = infoReader.read()
-    items = data.split('{')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
+
+    if data.find('{') != -1 :
+
+        # older style kindle-info file
+        items = data.split('{')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                DB[keyname] = CryptUnprotectData(encryptedValue, "", 0)
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+
+        # get the first item record
+        item = items.pop(0)
+
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        entropy = SHA1(keyhash)
+
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+        noffset = contlen - primes(int(contlen/3))[-1]
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+
+        # decode using Map5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        DB[keyname] = CryptUnprotectData(encryptedValue, entropy, 1)
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
     return DB
+
+

Calibre_Plugins/k4mobidedrm_plugin/mobidedrm.py

@@ -49,10 +49,13 @@
 #  0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
 #  0.28 - slight additional changes to metadata token generation (None -> '')
 #  0.29 - It seems that the ideas about when multibyte trailing characters were
-#         included in the encryption were wrong. They aren't for DOC compressed
-#         files, but they are for HUFF/CDIC compress files!
+#         included in the encryption were wrong. They are for DOC compressed
+#         files, but they are not for HUFF/CDIC compress files!
+#  0.30 - Modified interface slightly to work better with new calibre plugin style
+#  0.31 - The multibyte encrytion info is true for version 7 files too.
+#  0.32 - Added support for "Print Replica" Kindle ebooks
 
-__version__ = '0.29'
+__version__ = '0.32'
 
 import sys
 
@@ -161,8 +164,12 @@ class MobiBook:
         return self.data_file[off:endoff]
 
     def __init__(self, infile):
+        print ('MobiDeDrm v%(__version__)s. '
+           'Copyright 2008-2011 The Dark Reverser et al.' % globals())
+
         # initial sanity check on file
         self.data_file = file(infile, 'rb').read()
+        self.mobi_data = ''
         self.header = self.data_file[0:78]
         if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
             raise DrmException("invalid file format")
@@ -190,14 +197,15 @@ class MobiBook:
             self.meta_array = {}
             return
         self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
+        self.mobi_codepage, = struct.unpack('>L',self.sect[0x1c:0x20])
         self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
         print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
         self.extra_data_flags = 0
         if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
             self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
             print "Extra Data Flags = %d" % self.extra_data_flags
-        if (self.mobi_version < 7) and (self.compression != 17480):
-            # multibyte utf8 data is included in the encryption for mobi_version 6 and below
+        if (self.compression != 17480):
+            # multibyte utf8 data is included in the encryption for PalmDoc compression
             # so clear that byte so that we leave it to be decrypted.
             self.extra_data_flags &= 0xFFFE
 
@@ -227,8 +235,13 @@ class MobiBook:
         except:
             self.meta_array = {}
             pass
+        self.print_replica = False
             
     def getBookTitle(self):
+        codec_map = {
+            1252 : 'windows-1252',
+            65001 : 'utf-8',
+        }
         title = ''
         if 503 in self.meta_array:
             title = self.meta_array[503]
@@ -239,7 +252,10 @@ class MobiBook:
         if title == '':
             title = self.header[:32]
             title = title.split("\0")[0]
-        return title
+        codec = 'windows-1252'
+        if self.mobi_codepage in codec_map.keys():
+            codec = codec_map[self.mobi_codepage]
+        return unicode(title, codec).encode('utf-8')
 
     def getPIDMetaInfo(self):
         rec209 = ''
@@ -301,15 +317,29 @@ class MobiBook:
                         break
         return [found_key,pid]
 
+    def getMobiFile(self, outpath):
+        file(outpath,'wb').write(self.mobi_data)
+        
+    def getPrintReplica(self):
+        return self.print_replica
+
     def processBook(self, pidlist):
         crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
         print 'Crypto Type is: ', crypto_type
         self.crypto_type = crypto_type
         if crypto_type == 0:
             print "This book is not encrypted."
-            return self.data_file
+            # we must still check for Print Replica
+            self.print_replica = (self.loadSection(1)[0:4] == '%MOP')
+            self.mobi_data = self.data_file
+            return
         if crypto_type != 2 and crypto_type != 1:
             raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
+        if 406 in self.meta_array:
+            data406 = self.meta_array[406]
+            val406, = struct.unpack('>Q',data406)
+            if val406 != 0:
+                raise DrmException("Cannot decode library or rented ebooks.")
 
         goodpids = []
         for pid in pidlist:
@@ -353,39 +383,44 @@ class MobiBook:
 
         # decrypt sections
         print "Decrypting. Please wait . . .",
-        new_data = self.data_file[:self.sections[1][0]]
+        self.mobi_data = self.data_file[:self.sections[1][0]]
         for i in xrange(1, self.records+1):
             data = self.loadSection(i)
             extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
             if i%100 == 0:
                 print ".",
             # print "record %d, extra_size %d" %(i,extra_size)
-            new_data += PC1(found_key, data[0:len(data) - extra_size])
+            decoded_data = PC1(found_key, data[0:len(data) - extra_size])
+            if i==1:
+                self.print_replica = (decoded_data[0:4] == '%MOP')
+            self.mobi_data += decoded_data
             if extra_size > 0:
-                new_data += data[-extra_size:]
+                self.mobi_data += data[-extra_size:]
         if self.num_sections > self.records+1:
-            new_data += self.data_file[self.sections[self.records+1][0]:]
-        self.data_file = new_data
+            self.mobi_data += self.data_file[self.sections[self.records+1][0]:]
         print "done"
-        return self.data_file
+        return
 
 def getUnencryptedBook(infile,pid):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook([pid])
+    book.processBook([pid])
+    return book.mobi_data
 
 def getUnencryptedBookWithList(infile,pidlist):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook(pidlist)
+    book.processBook(pidlist)
+    return book.mobi_data
+
 
 def main(argv=sys.argv):
     print ('MobiDeDrm v%(__version__)s. '
-	   'Copyright 2008-2010 The Dark Reverser.' % globals())
+        'Copyright 2008-2011 The Dark Reverser et al.' % globals())
     if len(argv)<3 or len(argv)>4:
-        print "Removes protection from Mobipocket books"
+        print "Removes protection from Kindle/Mobipocket and Kindle/Print Replica ebooks"
         print "Usage:"
         print "    %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
         return 1
@@ -393,9 +428,9 @@ def main(argv=sys.argv):
         infile = argv[1]
         outfile = argv[2]
         if len(argv) is 4:
-        	pidlist = argv[3].split(',')
+            pidlist = argv[3].split(',')
         else:
-        	pidlist = {}
+            pidlist = {}
         try:
             stripped_file = getUnencryptedBookWithList(infile, pidlist)
             file(outfile, 'wb').write(stripped_file)

DeDRM_Macintosh_Application/DeDRM.app/Contents/Info.plist

@@ -24,17 +24,17 @@
 	<key>CFBundleExecutable</key>
 	<string>droplet</string>
 	<key>CFBundleGetInfoString</key>
-	<string>DeDRM 2.6, Written 2010–2011 by Apprentice Alf and others.</string>
+	<string>DeDRM 3.1, Written 2010–2011 by Apprentice Alf and others.</string>
 	<key>CFBundleIconFile</key>
 	<string>droplet</string>
 	<key>CFBundleInfoDictionaryVersion</key>
 	<string>6.0</string>
 	<key>CFBundleName</key>
-	<string>DeDRM</string>
+	<string>DeDRM 3.1</string>
 	<key>CFBundlePackageType</key>
 	<string>APPL</string>
 	<key>CFBundleShortVersionString</key>
-	<string>2.6</string>
+	<string>3.1</string>
 	<key>CFBundleSignature</key>
 	<string>dplt</string>
 	<key>LSMinimumSystemVersion</key>
@@ -44,15 +44,15 @@
 	<key>WindowState</key>
 	<dict>
 		<key>dividerCollapsed</key>
-		<true/>
+		<false/>
 		<key>eventLogLevel</key>
 		<integer>-1</integer>
 		<key>name</key>
 		<string>ScriptWindowState</string>
 		<key>positionOfDivider</key>
-		<real>0</real>
+		<real>460</real>
 		<key>savedFrame</key>
-		<string>1578 27 862 788 1440 -150 1680 1050 </string>
+		<string>39 106 1316 746 0 0 1440 878 </string>
 		<key>selectedTabView</key>
 		<string>event log</string>
 	</dict>

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/convert2xml.py

@@ -20,6 +20,8 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # Get a 7 bit encoded number from string. The most 
 # significant byte comes first and has the high bit (8th) set
@@ -138,7 +140,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside of string table limits')
+            # sys.exit(-1)
 
     def getSize(self):
         return self.size
@@ -258,6 +261,11 @@ class PageParser(object):
         'paragraph.class'     : (1, 'scalar_text', 0, 0),
         'paragraph.firstWord' : (1, 'scalar_number', 0, 0),
         'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridSize'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridTopCenter' : (1, 'scalar_number', 0, 0),
+
 
         'word_semantic'           : (1, 'snippets', 1, 1),
         'word_semantic.type'      : (1, 'scalar_text', 0, 0),
@@ -272,11 +280,17 @@ class PageParser(object):
 
         '_span'           : (1, 'snippets', 1, 0),
         '_span.firstWord' : (1, 'scalar_number', 0, 0),
-        '-span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.gridSize'  : (1, 'scalar_number', 0, 0),
+        '_span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        '_span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'span'           : (1, 'snippets', 1, 0),
         'span.firstWord' : (1, 'scalar_number', 0, 0),
         'span.lastWord'  : (1, 'scalar_number', 0, 0),
+        'span.gridSize'  : (1, 'scalar_number', 0, 0),
+        'span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'extratokens'            : (1, 'snippets', 1, 0),
         'extratokens.type'       : (1, 'scalar_text', 0, 0),

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/description.rtfd/TXT.rtf

@@ -1,4 +1,4 @@
-{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf350
+{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf360
 {\fonttbl}
 {\colortbl;\red255\green255\blue255;}
 }

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/erdr2pml.py

@@ -58,8 +58,12 @@
 #  0.17 - added support for pycrypto's DES as well
 #  0.18 - on Windows try PyCrypto first and OpenSSL next
 #  0.19 - Modify the interface to allow use of import
+#  0.20 - modify to allow use inside new interface for calibre plugins
+#  0.21 - Support eReader (drm) version 11. 
+#       - Don't reject dictionary format. 
+#       - Ignore sidebars for dictionaries (different format?)
 
-__version__='0.19'
+__version__='0.21'
 
 class Unbuffered:
     def __init__(self, stream):
@@ -71,32 +75,50 @@ class Unbuffered:
         return getattr(self.stream, attr)
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
-
 import struct, binascii, getopt, zlib, os, os.path, urllib, tempfile
 
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
 Des = None
 if sys.platform.startswith('win'):
     # first try with pycrypto
-    import pycrypto_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import pycrypto_des
+    else:
+        import pycrypto_des
     Des = pycrypto_des.load_pycrypto()
     if Des == None:
         # they try with openssl
-        import openssl_des
+        if inCalibre:
+            from calibre_plugins.erdrpdb2pml import openssl_des
+        else:
+            import openssl_des
         Des = openssl_des.load_libcrypto()
 else:
     # first try with openssl
-    import openssl_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import openssl_des
+    else:
+        import openssl_des
     Des = openssl_des.load_libcrypto()
     if Des == None:
         # then try with pycrypto
-        import pycrypto_des
+        if inCalibre:
+            from calibre_plugins.erdrpdb2pml import pycrypto_des
+        else:
+            import pycrypto_des
         Des = pycrypto_des.load_pycrypto()
 
 # if that did not work then use pure python implementation
 # of DES and try to speed it up with Psycho
 if Des == None:
-    import python_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import python_des
+    else:
+        import python_des
     Des = python_des.Des
     # Import Psyco if available
     try:
@@ -121,12 +143,18 @@ logging.basicConfig()
 
 
 class Sectionizer(object):
+    bkType = "Book"
+
     def __init__(self, filename, ident):
         self.contents = file(filename, 'rb').read()
         self.header = self.contents[0:72]
         self.num_sections, = struct.unpack('>H', self.contents[76:78])
+        # Dictionary or normal content (TODO: Not hard-coded)
         if self.header[0x3C:0x3C+8] != ident:
-            raise ValueError('Invalid file format')
+            if self.header[0x3C:0x3C+8] == "PDctPPrs":
+                self.bkType = "Dict"
+            else:
+                raise ValueError('Invalid file format')
         self.sections = []
         for i in xrange(self.num_sections):
             offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.contents[78+i*8:78+i*8+8])
@@ -163,15 +191,15 @@ def deXOR(text, sp, table):
     return r
 
 class EreaderProcessor(object):
-    def __init__(self, section_reader, username, creditcard):
-        self.section_reader = section_reader
-        data = section_reader(0)
+    def __init__(self, sect, username, creditcard):
+        self.section_reader = sect.loadSection
+        data = self.section_reader(0)
         version,  = struct.unpack('>H', data[0:2])
         self.version = version
         logging.info('eReader file format version %s', version)
         if version != 272 and version != 260 and version != 259:
             raise ValueError('incorrect eReader version %d (error 1)' % version)
-        data = section_reader(1)
+        data = self.section_reader(1)
         self.data = data
         des = Des(fixKey(data[0:8]))
         cookie_shuf, cookie_size = struct.unpack('>LL', des.decrypt(data[-8:]))
@@ -200,11 +228,17 @@ class EreaderProcessor(object):
         self.num_text_pages = struct.unpack('>H', r[2:4])[0] - 1
         self.num_image_pages = struct.unpack('>H', r[26:26+2])[0]
         self.first_image_page = struct.unpack('>H', r[24:24+2])[0]
+        # Default values
+        self.num_footnote_pages = 0
+        self.num_sidebar_pages = 0
+        self.first_footnote_page = -1
+        self.first_sidebar_page = -1
         if self.version == 272:
             self.num_footnote_pages = struct.unpack('>H', r[46:46+2])[0]
             self.first_footnote_page = struct.unpack('>H', r[44:44+2])[0]
-            self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
-            self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
+            if (sect.bkType == "Book"):
+                self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
+                self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
             # self.num_bookinfo_pages = struct.unpack('>H', r[34:34+2])[0]
             # self.first_bookinfo_page = struct.unpack('>H', r[32:32+2])[0]
             # self.num_chapter_pages = struct.unpack('>H', r[22:22+2])[0]
@@ -220,10 +254,8 @@ class EreaderProcessor(object):
             self.xortable_size = struct.unpack('>H', r[42:42+2])[0]
             self.xortable = self.data[self.xortable_offset:self.xortable_offset + self.xortable_size]
         else:
-            self.num_footnote_pages = 0
-            self.num_sidebar_pages = 0
-            self.first_footnote_page = -1
-            self.first_sidebar_page = -1
+            # Nothing needs to be done
+            pass
             # self.num_bookinfo_pages = 0
             # self.num_chapter_pages = 0
             # self.num_link_pages = 0
@@ -248,10 +280,14 @@ class EreaderProcessor(object):
             encrypted_key_sha = r[44:44+20]
             encrypted_key = r[64:64+8]
         elif version == 260:
-            if drm_sub_version != 13:
+            if drm_sub_version != 13 and drm_sub_version != 11:
                 raise ValueError('incorrect eReader version %d (error 3)' % drm_sub_version)
-            encrypted_key = r[44:44+8]
-            encrypted_key_sha = r[52:52+20]
+            if drm_sub_version == 13:
+                encrypted_key = r[44:44+8]
+                encrypted_key_sha = r[52:52+20]
+            else:
+                encrypted_key = r[64:64+8]
+                encrypted_key_sha = r[44:44+20]
         elif version == 272:
             encrypted_key = r[172:172+8]
             encrypted_key_sha = r[56:56+20]
@@ -337,6 +373,12 @@ class EreaderProcessor(object):
                 r += fmarker
                 fnote_ids = fnote_ids[id_len+4:]
 
+        # TODO: Handle dictionary index (?) pages - which are also marked as
+        # sidebar_pages (?). For now dictionary sidebars are ignored
+        # For dictionaries - record 0 is null terminated strings, followed by
+        # blocks of around 62000 bytes and a final block. Not sure of the
+        # encoding
+
         # now handle sidebar pages
         if self.num_sidebar_pages > 0:
             r += '\n'
@@ -349,7 +391,7 @@ class EreaderProcessor(object):
                 id_len = ord(sbar_ids[2])
                 id = sbar_ids[3:3+id_len]
                 smarker = '<sidebar id="%s">\n' % id
-                smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_footnote_page + i)))
+                smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_sidebar_page + i)))
                 smarker += '\n</sidebar>\n'
                 r += smarker
                 sbar_ids = sbar_ids[id_len+4:]
@@ -370,7 +412,7 @@ def convertEreaderToPml(infile, name, cc, outdir):
     bookname = os.path.splitext(os.path.basename(infile))[0]
     print "   Decoding File"
     sect = Sectionizer(infile, 'PNRdPPrs')
-    er = EreaderProcessor(sect.loadSection, name, cc)
+    er = EreaderProcessor(sect, name, cc)
 
     if er.getNumImages() > 0:
         print "   Extracting images"
@@ -480,5 +522,6 @@ def main(argv=None):
 
 
 if __name__ == "__main__":
+    sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/flatxml2html.py

@@ -271,6 +271,9 @@ class DocParser(object):
 
         pclass = self.getClass(pclass)
 
+        # if paragraph uses extratokens (extra glyphs) then make it fixed
+        (pos, extraglyphs) = self.findinDoc('paragraph.extratokens',start,end)
+
         # build up a description of the paragraph in result and return it
         # first check for the  basic - all words paragraph
         (pos, sfirst) = self.findinDoc('paragraph.firstWord',start,end)
@@ -280,6 +283,7 @@ class DocParser(object):
             last = int(slast)
             
             makeImage = (regtype == 'vertical') or (regtype == 'table')
+            makeImage = makeImage or (extraglyphs != None) 
             if self.fixedimage:
                 makeImage = makeImage or (regtype == 'fixed')
 
@@ -353,6 +357,8 @@ class DocParser(object):
 
         word_class = ''
 
+        word_semantic_type = ''
+
         while (line < end) :
 
             (name, argres) = self.lineinDoc(line)
@@ -512,6 +518,72 @@ class DocParser(object):
         return parares
 
 
+    def buildTOCEntry(self, pdesc) :
+        parares = ''
+        sep =''
+        tocentry = ''
+        handle_links = len(self.link_id) > 0
+
+        lstart = 0
+
+        cnt = len(pdesc)
+        for j in xrange( 0, cnt) :
+
+            (wtype, num) = pdesc[j]
+
+            if wtype == 'ocr' :
+                word = self.ocrtext[num]
+                sep = ' '
+
+                if handle_links:
+                    link = self.link_id[num]
+                    if (link > 0):
+                        linktype = self.link_type[link-1]
+                        title = self.link_title[link-1]
+                        title = title.rstrip('. ')
+                        alt_title = parares[lstart:]
+                        alt_title = alt_title.strip()
+                        # now strip off the actual printed page number
+                        alt_title = alt_title.rstrip('01234567890ivxldIVXLD-.')
+                        alt_title = alt_title.rstrip('. ')
+                        # skip over any external links - can't have them in a books toc
+                        if linktype == 'external' :
+                            title = ''
+                            alt_title = ''
+                            linkpage = ''
+                        else : 
+                            if len(self.link_page) >= link :
+                                ptarget = self.link_page[link-1] - 1
+                                linkpage = '%04d' % ptarget
+                            else :
+                                # just link to the current page
+                                linkpage = self.id[4:]
+                        if len(alt_title) >= len(title):
+                            title = alt_title
+                        if title != '' and linkpage != '':
+                            tocentry += title + '|' + linkpage + '\n'
+                        lstart = len(parares)
+                        if word == '_link_' : word = ''
+                    elif (link < 0) :
+                        if word == '_link_' : word = ''
+
+                if word == '_lb_':
+                    word = ''
+                    sep = ''
+
+                if num in self.dehyphen_rootid :
+                    word = word[0:-1]
+                    sep = ''
+
+                parares += word + sep
+
+            else :
+                continue
+
+        return tocentry
+
+
+
     
     # walk the document tree collecting the information needed
     # to build an html page using the ocrText
@@ -519,6 +591,7 @@ class DocParser(object):
     def process(self):
 
         htmlpage = ''
+        tocinfo = ''
 
         # get the ocr text
         (pos, argres) = self.findinDoc('info.word.ocrText',0,-1)
@@ -644,9 +717,9 @@ class DocParser(object):
                         ptype = 'end'
                         first_para_continued = False
                     (pclass, pdesc) = self.getParaDescription(start,end, regtype)
+                    tocinfo += self.buildTOCEntry(pdesc)
                     htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
 
-
                 elif (regtype == 'vertical') or (regtype == 'table') :
                     ptype = 'full'
                     if inGroup:
@@ -704,12 +777,11 @@ class DocParser(object):
                 htmlpage = htmlpage[0:-4]
             last_para_continued = False
 
-        return htmlpage
-
+        return htmlpage, tocinfo
 
 
 def convert2HTML(flatxml, classlst, fileid, bookDir, gdict, fixedimage):
     # create a document parser
     dp = DocParser(flatxml, classlst, fileid, bookDir, gdict, fixedimage)
-    htmlpage = dp.process()
-    return htmlpage
+    htmlpage, tocinfo = dp.process()
+    return htmlpage, tocinfo

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/flatxml2svg.py

@@ -10,17 +10,94 @@ from struct import unpack
 
 
 class PParser(object):
-    def __init__(self, gd, flatxml):
+    def __init__(self, gd, flatxml, meta_array):
         self.gd = gd
         self.flatdoc = flatxml.split('\n')
+        self.docSize = len(self.flatdoc)
         self.temp = []
-        foo = self.getData('page.h') or self.getData('book.h')
-        self.ph = foo[0]
-        foo = self.getData('page.w') or self.getData('book.w')
-        self.pw = foo[0]
-        self.gx = self.getData('info.glyph.x')
-        self.gy = self.getData('info.glyph.y')
-        self.gid = self.getData('info.glyph.glyphID')
+        
+        self.ph = -1
+        self.pw = -1
+        startpos = self.posinDoc('page.h') or self.posinDoc('book.h')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.ph = max(self.ph, int(argres))
+        startpos = self.posinDoc('page.w') or self.posinDoc('book.w')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.pw = max(self.pw, int(argres))
+        
+        if self.ph <= 0:
+            self.ph = int(meta_array.get('pageHeight', '11000'))
+        if self.pw <= 0:
+            self.pw = int(meta_array.get('pageWidth', '8500'))
+
+        res = []
+        startpos = self.posinDoc('info.glyph.x')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.x', p)
+            res.extend(argres)
+        self.gx = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.y')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.y', p)
+            res.extend(argres)
+        self.gy = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.glyphID')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.glyphID', p)
+            res.extend(argres)
+        self.gid = res
+
+
+    # return tag at line pos in document
+    def lineinDoc(self, pos) :
+        if (pos >= 0) and (pos < self.docSize) :
+            item = self.flatdoc[pos]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+        return name, argres
+
+    # find tag in doc if within pos to end inclusive
+    def findinDoc(self, tagpath, pos, end) :
+        result = None
+        if end == -1 :
+            end = self.docSize
+        else:
+            end = min(self.docSize, end)
+        foundat = -1
+        for j in xrange(pos, end):
+            item = self.flatdoc[j]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+            if name.endswith(tagpath) :
+                result = argres
+                foundat = j
+                break
+        return foundat, result
+
+    # return list of start positions for the tagpath
+    def posinDoc(self, tagpath):
+        startpos = []
+        pos = 0
+        res = ""
+        while res != None :
+            (foundpos, res) = self.findinDoc(tagpath, pos, -1)
+            if res != None :
+                startpos.append(foundpos)
+            pos = foundpos + 1
+        return startpos
+
     def getData(self, path):
         result = None
         cnt = len(self.flatdoc)
@@ -39,6 +116,23 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
+    def getDataatPos(self, path, pos):
+        result = None
+        item = self.flatdoc[pos]
+        if item.find('=') >= 0:
+            (name, argt) = item.split('=')
+            argres = argt.split('|')
+        else:
+            name = item
+            argres = []
+        if (len(argres) > 0) :
+            for j in xrange(0,len(argres)):
+                argres[j] = int(argres[j])
+        if (name.endswith(path)):
+            result = argres
+        return result
+
     def getDataTemp(self, path):
         result = None
         cnt = len(self.temp)
@@ -58,6 +152,7 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
     def getImages(self):
         result = []
         self.temp = self.flatdoc
@@ -69,6 +164,7 @@ class PParser(object):
             src = self.getDataTemp('img.src')[0]
             result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
         return result
+
     def getGlyphs(self):
         result = []
         if (self.gid != None) and (len(self.gid) > 0):
@@ -84,25 +180,25 @@ class PParser(object):
         return result
 
 
-def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi):
+def convert2SVG(gdict, flat_xml, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi):
     ml = ''
-    pp = PParser(gdict, flat_xml)
+    pp = PParser(gdict, flat_xml, meta_array)
     ml += '<?xml version="1.0" standalone="no"?>\n'
     if (raw):
         ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
         ml += '<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1)
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
     else:
         ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
         ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
         ml += '<script><![CDATA[\n'
         ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
         ml += 'var dpi=%d;\n' % scaledpi
-        if (counter) :
-            ml += 'var prevpage="page%04d.xhtml";\n' % (counter - 1)
-        if (counter < numfiles-1) :
-            ml += 'var nextpage="page%04d.xhtml";\n' % (counter + 1)
+        if (previd) :
+            ml += 'var prevpage="page%04d.xhtml";\n' % (previd)
+        if (nextid) :
+            ml += 'var nextpage="page%04d.xhtml";\n' % (nextid)
         ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
         ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
         ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
@@ -115,10 +211,11 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         ml += '</head>\n'
         ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
         ml += '<div style="white-space:nowrap;">\n'
-        if (counter == 0) :
+        if previd == None:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n'
+        
         ml += '<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph)
     if (pp.gid != None): 
         ml += '<defs>\n'
@@ -134,12 +231,14 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         for j in xrange(0,len(pp.gid)):
             ml += '<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j])
     if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
-        ml += '<text x="10" y="10" font-family="Helvetica" font-size="100" stroke="black">This page intentionally left blank.</text>\n<text x="10" y="110" font-family="Helvetica" font-size="50" stroke="black">Until this notice unintentionally gave it content.  (gensvg.py)</text>\n'
+        xpos = "%d" % (pp.pw // 3)
+        ypos = "%d" % (pp.ph // 3)
+        ml += '<text x="' + xpos + '" y="' + ypos + '" font-size="' + meta_array['fontSize'] + '" font-family="Helvetica" stroke="black">This page intentionally left blank.</text>\n'
     if (raw) :
         ml += '</svg>'
     else :
         ml += '</svg></a>\n'
-        if (counter == numfiles - 1) :
+        if nextid == None:
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else :
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n'

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/genbook.py

@@ -19,12 +19,25 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # local support routines
-import convert2xml
-import flatxml2html
-import flatxml2svg
-import stylexml2css
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre :
+    from calibre_plugins.k4mobidedrm import convert2xml
+    from calibre_plugins.k4mobidedrm import flatxml2html
+    from calibre_plugins.k4mobidedrm import flatxml2svg
+    from calibre_plugins.k4mobidedrm import stylexml2css
+else :
+    import convert2xml
+    import flatxml2html
+    import flatxml2svg
+    import stylexml2css
 
 
 # Get a 7 bit encoded number from a file
@@ -103,7 +116,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside or string table limits')
+            # sys.exit(-1)
     def getSize(self):
         return self.size
     def getPos(self):
@@ -360,10 +374,34 @@ def generateBook(bookDir, raw, fixedimage):
     (ph, pw) = getPageDim(flat_xml)
     if (ph == '-1') or (ph == '0') : ph = '11000'
     if (pw == '-1') or (pw == '0') : pw = '8500'
+    meta_array['pageHeight'] = ph
+    meta_array['pageWidth'] = pw
+    if 'fontSize' not in meta_array.keys():
+        meta_array['fontSize'] = fontsize
 
-    # print '     ', 'other0000.dat'
+    # process other.dat for css info and for map of page files to svg images
+    # this map is needed because some pages actually are made up of multiple
+    # pageXXXX.xml files
     xname = os.path.join(bookDir, 'style.css')
     flat_xml = convert2xml.fromData(dict, otherFile)
+
+    # extract info.original.pid to get original page information
+    pageIDMap = {}
+    pageidnums = stylexml2css.getpageIDMap(flat_xml)
+    if len(pageidnums) == 0:
+        filenames = os.listdir(pageDir)
+        numfiles = len(filenames)
+        for k in range(numfiles):
+            pageidnums.append(k)
+    # create a map from page ids to list of page file nums to process for that page
+    for i in range(len(pageidnums)):
+        id = pageidnums[i]
+        if id in pageIDMap.keys():
+            pageIDMap[id].append(i)
+        else:
+            pageIDMap[id] = [i]
+
+    # now get the css info
     cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
     file(xname, 'wb').write(cssstr)
     xname = os.path.join(xmlDir, 'other0000.xml')
@@ -403,6 +441,9 @@ def generateBook(bookDir, raw, fixedimage):
     glyfile.close()
     print " "
 
+    # build up tocentries while processing html
+    tocentries = ''
+
     # start up the html
     htmlFileName = "book.html"
     htmlstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -425,6 +466,77 @@ def generateBook(bookDir, raw, fixedimage):
     # readability when rendering to the screen.  
     scaledpi = 1440.0
 
+    filenames = os.listdir(pageDir)
+    filenames = sorted(filenames)
+    numfiles = len(filenames)
+
+    xmllst = []
+
+    for filename in filenames:
+        # print '     ', filename
+        print ".",
+        fname = os.path.join(pageDir,filename)
+        flat_xml = convert2xml.fromData(dict, fname)
+
+        # keep flat_xml for later svg processing
+        xmllst.append(flat_xml)
+
+        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
+        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
+
+        # first get the html
+        pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
+        tocentries += tocinfo 
+        htmlstr += pagehtml
+
+    # finish up the html string and output it
+    htmlstr += '</body>\n</html>\n'
+    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
+    
+    print " "
+    print 'Extracting Table of Contents from Amazon OCR'
+
+    # first create a table of contents file for the svg images
+    tochtml = '<?xml version="1.0" encoding="utf-8"?>\n'
+    tochtml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
+    tochtml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
+    tochtml += '<head>\n'
+    tochtml += '<title>' + meta_array['Title'] + '</title>\n'
+    tochtml += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
+    tochtml += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
+    if 'ASIN' in meta_array:
+        tochtml += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
+    if 'GUID' in meta_array:
+        tochtml += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
+    tochtml += '</head>\n'
+    tochtml += '<body>\n'
+
+    tochtml += '<h2>Table of Contents</h2>\n'
+    start = pageidnums[0]
+    if (raw):
+        startname = 'page%04d.svg' % start
+    else:
+        startname = 'page%04d.xhtml' % start
+
+    tochtml += '<h3><a href="' + startname + '">Start of Book</a></h3>\n'
+    # build up a table of contents for the svg xhtml output
+    toclst = tocentries.split('\n')
+    toclst.pop()
+    for entry in toclst:
+        print entry
+        title, pagenum = entry.split('|')
+        id = pageidnums[int(pagenum)]
+        if (raw):
+            fname = 'page%04d.svg' % id
+        else:
+            fname = 'page%04d.xhtml' % id
+        tochtml += '<h3><a href="'+ fname + '">' + title + '</a></h3>\n'
+    tochtml += '</body>\n'
+    tochtml += '</html>\n'
+    file(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
+
+
+    # now create index_svg.xhtml that points to all required files
     svgindex = '<?xml version="1.0" encoding="utf-8"?>\n'
     svgindex += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
     svgindex += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
@@ -439,50 +551,42 @@ def generateBook(bookDir, raw, fixedimage):
     svgindex += '</head>\n'
     svgindex += '<body>\n'
 
-    filenames = os.listdir(pageDir)
-    filenames = sorted(filenames)
-    numfiles = len(filenames)
-    counter = 0
-
-    for filename in filenames:
-        # print '     ', filename
-        print ".",
-
-        fname = os.path.join(pageDir,filename)
-        flat_xml = convert2xml.fromData(dict, fname)
-
-        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
-        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
-
-        # first get the html
-        htmlstr += flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
-
-        # now get the svg image of the page
-        svgxml = flatxml2svg.convert2SVG(gd, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi)
-
+    print "Building svg images of each book page"
+    svgindex += '<h2>List of Pages</h2>\n'
+    svgindex += '<div>\n'
+    idlst = sorted(pageIDMap.keys())
+    numids = len(idlst)
+    cnt = len(idlst)
+    previd = None
+    for j in range(cnt):
+        pageid = idlst[j]
+        if j < cnt - 1:
+            nextid = idlst[j+1]
+        else:
+            nextid = None
+        print '.',
+        pagelst = pageIDMap[pageid]
+        flat_svg = ''
+        for page in pagelst:
+            flat_svg += xmllst[page]
+        svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
         if (raw) :
-            pfile = open(os.path.join(svgDir,filename.replace('.dat','.svg')), 'w')
-            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (counter, counter)
+            pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
+            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid)
         else :
-            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % counter), 'w')
-            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (counter, counter)
-
-
+            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
+            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid)
+        previd = pageid
         pfile.write(svgxml)
         pfile.close()
-
         counter += 1
-
-    print " "
-
-    # finish up the html string and output it
-    htmlstr += '</body>\n</html>\n'
-    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
-
-    # finish up the svg index string and output it
+    svgindex += '</div>\n'
+    svgindex += '<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n'
     svgindex += '</body>\n</html>\n'
     file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
 
+    print " "
+
     # build the opf file
     opfname = os.path.join(bookDir, 'book.opf')
     opfstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -504,7 +608,7 @@ def generateBook(bookDir, raw, fixedimage):
     opfstr += '   </metadata>\n'
     opfstr += '<manifest>\n'
     opfstr += '   <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n'
-    opfstr += '   <item id="stylesheet" href="style.css" media-type="text.css"/>\n'
+    opfstr += '   <item id="stylesheet" href="style.css" media-type="text/css"/>\n'
     # adding image files to manifest
     filenames = os.listdir(imgDir)
     filenames = sorted(filenames)
@@ -562,7 +666,7 @@ def main(argv):
         return 1 
 
     raw = 0
-    fixedimage = False
+    fixedimage = True
     for o, a in opts:
         if o =="-h":
             usage()

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/ineptpdf.py

@@ -157,6 +157,7 @@ def _load_crypto_libcrypto():
             return out.raw
 
     class AES(object):
+        MODE_CBC = 0
         @classmethod
         def new(cls, userkey, mode, iv):
             self = AES()

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/k4mobidedrm.py

@@ -16,20 +16,8 @@ from __future__ import with_statement
 #    unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates 
 #    and many many others
 
-# It can run standalone to convert K4M/K4PC/Mobi files, or it can be installed as a
-# plugin for Calibre (http://calibre-ebook.com/about) so that importing
-# K4 or Mobi with DRM is no londer a multi-step process.
-#
-# ***NOTE*** If you are using this script as a calibre plugin for a K4M or K4PC ebook
-# then calibre must be installed on the same machine and in the same account as K4PC or K4M
-# for the plugin version to function properly.
-#
-# To create a Calibre plugin, rename this file so that the filename
-# ends in '_plugin.py', put it into a ZIP file with all its supporting python routines
-# and import that ZIP into Calibre using its plugin configuration GUI.
 
-
-__version__ = '2.8'
+__version__ = '3.9'
 
 class Unbuffered:
     def __init__(self, stream):
@@ -43,11 +31,8 @@ class Unbuffered:
 import sys
 import os, csv, getopt
 import string
-import binascii
-import zlib
 import re
-import zlib, zipfile, tempfile, shutil
-from struct import pack, unpack, unpack_from
+import traceback
 
 class DrmException(Exception):
     pass
@@ -57,19 +42,15 @@ if 'calibre' in sys.modules:
 else:
     inCalibre = False
 
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import mobidedrm
+    from calibre_plugins.k4mobidedrm import topazextract
+    from calibre_plugins.k4mobidedrm import kgenpids
+else:
+    import mobidedrm
+    import topazextract
+    import kgenpids
+        
 
 # cleanup bytestring filenames
 # borrowed from calibre from calibre/src/calibre/__init__.py
@@ -94,13 +75,9 @@ def cleanup_name(name):
     return one
 
 def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
-    import mobidedrm
-    import topazextract
-    import kgenpids
-
     # handle the obvious cases at the beginning
     if not os.path.isfile(infile):
-        print "Error: Input file does not exist"
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: Input file does not exist"
         return 1
 
     mobi = True
@@ -113,75 +90,62 @@ def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
     if mobi:
         mb = mobidedrm.MobiBook(infile)
     else:
-        tempdir = tempfile.mkdtemp()
-        mb = topazextract.TopazBook(infile, tempdir)
+        mb = topazextract.TopazBook(infile)
 
     title = mb.getBookTitle()
     print "Processing Book: ", title
     filenametitle = cleanup_name(title)
     outfilename = bookname
-    if len(bookname)>4 and len(filenametitle)>4 and bookname[:4] != filenametitle[:4]:
+    if len(outfilename)<=8 or len(filenametitle)<=8:
         outfilename = outfilename + "_" + filenametitle
+    elif outfilename[:8] != filenametitle[:8]:
+        outfilename = outfilename[:8] + "_" + filenametitle
+        
+    # avoid excessively long file names
+    if len(outfilename)>150:
+        outfilename = outfilename[:150]
 
     # build pid list
     md1, md2 = mb.getPIDMetaInfo()
     pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
 
     try:
-        if mobi:
-            unlocked_file = mb.processBook(pidlst)
-        else:
-            mb.processBook(pidlst)
+        mb.processBook(pidlst)
 
     except mobidedrm.DrmException, e:
-        print "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+    except topazextract.TpzDRMError, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
         return 1
     except Exception, e:
-        if not mobi:
-            print "Error: " + str(e) + "\nDRM Removal Failed.\n"
-            print "   Creating DeBug Full Zip Archive of Book"
-            zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-            myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-            zipUpDir(myzip, tempdir, '')
-            myzip.close()
-            shutil.rmtree(tempdir, True)
-            return 1
-        pass
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
 
     if mobi:
-        outfile = os.path.join(outdir,outfilename + '_nodrm' + '.mobi')
-        file(outfile, 'wb').write(unlocked_file)
+        if mb.getPrintReplica():
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.azw4')
+        else:
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.mobi')
+        mb.getMobiFile(outfile)
         return 0            
 
-    # topaz:  build up zip archives of results
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
+    # topaz: 
+    print "   Creating NoDRM HTMLZ Archive"
+    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.htmlz')
+    mb.getHTMLZip(zipname)
 
     print "   Creating SVG ZIP Archive"
     zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
+    mb.getSVGZip(zipname)
 
     print "   Creating XML ZIP Archive"
     zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
+    mb.getXMLZip(zipname)
+
+    # remove internal temporary directory of Topaz pieces
+    mb.cleanup()
 
-    shutil.rmtree(tempdir, True)
     return 0
 
 
@@ -204,7 +168,6 @@ def main(argv=sys.argv):
     print ('K4MobiDeDrm v%(__version__)s '
 	   'provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc .' % globals())
 
-    print ' '
     try:
         opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
     except getopt.GetoptError, err:
@@ -236,7 +199,6 @@ def main(argv=sys.argv):
 	kInfoFiles = None
     infile = args[0]
     outdir = args[1]
-
     return decryptBook(infile, outdir, k4, kInfoFiles, serials, pids)
 
 
@@ -244,131 +206,3 @@ if __name__ == '__main__':
     sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 
-if not __name__ == "__main__" and inCalibre:
-    from calibre.customize import FileTypePlugin
-
-    class K4DeDRM(FileTypePlugin):
-        name                = 'K4PC, K4Mac, Kindle Mobi and Topaz DeDRM' # Name of the plugin
-        description         = 'Removes DRM from K4PC and Mac, Kindle Mobi and Topaz files. \
-                                Provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc.'
-        supported_platforms = ['osx', 'windows', 'linux'] # Platforms this plugin will run on
-        author              = 'DiapDealer, SomeUpdates' # The author of this plugin
-        version             = (0, 2, 8)   # The version number of this plugin
-        file_types          = set(['prc','mobi','azw','azw1','tpz']) # The file types that this plugin will be applied to
-        on_import           = True # Run this plugin during the import
-        priority            = 210  # run this plugin before mobidedrm, k4pcdedrm, k4dedrm
-
-        def run(self, path_to_ebook):
-            from calibre.gui2 import is_ok_to_use_qt
-            from PyQt4.Qt import QMessageBox
-            from calibre.ptempfile import PersistentTemporaryDirectory
-
-            import kgenpids
-            import zlib
-            import zipfile
-            import topazextract
-            import mobidedrm
-
-            k4 = True
-	    if sys.platform.startswith('linux'):
-		k4 = False
-            pids = []
-            serials = []
-            kInfoFiles = []
-
-            # Get supplied list of PIDs to try from plugin customization.
-            customvalues = self.site_customization.split(',')
-            for customvalue in customvalues:
-                customvalue = str(customvalue)
-                customvalue = customvalue.strip()
-            	if len(customvalue) == 10 or len(customvalue) == 8:
-                    pids.append(customvalue)
-            	else :
-                    if len(customvalue) == 16 and customvalue[0] == 'B':
-                        serials.append(customvalue)
-                    else:
-                        print "%s is not a valid Kindle serial number or PID." % str(customvalue)
-            		
-            # Load any kindle info files (*.info) included Calibre's config directory.
-            try:
-                # Find Calibre's configuration directory.
-                confpath = os.path.split(os.path.split(self.plugin_path)[0])[0]
-                print 'K4MobiDeDRM: Calibre configuration directory = %s' % confpath
-                files = os.listdir(confpath)
-                filefilter = re.compile("\.info$", re.IGNORECASE)
-                files = filter(filefilter.search, files)
-    
-                if files:
-                    for filename in files:
-                        fpath = os.path.join(confpath, filename)
-                        kInfoFiles.append(fpath)
-                        print 'K4MobiDeDRM: Kindle info file %s found in config folder.' % filename
-            except IOError:
-                print 'K4MobiDeDRM: Error reading kindle info files from config directory.'
-                pass
-
-
-            mobi = True
-            magic3 = file(path_to_ebook,'rb').read(3)
-            if magic3 == 'TPZ':
-                mobi = False
-
-            bookname = os.path.splitext(os.path.basename(path_to_ebook))[0]
-
-            if mobi:
-                mb = mobidedrm.MobiBook(path_to_ebook)
-            else:
-                tempdir = PersistentTemporaryDirectory()
-                mb = topazextract.TopazBook(path_to_ebook, tempdir)
-
-            title = mb.getBookTitle()
-            md1, md2 = mb.getPIDMetaInfo()
-            pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
-
-            try:
-                if mobi:
-                    unlocked_file = mb.processBook(pidlst)
-                else:
-                    mb.processBook(pidlst)
-
-            except mobidedrm.DrmException:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-            except topazextract.TpzDRMError:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-
-            print "Success!"
-            if mobi:
-                of = self.temporary_file(bookname+'.mobi')
-                of.write(unlocked_file)
-                of.close()
-                return of.name
-
-            # topaz:  build up zip archives of results
-            print "   Creating HTML ZIP Archive"
-            of = self.temporary_file(bookname + '.zip')
-            myzip = zipfile.ZipFile(of.name,'w',zipfile.ZIP_DEFLATED, False)
-            myzip.write(os.path.join(tempdir,'book.html'),'book.html')
-            myzip.write(os.path.join(tempdir,'book.opf'),'book.opf')
-            if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-                myzip.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-            myzip.write(os.path.join(tempdir,'style.css'),'style.css')
-            zipUpDir(myzip, tempdir, 'img')
-            myzip.close()
-            return of.name
-
-        def customization_help(self, gui=False):
-            return 'Enter 10 character PIDs and/or Kindle serial numbers, separated by commas.'

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/k4mutils.py

@@ -1,10 +1,13 @@
-# standlone set of Mac OSX specific routines needed for K4DeDRM
+# standlone set of Mac OSX specific routines needed for KindleBooks
 
 from __future__ import with_statement
+
 import sys
 import os
-import subprocess
+import os.path
 
+import subprocess
+from struct import pack, unpack, unpack_from
 
 class DrmException(Exception):
     pass
@@ -66,12 +69,9 @@ def _load_crypto_libcrypto():
                 raise DrmException('AES decryption failed')
             return out.raw
 
-        def keyivgen(self, passwd):
-            salt = '16743'
-            saltlen = 5
+        def keyivgen(self, passwd, salt, iter, keylen):
+            saltlen = len(salt)
             passlen = len(passwd)
-            iter = 0x3e8
-            keylen = 80
             out = create_string_buffer(keylen)
             rv = PKCS5_PBKDF2_HMAC_SHA1(passwd, passlen, salt, saltlen, iter, keylen, out)
             return out.raw
@@ -91,13 +91,79 @@ LibCrypto = _load_crypto()
 # Utility Routines
 #
 
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA256(message):
+    ctx = hashlib.sha256()
+    ctx.update(message)
+    return ctx.digest()
 
 # Various character maps used to decrypt books. Probably supposed to act as obfuscation
 charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
 charMap2 = "ZB0bYyc1xDdW2wEV3Ff7KkPpL8UuGA4gz-Tme9Nn_tHh5SvXCsIiR6rJjQaqlOoM" 
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
 
+# For kinf approach of K4PC/K4Mac
+# On K4PC charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
+# For Mac they seem to re-use charMap2 here
+charMap5 = charMap2
+
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+# For .kinf approach of K4PC and now K4Mac
+# generate table of prime number less than or equal to int n
+def primes(n):
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
 
 
 # uses a sub process to get the Hard Drive Serial Number using ioreg
@@ -129,47 +195,223 @@ def GetVolumeSerialNumber():
                 foundIt = True
                 break
     if not foundIt:
-        sernum = '9999999999'
+        sernum = ''
     return sernum
 
+def GetUserHomeAppSupKindleDirParitionName():
+    home = os.getenv('HOME')
+    dpath =  home + '/Library/Application Support/Kindle'
+    cmdline = '/sbin/mount'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    disk = ''
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.startswith('/dev'):
+            (devpart, mpath) = resline.split(' on ')
+            dpart = devpart[5:]
+            pp = mpath.find('(')
+            if pp >= 0:
+                mpath = mpath[:pp-1]
+            if dpath.startswith(mpath):
+                disk = dpart
+    return disk
+
+# uses a sub process to get the UUID of the specified disk partition using ioreg
+def GetDiskPartitionUUID(diskpart):
+    uuidnum = os.getenv('MYUUIDNUMBER')
+    if uuidnum != None:
+        return uuidnum
+    cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    bsdname = None
+    uuidnum = None
+    foundIt = False
+    nest = 0
+    uuidnest = -1
+    partnest = -2
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.find('{') >= 0:
+            nest += 1
+        if resline.find('}') >= 0:
+            nest -= 1
+        pp = resline.find('"UUID" = "')
+        if pp >= 0:
+            uuidnum = resline[pp+10:-1]
+            uuidnum = uuidnum.strip()
+            uuidnest = nest
+            if partnest == uuidnest and uuidnest > 0:
+                foundIt = True
+                break
+        bb = resline.find('"BSD Name" = "')
+        if bb >= 0:
+            bsdname = resline[bb+14:-1]
+            bsdname = bsdname.strip()
+            if (bsdname == diskpart):
+                partnest = nest
+            else :
+                partnest = -2
+            if partnest == uuidnest and partnest > 0:
+                foundIt = True
+                break
+        if nest == 0:
+            partnest = -2
+            uuidnest = -1
+            uuidnum = None
+            bsdname = None
+    if not foundIt:
+        uuidnum = ''
+    return uuidnum
+    
+def GetMACAddressMunged():
+    macnum = os.getenv('MYMACNUM')
+    if macnum != None:
+        return macnum
+    cmdline = '/sbin/ifconfig en0'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    macnum = None
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        pp = resline.find('ether ')
+        if pp >= 0:
+            macnum = resline[pp+6:-1]
+            macnum = macnum.strip()
+            # print "original mac", macnum
+            # now munge it up the way Kindle app does
+            # by xoring it with 0xa5 and swapping elements 3 and 4
+            maclst = macnum.split(':')
+            n = len(maclst)
+            if n != 6:
+                fountIt = False
+                break
+            for i in range(6):
+                maclst[i] = int('0x' + maclst[i], 0)
+            mlst = [0x00, 0x00, 0x00, 0x00, 0x00, 0x00]
+            mlst[5] = maclst[5] ^ 0xa5
+            mlst[4] = maclst[3] ^ 0xa5
+            mlst[3] = maclst[4] ^ 0xa5
+            mlst[2] = maclst[2] ^ 0xa5
+            mlst[1] = maclst[1] ^ 0xa5
+            mlst[0] = maclst[0] ^ 0xa5
+            macnum = "%0.2x%0.2x%0.2x%0.2x%0.2x%0.2x" % (mlst[0], mlst[1], mlst[2], mlst[3], mlst[4], mlst[5])
+            foundIt = True
+            break
+    if not foundIt:
+        macnum = ''
+    return macnum
+
+
 # uses unix env to get username instead of using sysctlbyname 
 def GetUserName():
     username = os.getenv('USER')
     return username
 
 
-def encode(data, map):
-    result = ""
-    for char in data:
-        value = ord(char)
-        Q = (value ^ 0x80) // len(map)
-        R = value % len(map)
-        result += map[Q]
-        result += map[R]
-    return result
-
-import hashlib
-
-def SHA256(message):
-    ctx = hashlib.sha256()
-    ctx.update(message)
-    return ctx.digest()
-
 # implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used by Kindle for Mac versions < 1.6.0
 def CryptUnprotectData(encryptedData):
-    sp = GetVolumeSerialNumber() + '!@#' + GetUserName()
+    sernum = GetVolumeSerialNumber()
+    if sernum == '':
+        sernum = '9999999999'
+    sp = sernum + '!@#' + GetUserName()
     passwdData = encode(SHA256(sp),charMap1)
+    salt = '16743'
+    iter = 0x3e8
+    keylen = 0x80
     crp = LibCrypto()
-    key_iv = crp.keyivgen(passwdData)
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
     key = key_iv[0:32]
     iv = key_iv[32:48]
     crp.set_decrypt_key(key,iv)
     cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext,charMap1)
+    return cleartext
+
+
+def isNewInstall():
+    home = os.getenv('HOME')
+    # soccer game fan anyone
+    dpath = home + '/Library/Application Support/Kindle/storage/.pes2011'
+    # print dpath, os.path.exists(dpath)
+    if os.path.exists(dpath):
+        return True
+    return False
+    
+
+def GetIDString():
+    # K4Mac now has an extensive set of ids strings it uses
+    # in encoding pids and in creating unique passwords
+    # for use in its own version of CryptUnprotectDataV2
+
+    # BUT Amazon has now become nasty enough to detect when its app
+    # is being run under a debugger and actually changes code paths
+    # including which one of these strings is chosen, all to try 
+    # to prevent reverse engineering
+
+    # Sad really ... they will only hurt their own sales ...
+    # true book lovers really want to keep their books forever
+    # and move them to their devices and DRM prevents that so they 
+    # will just buy from someplace else that they can remove 
+    # the DRM from
+
+    # Amazon should know by now that true book lover's are not like
+    # penniless kids that pirate music, we do not pirate books
+
+    if isNewInstall():
+        mungedmac = GetMACAddressMunged()
+        if len(mungedmac) > 7:
+            return mungedmac
+    sernum = GetVolumeSerialNumber()
+    if len(sernum) > 7:
+        return sernum
+    diskpart = GetUserHomeAppSupKindleDirParitionName()
+    uuidnum = GetDiskPartitionUUID(diskpart)
+    if len(uuidnum) > 7:
+        return uuidnum
+    mungedmac = GetMACAddressMunged()
+    if len(mungedmac) > 7:
+        return mungedmac
+    return '9999999999'
+
+
+# implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used for Kindle for Mac Versions >= 1.6.0
+def CryptUnprotectDataV2(encryptedData):
+    sp = GetUserName() + ':&%:' + GetIDString()
+    passwdData = encode(SHA256(sp),charMap5)
+    # salt generation as per the code
+    salt = 0x0512981d * 2 * 1 * 1
+    salt = str(salt) + GetUserName()
+    salt = encode(salt,charMap5)
+    crp = LibCrypto()
+    iter = 0x800
+    keylen = 0x400
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
+    key = key_iv[0:32]
+    iv = key_iv[32:48]
+    crp.set_decrypt_key(key,iv)
+    cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext, charMap5)
     return cleartext
 
 
 # Locate the .kindle-info files
 def getKindleInfoFiles(kInfoFiles):
+    # first search for current .kindle-info files
     home = os.getenv('HOME')
     cmdline = 'find "' + home + '/Library/Application Support" -name ".kindle-info"'
     cmdline = cmdline.encode(sys.getfilesystemencoding())
@@ -178,23 +420,132 @@ def getKindleInfoFiles(kInfoFiles):
     reslst = out1.split('\n')
     kinfopath = 'NONE'
     found = False
-    cnt = len(reslst)
+    for resline in reslst:
+        if os.path.isfile(resline):
+            kInfoFiles.append(resline)
+            found = True
+    # add any .kinf files 
+    cmdline = 'find "' + home + '/Library/Application Support" -name ".rainier*-kinf"'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p1.communicate()
+    reslst = out1.split('\n')
     for resline in reslst:
         if os.path.isfile(resline):
             kInfoFiles.append(resline)
             found = True
     if not found:
-        print('No .kindle-info files have been found.')
+        print('No kindle-info files have been found.')
     return kInfoFiles
 
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
     DB = {}
+    cnt = 0
     infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
+    hdr = infoReader.read(1)
     data = infoReader.read()
-    items = data.split('[')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
+
+    if data.find('[') != -1 :
+        # older style kindle-info file
+        items = data.split('[')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                cleartext = CryptUnprotectData(encryptedValue)
+                DB[keyname] = cleartext
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file used by K4Mac >= 1.6.0
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+    
+        # get the first item record
+        item = items.pop(0)
+    
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+        keyname = "unknown"
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        # "entropy" not used for K4Mac only K4PC
+        # entropy = SHA1(keyhash)
+    
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+    
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+    
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+    
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+    
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+    
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        noffset = contlen - primes(int(contlen/3))[-1]
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+    
+        # decode using charMap5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        cleartext = CryptUnprotectDataV2(encryptedValue)
+        # Debugging
+        # print keyname
+        # print cleartext
+        # print cleartext.encode('hex')
+        # print
+        DB[keyname] = cleartext
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
     return DB

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/k4pcutils.py

@@ -1,8 +1,10 @@
+#!/usr/bin/env python
 # K4PC Windows specific routines
 
 from __future__ import with_statement
 
 import sys, os
+from struct import pack, unpack, unpack_from
 
 from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
     create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
@@ -10,25 +12,86 @@ from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
 
 import _winreg as winreg
 
-import traceback
-
 MAX_PATH = 255
 
 kernel32 = windll.kernel32
 advapi32 = windll.advapi32
 crypt32 = windll.crypt32
 
+import traceback
 
-# Various character maps used to decrypt books. Probably supposed to act as obfuscation
-charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+
+# simple primes table (<= n) calculator
+def primes(n): 
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
+
+
+# Various character maps used to decrypt kindle info values.
+# Probably supposed to act as obfuscation
 charMap2 = "AaZzB0bYyCc1XxDdW2wEeVv3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_"
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
+charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
 
 class DrmException(Exception):
     pass
-    
 
+# Encode the bytes in data with the characters in map
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+  
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+
+# interface with Windows OS Routines
 class DataBlob(Structure):
     _fields_ = [('cbData', c_uint),
                 ('pbData', c_void_p)]
@@ -59,59 +122,187 @@ def GetVolumeSerialNumber():
     return GetVolumeSerialNumber
 GetVolumeSerialNumber = GetVolumeSerialNumber()
 
+def GetIDString():
+    return GetVolumeSerialNumber()
+
+def getLastError():
+    GetLastError = kernel32.GetLastError
+    GetLastError.argtypes = None
+    GetLastError.restype = c_uint
+    def getLastError():
+        return GetLastError()
+    return getLastError
+getLastError = getLastError()
 
 def GetUserName():
     GetUserNameW = advapi32.GetUserNameW
     GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
     GetUserNameW.restype = c_uint
     def GetUserName():
-        buffer = create_unicode_buffer(32)
+        buffer = create_unicode_buffer(2)
         size = c_uint(len(buffer))
         while not GetUserNameW(buffer, byref(size)):
+            errcd = getLastError()
+            if errcd == 234:
+                # bad wine implementation up through wine 1.3.21
+                return "AlternateUserName"
             buffer = create_unicode_buffer(len(buffer) * 2)
             size.value = len(buffer)
         return buffer.value.encode('utf-16-le')[::2]
     return GetUserName
 GetUserName = GetUserName()
 
-
 def CryptUnprotectData():
     _CryptUnprotectData = crypt32.CryptUnprotectData
     _CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
                                    c_void_p, c_void_p, c_uint, DataBlob_p]
     _CryptUnprotectData.restype = c_uint
-    def CryptUnprotectData(indata, entropy):
+    def CryptUnprotectData(indata, entropy, flags):
         indatab = create_string_buffer(indata)
         indata = DataBlob(len(indata), cast(indatab, c_void_p))
         entropyb = create_string_buffer(entropy)
         entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
         outdata = DataBlob()
         if not _CryptUnprotectData(byref(indata), None, byref(entropy),
-                                   None, None, 0, byref(outdata)):
+                                   None, None, flags, byref(outdata)):
             raise DrmException("Failed to Unprotect Data")
         return string_at(outdata.pbData, outdata.cbData)
     return CryptUnprotectData
 CryptUnprotectData = CryptUnprotectData()
 
-# Locate the .kindle-info files
+
+# Locate all of the kindle-info style files and return as list
 def getKindleInfoFiles(kInfoFiles):
     regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders\\")
     path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
+
+    # first look for older kindle-info files
     kinfopath = path +'\\Amazon\\Kindle For PC\\{AMAwzsaPaaZAzmZzZQzgZCAkZ3AjA_AY}\\kindle.info'
     if not os.path.isfile(kinfopath):
-        print('The kindle.info files has not been found.')
+        print('No kindle.info files have not been found.')
     else:
         kInfoFiles.append(kinfopath)
+
+    # now look for newer (K4PC 1.5.0 and later rainier.2.1.1.kinf file
+
+    kinfopath = path +'\\Amazon\\Kindle For PC\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.5.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
+    # now look for even newer (K4PC 1.6.0 and later) rainier.2.1.1.kinf file
+    kinfopath = path +'\\Amazon\\Kindle\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.6.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
     return kInfoFiles
 
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
+
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
     DB = {}
+    cnt = 0
     infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
+    hdr = infoReader.read(1)
     data = infoReader.read()
-    items = data.split('{')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
+
+    if data.find('{') != -1 :
+
+        # older style kindle-info file
+        items = data.split('{')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                DB[keyname] = CryptUnprotectData(encryptedValue, "", 0)
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+
+        # get the first item record
+        item = items.pop(0)
+
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        entropy = SHA1(keyhash)
+
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+        noffset = contlen - primes(int(contlen/3))[-1]
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+
+        # decode using Map5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        DB[keyname] = CryptUnprotectData(encryptedValue, entropy, 1)
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
     return DB
+
+

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/kgenpids.py

@@ -11,16 +11,28 @@ from struct import pack, unpack, unpack_from
 class DrmException(Exception):
     pass
 
-global kindleDatabase
 global charMap1
-global charMap2
 global charMap3
 global charMap4
 
-if sys.platform.startswith('win'):
-    from k4pcutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
-if sys.platform.startswith('darwin'):
-    from k4mutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre:
+    if sys.platform.startswith('win'):
+        from calibre_plugins.k4mobidedrm.k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from calibre_plugins.k4mobidedrm.k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+else:
+    if sys.platform.startswith('win'):
+        from k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
 
 charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
 charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
@@ -66,50 +78,7 @@ def decode(data,map):
         value = (((high * len(map)) ^ 0x80) & 0xFF) + low
         result += pack("B",value)
     return result
-
-# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForHash(hashedKey):
-    global kindleDatabase
-    global charMap1
-    global charMap2
-    encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
-    if sys.platform.startswith('win'):
-        return CryptUnprotectData(encryptedValue,"")
-    else:
-        cleartext = CryptUnprotectData(encryptedValue)
-        return decode(cleartext, charMap1)
- 
-# Get a record from the Kindle.info file for the string in "key" (plaintext). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForKey(key):
-    global charMap2
-    return getKindleInfoValueForHash(encodeHash(key,charMap2))
-
-# Find if the original string for a hashed/encoded string is known. 
-# If so return the original string othwise return an empty string.
-def findNameForHash(hash):
-    global charMap2
-    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
-    result = ""
-    for name in names:
-        if hash == encodeHash(name, charMap2):
-           result = name
-           break
-    return result
     
-# Print all the records from the kindle.info file (option -i)
-def printKindleInfo():
-    for record in kindleDatabase:
-        name = findNameForHash(record)
-        if name != "" :
-            print (name)
-            print ("--------------------------")
-        else :
-            print ("Unknown Record")
-        print getKindleInfoValueForHash(record)
-        print "\n"
-
 #
 # PID generation routines
 #
@@ -222,15 +191,15 @@ def getKindlePid(pidlst, rec209, token, serialnum):
     return pidlst
 
 
-# Parse the EXTH header records and parse the Kindleinfo
-# file to calculate the book pid.
+# parse the Kindleinfo file to calculate the book pid.
+
+keynames = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
 
 def getK4Pids(pidlst, rec209, token, kInfoFile):
-    global kindleDatabase
     global charMap1
     kindleDatabase = None
     try:
-        kindleDatabase = parseKindleInfo(kInfoFile)
+        kindleDatabase = getDBfromFile(kInfoFile)
     except Exception, message:
         print(message)
         kindleDatabase = None
@@ -241,22 +210,22 @@ def getK4Pids(pidlst, rec209, token, kInfoFile):
         
     try:
         # Get the Mazama Random number
-        MazamaRandomNumber = getKindleInfoValueForKey("MazamaRandomNumber")
+        MazamaRandomNumber = kindleDatabase["MazamaRandomNumber"]
 
         # Get the kindle account token
-        kindleAccountToken = getKindleInfoValueForKey("kindle.account.tokens")
+        kindleAccountToken = kindleDatabase["kindle.account.tokens"]
     except KeyError:
         print "Keys not found in " + kInfoFile
         return pidlst
         
-    # Get the HDD serial
-    encodedSystemVolumeSerialNumber = encodeHash(GetVolumeSerialNumber(),charMap1)
+    # Get the ID string used
+    encodedIDString = encodeHash(GetIDString(),charMap1)
 
     # Get the current user name
     encodedUsername = encodeHash(GetUserName(),charMap1)
 
     # concat, hash and encode to calculate the DSN
-    DSN = encode(SHA1(MazamaRandomNumber+encodedSystemVolumeSerialNumber+encodedUsername),charMap1)
+    DSN = encode(SHA1(MazamaRandomNumber+encodedIDString+encodedUsername),charMap1)
        
     # Compute the device PID (for which I can tell, is used for nothing).
     table =  generatePidEncryptionTable()

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/mobidedrm.py

@@ -49,10 +49,13 @@
 #  0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
 #  0.28 - slight additional changes to metadata token generation (None -> '')
 #  0.29 - It seems that the ideas about when multibyte trailing characters were
-#         included in the encryption were wrong. They aren't for DOC compressed
-#         files, but they are for HUFF/CDIC compress files!
+#         included in the encryption were wrong. They are for DOC compressed
+#         files, but they are not for HUFF/CDIC compress files!
+#  0.30 - Modified interface slightly to work better with new calibre plugin style
+#  0.31 - The multibyte encrytion info is true for version 7 files too.
+#  0.32 - Added support for "Print Replica" Kindle ebooks
 
-__version__ = '0.29'
+__version__ = '0.32'
 
 import sys
 
@@ -161,8 +164,12 @@ class MobiBook:
         return self.data_file[off:endoff]
 
     def __init__(self, infile):
+        print ('MobiDeDrm v%(__version__)s. '
+           'Copyright 2008-2011 The Dark Reverser et al.' % globals())
+
         # initial sanity check on file
         self.data_file = file(infile, 'rb').read()
+        self.mobi_data = ''
         self.header = self.data_file[0:78]
         if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
             raise DrmException("invalid file format")
@@ -190,14 +197,15 @@ class MobiBook:
             self.meta_array = {}
             return
         self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
+        self.mobi_codepage, = struct.unpack('>L',self.sect[0x1c:0x20])
         self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
         print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
         self.extra_data_flags = 0
         if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
             self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
             print "Extra Data Flags = %d" % self.extra_data_flags
-        if (self.mobi_version < 7) and (self.compression != 17480):
-            # multibyte utf8 data is included in the encryption for mobi_version 6 and below
+        if (self.compression != 17480):
+            # multibyte utf8 data is included in the encryption for PalmDoc compression
             # so clear that byte so that we leave it to be decrypted.
             self.extra_data_flags &= 0xFFFE
 
@@ -227,8 +235,13 @@ class MobiBook:
         except:
             self.meta_array = {}
             pass
+        self.print_replica = False
             
     def getBookTitle(self):
+        codec_map = {
+            1252 : 'windows-1252',
+            65001 : 'utf-8',
+        }
         title = ''
         if 503 in self.meta_array:
             title = self.meta_array[503]
@@ -239,7 +252,10 @@ class MobiBook:
         if title == '':
             title = self.header[:32]
             title = title.split("\0")[0]
-        return title
+        codec = 'windows-1252'
+        if self.mobi_codepage in codec_map.keys():
+            codec = codec_map[self.mobi_codepage]
+        return unicode(title, codec).encode('utf-8')
 
     def getPIDMetaInfo(self):
         rec209 = ''
@@ -301,15 +317,29 @@ class MobiBook:
                         break
         return [found_key,pid]
 
+    def getMobiFile(self, outpath):
+        file(outpath,'wb').write(self.mobi_data)
+        
+    def getPrintReplica(self):
+        return self.print_replica
+
     def processBook(self, pidlist):
         crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
         print 'Crypto Type is: ', crypto_type
         self.crypto_type = crypto_type
         if crypto_type == 0:
             print "This book is not encrypted."
-            return self.data_file
+            # we must still check for Print Replica
+            self.print_replica = (self.loadSection(1)[0:4] == '%MOP')
+            self.mobi_data = self.data_file
+            return
         if crypto_type != 2 and crypto_type != 1:
             raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
+        if 406 in self.meta_array:
+            data406 = self.meta_array[406]
+            val406, = struct.unpack('>Q',data406)
+            if val406 != 0:
+                raise DrmException("Cannot decode library or rented ebooks.")
 
         goodpids = []
         for pid in pidlist:
@@ -353,39 +383,44 @@ class MobiBook:
 
         # decrypt sections
         print "Decrypting. Please wait . . .",
-        new_data = self.data_file[:self.sections[1][0]]
+        self.mobi_data = self.data_file[:self.sections[1][0]]
         for i in xrange(1, self.records+1):
             data = self.loadSection(i)
             extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
             if i%100 == 0:
                 print ".",
             # print "record %d, extra_size %d" %(i,extra_size)
-            new_data += PC1(found_key, data[0:len(data) - extra_size])
+            decoded_data = PC1(found_key, data[0:len(data) - extra_size])
+            if i==1:
+                self.print_replica = (decoded_data[0:4] == '%MOP')
+            self.mobi_data += decoded_data
             if extra_size > 0:
-                new_data += data[-extra_size:]
+                self.mobi_data += data[-extra_size:]
         if self.num_sections > self.records+1:
-            new_data += self.data_file[self.sections[self.records+1][0]:]
-        self.data_file = new_data
+            self.mobi_data += self.data_file[self.sections[self.records+1][0]:]
         print "done"
-        return self.data_file
+        return
 
 def getUnencryptedBook(infile,pid):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook([pid])
+    book.processBook([pid])
+    return book.mobi_data
 
 def getUnencryptedBookWithList(infile,pidlist):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook(pidlist)
+    book.processBook(pidlist)
+    return book.mobi_data
+
 
 def main(argv=sys.argv):
     print ('MobiDeDrm v%(__version__)s. '
-	   'Copyright 2008-2010 The Dark Reverser.' % globals())
+        'Copyright 2008-2011 The Dark Reverser et al.' % globals())
     if len(argv)<3 or len(argv)>4:
-        print "Removes protection from Mobipocket books"
+        print "Removes protection from Kindle/Mobipocket and Kindle/Print Replica ebooks"
         print "Usage:"
         print "    %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
         return 1
@@ -393,9 +428,9 @@ def main(argv=sys.argv):
         infile = argv[1]
         outfile = argv[2]
         if len(argv) is 4:
-        	pidlist = argv[3].split(',')
+            pidlist = argv[3].split(',')
         else:
-        	pidlist = {}
+            pidlist = {}
         try:
             stripped_file = getUnencryptedBookWithList(infile, pidlist)
             file(outfile, 'wb').write(stripped_file)

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/stylexml2css.py

@@ -81,6 +81,14 @@ class DocParser(object):
             pos = foundpos + 1
         return startpos
 
+    # returns a vector of integers for the tagpath
+    def getData(self, tagpath, pos, end):
+        argres=[]
+        (foundat, argt) = self.findinDoc(tagpath, pos, end)
+        if (argt != None) and (len(argt) > 0) :
+            argList = argt.split('|')
+            argres = [ int(strval) for strval in argList]
+        return argres
 
     def process(self):
 
@@ -237,7 +245,11 @@ def convert2CSS(flatxml, fontsize, ph, pw):
 
     # create a document parser
     dp = DocParser(flatxml, fontsize, ph, pw)
-
     csspage = dp.process()
-
     return csspage
+
+
+def getpageIDMap(flatxml):
+    dp = DocParser(flatxml, 0, 0, 0)
+    pageidnumbers = dp.getData('info.original.pid', 0, -1)
+    return pageidnumbers

DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/topazextract.py

@@ -10,7 +10,12 @@ class Unbuffered:
         return getattr(self.stream, attr)
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
+
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
 import os, csv, getopt
 import zlib, zipfile, tempfile, shutil
 from struct import pack
@@ -18,10 +23,32 @@ from struct import unpack
 
 class TpzDRMError(Exception):
     pass
+
     
 # local support routines
-import kgenpids
-import genbook
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import kgenpids
+    from calibre_plugins.k4mobidedrm import genbook
+else:
+    import kgenpids
+    import genbook
+
+
+# recursive zip creation support routine
+def zipUpDir(myzip, tdir, localname):
+    currentdir = tdir
+    if localname != "":
+        currentdir = os.path.join(currentdir,localname)
+    list = os.listdir(currentdir)
+    for file in list:
+        afilename = file
+        localfilePath = os.path.join(localname, afilename)
+        realfilePath = os.path.join(currentdir,file)
+        if os.path.isfile(realfilePath):
+            myzip.write(realfilePath, localfilePath)
+        elif os.path.isdir(realfilePath):
+            zipUpDir(myzip, tdir, localfilePath)
+
 #
 # Utility routines
 #
@@ -110,9 +137,10 @@ def decryptDkeyRecords(data,PID):
 
 
 class TopazBook:
-    def __init__(self, filename, outdir):
+    def __init__(self, filename):
         self.fo = file(filename, 'rb')
-        self.outdir = outdir
+        self.outdir = tempfile.mkdtemp()
+        # self.outdir = 'rawdat'
         self.bookPayloadOffset = 0
         self.bookHeaderRecords = {}
         self.bookMetadata = {}
@@ -317,21 +345,34 @@ class TopazBook:
                         file(outputFile, 'wb').write(record)
         print " "
 
+    def getHTMLZip(self, zipname):
+        htmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        htmlzip.write(os.path.join(self.outdir,'book.html'),'book.html')
+        htmlzip.write(os.path.join(self.outdir,'book.opf'),'book.opf')
+        if os.path.isfile(os.path.join(self.outdir,'cover.jpg')):
+            htmlzip.write(os.path.join(self.outdir,'cover.jpg'),'cover.jpg')
+        htmlzip.write(os.path.join(self.outdir,'style.css'),'style.css')
+        zipUpDir(htmlzip, self.outdir, 'img')
+        htmlzip.close()
 
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
+    def getSVGZip(self, zipname):
+        svgzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        svgzip.write(os.path.join(self.outdir,'index_svg.xhtml'),'index_svg.xhtml')
+        zipUpDir(svgzip, self.outdir, 'svg')
+        zipUpDir(svgzip, self.outdir, 'img')
+        svgzip.close()
 
+    def getXMLZip(self, zipname):
+        xmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        targetdir = os.path.join(self.outdir,'xml')
+        zipUpDir(xmlzip, targetdir, '')
+        zipUpDir(xmlzip, self.outdir, 'img')
+        xmlzip.close()
+
+    def cleanup(self):
+        if os.path.isdir(self.outdir):
+            pass
+            # shutil.rmtree(self.outdir, True)
 
 def usage(progname):
     print "Removes DRM protection from Topaz ebooks and extract the contents"
@@ -383,58 +424,46 @@ def main(argv=sys.argv):
         return 1
 
     bookname = os.path.splitext(os.path.basename(infile))[0]
-    tempdir = tempfile.mkdtemp()
 
-    tb = TopazBook(infile, tempdir)
+    tb = TopazBook(infile)
     title = tb.getBookTitle()
     print "Processing Book: ", title
     keysRecord, keysRecordRecord = tb.getPIDMetaInfo()
     pidlst = kgenpids.getPidList(keysRecord, keysRecordRecord, k4, pids, serials, kInfoFiles) 
 
     try:
+        print "Decrypting Book"
         tb.processBook(pidlst)
+
+        print "   Creating HTML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_nodrm' + '.htmlz')
+        tb.getHTMLZip(zipname)
+
+        print "   Creating SVG ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
+        tb.getSVGZip(zipname)
+
+        print "   Creating XML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
+        tb.getXMLZip(zipname)
+
+        # removing internal temporary directory of pieces
+        tb.cleanup()
+
     except TpzDRMError, e:
         print str(e)
-        print "   Creating DeBug Full Zip Archive of Book"
-        zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-        myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-        zipUpDir(myzip, tempdir, '')
-        myzip.close()
-        shutil.rmtree(tempdir, True)
+        # tb.cleanup()
         return 1
 
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
-
-    print "   Creating SVG ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
-
-    print "   Creating XML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
-
-    shutil.rmtree(tempdir, True)
+    except Exception, e:
+        print str(e)
+        # tb.cleanup
+        return 1
 
     return 0
                 
 
 if __name__ == '__main__':
+    sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/DeDRM_app.pyw

@@ -124,14 +124,17 @@ class PrefsDialog(Toplevel):
         button = Tkinter.Button(body, text="...", command=self.get_bnkpath)
         button.grid(row=1, column=2)
         
-        Tkinter.Label(body, text='Additional kindle.info file').grid(row=2, sticky=Tkconstants.E)
+        Tkinter.Label(body, text='Additional kindle.info or .kinf file').grid(row=2, sticky=Tkconstants.E)
         self.altinfopath = Tkinter.Entry(body, width=50)
         self.altinfopath.grid(row=2, column=1, sticky=sticky)
         prefdir = self.prefs_array['dir']
-        infofile = os.path.join(prefdir,'kindle.info')
         path = ''
+        infofile = os.path.join(prefdir,'kindle.info')
+        ainfofile = os.path.join(prefdir,'.kinf')
         if os.path.isfile(infofile):
             path = infofile
+        elif os.path.isfile(ainfofile):
+            path = ainfofile
         path = path.encode('utf-8')
         self.altinfopath.insert(0, path)
         button = Tkinter.Button(body, text="...", command=self.get_altinfopath)
@@ -245,8 +248,8 @@ class PrefsDialog(Toplevel):
 
     def get_altinfopath(self):
         cpath = self.altinfopath.get()
-        altinfopath = tkFileDialog.askopenfilename(parent=None, title='Select Alternative kindle.info File',
-            defaultextension='.info', filetypes=[('Kindle Info', '.info'),('All Files', '.*')],
+        altinfopath = tkFileDialog.askopenfilename(parent=None, title='Select Alternative kindle.info or .kinf File',
+            defaultextension='.info', filetypes=[('Kindle Info', '.info'),('Kindle KInf','.kinf')('All Files', '.*')],
             initialdir=cpath)
         if altinfopath:
             altinfopath = os.path.normpath(altinfopath)
@@ -260,6 +263,7 @@ class PrefsDialog(Toplevel):
             filetypes=[('ePub Files','.epub'),
                        ('Kindle','.azw'),
                        ('Kindle','.azw1'),
+                       ('Kindle','.azw4'),
                        ('Kindle','.tpz'),
                        ('Kindle','.mobi'),
                        ('Kindle','.prc'),
@@ -457,18 +461,16 @@ class ConvDialog(Toplevel):
         name, ext = os.path.splitext(os.path.basename(infile))
         ext = ext.lower()
         if ext == '.epub':
-            outfile = os.path.join(outdir, name + '_nodrm.epub')
-            self.p2 = processEPUB(apphome, infile, outfile, rscpath)
+            self.p2 = processEPUB(apphome, infile, outdir, rscpath)
             return 0
         if ext == '.pdb':
             self.p2 = processPDB(apphome, infile, outdir, rscpath)
             return 0
-        if ext in ['.azw', '.azw1', '.prc', '.mobi', '.tpz']:
+        if ext in ['.azw', '.azw1', '.azw4', '.prc', '.mobi', '.tpz']:
             self.p2 = processK4MOBI(apphome, infile, outdir, rscpath)
             return 0
         if ext == '.pdf':
-            outfile = os.path.join(outdir, name + '_nodrm.pdf')
-            self.p2 = processPDF(apphome, infile, outfile, rscpath)
+            self.p2 = processPDF(apphome, infile, outdir, rscpath)
             return 0
         return rv
 
@@ -506,7 +508,7 @@ def processK4MOBI(apphome, infile, outdir, rscpath):
         parms += '-s "' + serialnums + '" '
 
     files = os.listdir(rscpath)
-    filefilter = re.compile("\.info$", re.IGNORECASE)
+    filefilter = re.compile("\.info$|\.kinf$", re.IGNORECASE)
     files = filter(filefilter.search, files)
     if files:
         for filename in files:
@@ -516,16 +518,16 @@ def processK4MOBI(apphome, infile, outdir, rscpath):
     p2 = runit(apphome, cmd, parms)
     return p2
 
-def processPDF(apphome, infile, outfile, rscpath):
+def processPDF(apphome, infile, outdir, rscpath):
     cmd = os.path.join('lib','decryptpdf.py')
-    parms =  '"' + infile + '" "' + outfile + '" "' + rscpath + '"'
+    parms =  '"' + infile + '" "' + outdir + '" "' + rscpath + '"'
     p2 = runit(apphome, cmd, parms)
     return p2
 
-def processEPUB(apphome, infile, outfile, rscpath):
+def processEPUB(apphome, infile, outdir, rscpath):
     # invoke routine to check both Adept and Barnes and Noble
     cmd = os.path.join('lib','decryptepub.py')
-    parms = '"' + infile + '" "' + outfile + '" "' + rscpath + '"'
+    parms = '"' + infile + '" "' + outdir + '" "' + rscpath + '"'
     p2 = runit(apphome, cmd, parms)
     return p2
 

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/convert2xml.py

@@ -20,6 +20,8 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # Get a 7 bit encoded number from string. The most 
 # significant byte comes first and has the high bit (8th) set
@@ -138,7 +140,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside of string table limits')
+            # sys.exit(-1)
 
     def getSize(self):
         return self.size
@@ -258,6 +261,11 @@ class PageParser(object):
         'paragraph.class'     : (1, 'scalar_text', 0, 0),
         'paragraph.firstWord' : (1, 'scalar_number', 0, 0),
         'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridSize'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridTopCenter' : (1, 'scalar_number', 0, 0),
+
 
         'word_semantic'           : (1, 'snippets', 1, 1),
         'word_semantic.type'      : (1, 'scalar_text', 0, 0),
@@ -272,11 +280,17 @@ class PageParser(object):
 
         '_span'           : (1, 'snippets', 1, 0),
         '_span.firstWord' : (1, 'scalar_number', 0, 0),
-        '-span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.gridSize'  : (1, 'scalar_number', 0, 0),
+        '_span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        '_span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'span'           : (1, 'snippets', 1, 0),
         'span.firstWord' : (1, 'scalar_number', 0, 0),
         'span.lastWord'  : (1, 'scalar_number', 0, 0),
+        'span.gridSize'  : (1, 'scalar_number', 0, 0),
+        'span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'extratokens'            : (1, 'snippets', 1, 0),
         'extratokens.type'       : (1, 'scalar_text', 0, 0),

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/decryptepub.py

@@ -24,7 +24,7 @@ def main(argv=sys.argv):
     if len(args) != 3:
         return -1
     infile = args[0]
-    outfile = args[1]
+    outdir = args[1]
     rscpath = args[2]
     errlog = ''
 
@@ -37,6 +37,9 @@ def main(argv=sys.argv):
         print "Error while trying to fix epub"
         return rv
 
+    # determine a good name for the output file
+    outfile = os.path.join(outdir, name + '_nodrm.epub')
+
     rv = 1
     # first try with the Adobe adept epub
     # try with any keyfiles (*.der) in the rscpath

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/decryptpdf.py

@@ -21,10 +21,15 @@ def main(argv=sys.argv):
     if len(args) != 3:
         return -1
     infile = args[0]
-    outfile = args[1]
+    outdir = args[1]
     rscpath = args[2]
     errlog = ''
     rv = 1
+    
+    # determine a good name for the output file
+    name, ext = os.path.splitext(os.path.basename(infile))
+    outfile = os.path.join(outdir, name + '_nodrm.pdf')
+    
     # try with any keyfiles (*.der) in the rscpath
     files = os.listdir(rscpath)
     filefilter = re.compile("\.der$", re.IGNORECASE)

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/erdr2pml.py

@@ -58,8 +58,12 @@
 #  0.17 - added support for pycrypto's DES as well
 #  0.18 - on Windows try PyCrypto first and OpenSSL next
 #  0.19 - Modify the interface to allow use of import
+#  0.20 - modify to allow use inside new interface for calibre plugins
+#  0.21 - Support eReader (drm) version 11. 
+#       - Don't reject dictionary format. 
+#       - Ignore sidebars for dictionaries (different format?)
 
-__version__='0.19'
+__version__='0.21'
 
 class Unbuffered:
     def __init__(self, stream):
@@ -71,32 +75,50 @@ class Unbuffered:
         return getattr(self.stream, attr)
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
-
 import struct, binascii, getopt, zlib, os, os.path, urllib, tempfile
 
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
 Des = None
 if sys.platform.startswith('win'):
     # first try with pycrypto
-    import pycrypto_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import pycrypto_des
+    else:
+        import pycrypto_des
     Des = pycrypto_des.load_pycrypto()
     if Des == None:
         # they try with openssl
-        import openssl_des
+        if inCalibre:
+            from calibre_plugins.erdrpdb2pml import openssl_des
+        else:
+            import openssl_des
         Des = openssl_des.load_libcrypto()
 else:
     # first try with openssl
-    import openssl_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import openssl_des
+    else:
+        import openssl_des
     Des = openssl_des.load_libcrypto()
     if Des == None:
         # then try with pycrypto
-        import pycrypto_des
+        if inCalibre:
+            from calibre_plugins.erdrpdb2pml import pycrypto_des
+        else:
+            import pycrypto_des
         Des = pycrypto_des.load_pycrypto()
 
 # if that did not work then use pure python implementation
 # of DES and try to speed it up with Psycho
 if Des == None:
-    import python_des
+    if inCalibre:
+        from calibre_plugins.erdrpdb2pml import python_des
+    else:
+        import python_des
     Des = python_des.Des
     # Import Psyco if available
     try:
@@ -121,12 +143,18 @@ logging.basicConfig()
 
 
 class Sectionizer(object):
+    bkType = "Book"
+
     def __init__(self, filename, ident):
         self.contents = file(filename, 'rb').read()
         self.header = self.contents[0:72]
         self.num_sections, = struct.unpack('>H', self.contents[76:78])
+        # Dictionary or normal content (TODO: Not hard-coded)
         if self.header[0x3C:0x3C+8] != ident:
-            raise ValueError('Invalid file format')
+            if self.header[0x3C:0x3C+8] == "PDctPPrs":
+                self.bkType = "Dict"
+            else:
+                raise ValueError('Invalid file format')
         self.sections = []
         for i in xrange(self.num_sections):
             offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.contents[78+i*8:78+i*8+8])
@@ -163,15 +191,15 @@ def deXOR(text, sp, table):
     return r
 
 class EreaderProcessor(object):
-    def __init__(self, section_reader, username, creditcard):
-        self.section_reader = section_reader
-        data = section_reader(0)
+    def __init__(self, sect, username, creditcard):
+        self.section_reader = sect.loadSection
+        data = self.section_reader(0)
         version,  = struct.unpack('>H', data[0:2])
         self.version = version
         logging.info('eReader file format version %s', version)
         if version != 272 and version != 260 and version != 259:
             raise ValueError('incorrect eReader version %d (error 1)' % version)
-        data = section_reader(1)
+        data = self.section_reader(1)
         self.data = data
         des = Des(fixKey(data[0:8]))
         cookie_shuf, cookie_size = struct.unpack('>LL', des.decrypt(data[-8:]))
@@ -200,11 +228,17 @@ class EreaderProcessor(object):
         self.num_text_pages = struct.unpack('>H', r[2:4])[0] - 1
         self.num_image_pages = struct.unpack('>H', r[26:26+2])[0]
         self.first_image_page = struct.unpack('>H', r[24:24+2])[0]
+        # Default values
+        self.num_footnote_pages = 0
+        self.num_sidebar_pages = 0
+        self.first_footnote_page = -1
+        self.first_sidebar_page = -1
         if self.version == 272:
             self.num_footnote_pages = struct.unpack('>H', r[46:46+2])[0]
             self.first_footnote_page = struct.unpack('>H', r[44:44+2])[0]
-            self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
-            self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
+            if (sect.bkType == "Book"):
+                self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
+                self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
             # self.num_bookinfo_pages = struct.unpack('>H', r[34:34+2])[0]
             # self.first_bookinfo_page = struct.unpack('>H', r[32:32+2])[0]
             # self.num_chapter_pages = struct.unpack('>H', r[22:22+2])[0]
@@ -220,10 +254,8 @@ class EreaderProcessor(object):
             self.xortable_size = struct.unpack('>H', r[42:42+2])[0]
             self.xortable = self.data[self.xortable_offset:self.xortable_offset + self.xortable_size]
         else:
-            self.num_footnote_pages = 0
-            self.num_sidebar_pages = 0
-            self.first_footnote_page = -1
-            self.first_sidebar_page = -1
+            # Nothing needs to be done
+            pass
             # self.num_bookinfo_pages = 0
             # self.num_chapter_pages = 0
             # self.num_link_pages = 0
@@ -248,10 +280,14 @@ class EreaderProcessor(object):
             encrypted_key_sha = r[44:44+20]
             encrypted_key = r[64:64+8]
         elif version == 260:
-            if drm_sub_version != 13:
+            if drm_sub_version != 13 and drm_sub_version != 11:
                 raise ValueError('incorrect eReader version %d (error 3)' % drm_sub_version)
-            encrypted_key = r[44:44+8]
-            encrypted_key_sha = r[52:52+20]
+            if drm_sub_version == 13:
+                encrypted_key = r[44:44+8]
+                encrypted_key_sha = r[52:52+20]
+            else:
+                encrypted_key = r[64:64+8]
+                encrypted_key_sha = r[44:44+20]
         elif version == 272:
             encrypted_key = r[172:172+8]
             encrypted_key_sha = r[56:56+20]
@@ -337,6 +373,12 @@ class EreaderProcessor(object):
                 r += fmarker
                 fnote_ids = fnote_ids[id_len+4:]
 
+        # TODO: Handle dictionary index (?) pages - which are also marked as
+        # sidebar_pages (?). For now dictionary sidebars are ignored
+        # For dictionaries - record 0 is null terminated strings, followed by
+        # blocks of around 62000 bytes and a final block. Not sure of the
+        # encoding
+
         # now handle sidebar pages
         if self.num_sidebar_pages > 0:
             r += '\n'
@@ -349,7 +391,7 @@ class EreaderProcessor(object):
                 id_len = ord(sbar_ids[2])
                 id = sbar_ids[3:3+id_len]
                 smarker = '<sidebar id="%s">\n' % id
-                smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_footnote_page + i)))
+                smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_sidebar_page + i)))
                 smarker += '\n</sidebar>\n'
                 r += smarker
                 sbar_ids = sbar_ids[id_len+4:]
@@ -370,7 +412,7 @@ def convertEreaderToPml(infile, name, cc, outdir):
     bookname = os.path.splitext(os.path.basename(infile))[0]
     print "   Decoding File"
     sect = Sectionizer(infile, 'PNRdPPrs')
-    er = EreaderProcessor(sect.loadSection, name, cc)
+    er = EreaderProcessor(sect, name, cc)
 
     if er.getNumImages() > 0:
         print "   Extracting images"
@@ -480,5 +522,6 @@ def main(argv=None):
 
 
 if __name__ == "__main__":
+    sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/flatxml2html.py

@@ -271,6 +271,9 @@ class DocParser(object):
 
         pclass = self.getClass(pclass)
 
+        # if paragraph uses extratokens (extra glyphs) then make it fixed
+        (pos, extraglyphs) = self.findinDoc('paragraph.extratokens',start,end)
+
         # build up a description of the paragraph in result and return it
         # first check for the  basic - all words paragraph
         (pos, sfirst) = self.findinDoc('paragraph.firstWord',start,end)
@@ -280,6 +283,7 @@ class DocParser(object):
             last = int(slast)
             
             makeImage = (regtype == 'vertical') or (regtype == 'table')
+            makeImage = makeImage or (extraglyphs != None) 
             if self.fixedimage:
                 makeImage = makeImage or (regtype == 'fixed')
 
@@ -353,6 +357,8 @@ class DocParser(object):
 
         word_class = ''
 
+        word_semantic_type = ''
+
         while (line < end) :
 
             (name, argres) = self.lineinDoc(line)
@@ -512,6 +518,72 @@ class DocParser(object):
         return parares
 
 
+    def buildTOCEntry(self, pdesc) :
+        parares = ''
+        sep =''
+        tocentry = ''
+        handle_links = len(self.link_id) > 0
+
+        lstart = 0
+
+        cnt = len(pdesc)
+        for j in xrange( 0, cnt) :
+
+            (wtype, num) = pdesc[j]
+
+            if wtype == 'ocr' :
+                word = self.ocrtext[num]
+                sep = ' '
+
+                if handle_links:
+                    link = self.link_id[num]
+                    if (link > 0):
+                        linktype = self.link_type[link-1]
+                        title = self.link_title[link-1]
+                        title = title.rstrip('. ')
+                        alt_title = parares[lstart:]
+                        alt_title = alt_title.strip()
+                        # now strip off the actual printed page number
+                        alt_title = alt_title.rstrip('01234567890ivxldIVXLD-.')
+                        alt_title = alt_title.rstrip('. ')
+                        # skip over any external links - can't have them in a books toc
+                        if linktype == 'external' :
+                            title = ''
+                            alt_title = ''
+                            linkpage = ''
+                        else : 
+                            if len(self.link_page) >= link :
+                                ptarget = self.link_page[link-1] - 1
+                                linkpage = '%04d' % ptarget
+                            else :
+                                # just link to the current page
+                                linkpage = self.id[4:]
+                        if len(alt_title) >= len(title):
+                            title = alt_title
+                        if title != '' and linkpage != '':
+                            tocentry += title + '|' + linkpage + '\n'
+                        lstart = len(parares)
+                        if word == '_link_' : word = ''
+                    elif (link < 0) :
+                        if word == '_link_' : word = ''
+
+                if word == '_lb_':
+                    word = ''
+                    sep = ''
+
+                if num in self.dehyphen_rootid :
+                    word = word[0:-1]
+                    sep = ''
+
+                parares += word + sep
+
+            else :
+                continue
+
+        return tocentry
+
+
+
     
     # walk the document tree collecting the information needed
     # to build an html page using the ocrText
@@ -519,6 +591,7 @@ class DocParser(object):
     def process(self):
 
         htmlpage = ''
+        tocinfo = ''
 
         # get the ocr text
         (pos, argres) = self.findinDoc('info.word.ocrText',0,-1)
@@ -644,9 +717,9 @@ class DocParser(object):
                         ptype = 'end'
                         first_para_continued = False
                     (pclass, pdesc) = self.getParaDescription(start,end, regtype)
+                    tocinfo += self.buildTOCEntry(pdesc)
                     htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
 
-
                 elif (regtype == 'vertical') or (regtype == 'table') :
                     ptype = 'full'
                     if inGroup:
@@ -704,12 +777,11 @@ class DocParser(object):
                 htmlpage = htmlpage[0:-4]
             last_para_continued = False
 
-        return htmlpage
-
+        return htmlpage, tocinfo
 
 
 def convert2HTML(flatxml, classlst, fileid, bookDir, gdict, fixedimage):
     # create a document parser
     dp = DocParser(flatxml, classlst, fileid, bookDir, gdict, fixedimage)
-    htmlpage = dp.process()
-    return htmlpage
+    htmlpage, tocinfo = dp.process()
+    return htmlpage, tocinfo

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/flatxml2svg.py

@@ -10,17 +10,94 @@ from struct import unpack
 
 
 class PParser(object):
-    def __init__(self, gd, flatxml):
+    def __init__(self, gd, flatxml, meta_array):
         self.gd = gd
         self.flatdoc = flatxml.split('\n')
+        self.docSize = len(self.flatdoc)
         self.temp = []
-        foo = self.getData('page.h') or self.getData('book.h')
-        self.ph = foo[0]
-        foo = self.getData('page.w') or self.getData('book.w')
-        self.pw = foo[0]
-        self.gx = self.getData('info.glyph.x')
-        self.gy = self.getData('info.glyph.y')
-        self.gid = self.getData('info.glyph.glyphID')
+        
+        self.ph = -1
+        self.pw = -1
+        startpos = self.posinDoc('page.h') or self.posinDoc('book.h')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.ph = max(self.ph, int(argres))
+        startpos = self.posinDoc('page.w') or self.posinDoc('book.w')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.pw = max(self.pw, int(argres))
+        
+        if self.ph <= 0:
+            self.ph = int(meta_array.get('pageHeight', '11000'))
+        if self.pw <= 0:
+            self.pw = int(meta_array.get('pageWidth', '8500'))
+
+        res = []
+        startpos = self.posinDoc('info.glyph.x')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.x', p)
+            res.extend(argres)
+        self.gx = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.y')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.y', p)
+            res.extend(argres)
+        self.gy = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.glyphID')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.glyphID', p)
+            res.extend(argres)
+        self.gid = res
+
+
+    # return tag at line pos in document
+    def lineinDoc(self, pos) :
+        if (pos >= 0) and (pos < self.docSize) :
+            item = self.flatdoc[pos]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+        return name, argres
+
+    # find tag in doc if within pos to end inclusive
+    def findinDoc(self, tagpath, pos, end) :
+        result = None
+        if end == -1 :
+            end = self.docSize
+        else:
+            end = min(self.docSize, end)
+        foundat = -1
+        for j in xrange(pos, end):
+            item = self.flatdoc[j]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+            if name.endswith(tagpath) :
+                result = argres
+                foundat = j
+                break
+        return foundat, result
+
+    # return list of start positions for the tagpath
+    def posinDoc(self, tagpath):
+        startpos = []
+        pos = 0
+        res = ""
+        while res != None :
+            (foundpos, res) = self.findinDoc(tagpath, pos, -1)
+            if res != None :
+                startpos.append(foundpos)
+            pos = foundpos + 1
+        return startpos
+
     def getData(self, path):
         result = None
         cnt = len(self.flatdoc)
@@ -39,6 +116,23 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
+    def getDataatPos(self, path, pos):
+        result = None
+        item = self.flatdoc[pos]
+        if item.find('=') >= 0:
+            (name, argt) = item.split('=')
+            argres = argt.split('|')
+        else:
+            name = item
+            argres = []
+        if (len(argres) > 0) :
+            for j in xrange(0,len(argres)):
+                argres[j] = int(argres[j])
+        if (name.endswith(path)):
+            result = argres
+        return result
+
     def getDataTemp(self, path):
         result = None
         cnt = len(self.temp)
@@ -58,6 +152,7 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
     def getImages(self):
         result = []
         self.temp = self.flatdoc
@@ -69,6 +164,7 @@ class PParser(object):
             src = self.getDataTemp('img.src')[0]
             result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
         return result
+
     def getGlyphs(self):
         result = []
         if (self.gid != None) and (len(self.gid) > 0):
@@ -84,25 +180,25 @@ class PParser(object):
         return result
 
 
-def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi):
+def convert2SVG(gdict, flat_xml, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi):
     ml = ''
-    pp = PParser(gdict, flat_xml)
+    pp = PParser(gdict, flat_xml, meta_array)
     ml += '<?xml version="1.0" standalone="no"?>\n'
     if (raw):
         ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
         ml += '<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1)
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
     else:
         ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
         ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
         ml += '<script><![CDATA[\n'
         ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
         ml += 'var dpi=%d;\n' % scaledpi
-        if (counter) :
-            ml += 'var prevpage="page%04d.xhtml";\n' % (counter - 1)
-        if (counter < numfiles-1) :
-            ml += 'var nextpage="page%04d.xhtml";\n' % (counter + 1)
+        if (previd) :
+            ml += 'var prevpage="page%04d.xhtml";\n' % (previd)
+        if (nextid) :
+            ml += 'var nextpage="page%04d.xhtml";\n' % (nextid)
         ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
         ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
         ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
@@ -115,10 +211,11 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         ml += '</head>\n'
         ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
         ml += '<div style="white-space:nowrap;">\n'
-        if (counter == 0) :
+        if previd == None:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n'
+        
         ml += '<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph)
     if (pp.gid != None): 
         ml += '<defs>\n'
@@ -134,12 +231,14 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         for j in xrange(0,len(pp.gid)):
             ml += '<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j])
     if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
-        ml += '<text x="10" y="10" font-family="Helvetica" font-size="100" stroke="black">This page intentionally left blank.</text>\n<text x="10" y="110" font-family="Helvetica" font-size="50" stroke="black">Until this notice unintentionally gave it content.  (gensvg.py)</text>\n'
+        xpos = "%d" % (pp.pw // 3)
+        ypos = "%d" % (pp.ph // 3)
+        ml += '<text x="' + xpos + '" y="' + ypos + '" font-size="' + meta_array['fontSize'] + '" font-family="Helvetica" stroke="black">This page intentionally left blank.</text>\n'
     if (raw) :
         ml += '</svg>'
     else :
         ml += '</svg></a>\n'
-        if (counter == numfiles - 1) :
+        if nextid == None:
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else :
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n'

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/genbook.py

@@ -19,12 +19,25 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # local support routines
-import convert2xml
-import flatxml2html
-import flatxml2svg
-import stylexml2css
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre :
+    from calibre_plugins.k4mobidedrm import convert2xml
+    from calibre_plugins.k4mobidedrm import flatxml2html
+    from calibre_plugins.k4mobidedrm import flatxml2svg
+    from calibre_plugins.k4mobidedrm import stylexml2css
+else :
+    import convert2xml
+    import flatxml2html
+    import flatxml2svg
+    import stylexml2css
 
 
 # Get a 7 bit encoded number from a file
@@ -103,7 +116,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside or string table limits')
+            # sys.exit(-1)
     def getSize(self):
         return self.size
     def getPos(self):
@@ -360,10 +374,34 @@ def generateBook(bookDir, raw, fixedimage):
     (ph, pw) = getPageDim(flat_xml)
     if (ph == '-1') or (ph == '0') : ph = '11000'
     if (pw == '-1') or (pw == '0') : pw = '8500'
+    meta_array['pageHeight'] = ph
+    meta_array['pageWidth'] = pw
+    if 'fontSize' not in meta_array.keys():
+        meta_array['fontSize'] = fontsize
 
-    # print '     ', 'other0000.dat'
+    # process other.dat for css info and for map of page files to svg images
+    # this map is needed because some pages actually are made up of multiple
+    # pageXXXX.xml files
     xname = os.path.join(bookDir, 'style.css')
     flat_xml = convert2xml.fromData(dict, otherFile)
+
+    # extract info.original.pid to get original page information
+    pageIDMap = {}
+    pageidnums = stylexml2css.getpageIDMap(flat_xml)
+    if len(pageidnums) == 0:
+        filenames = os.listdir(pageDir)
+        numfiles = len(filenames)
+        for k in range(numfiles):
+            pageidnums.append(k)
+    # create a map from page ids to list of page file nums to process for that page
+    for i in range(len(pageidnums)):
+        id = pageidnums[i]
+        if id in pageIDMap.keys():
+            pageIDMap[id].append(i)
+        else:
+            pageIDMap[id] = [i]
+
+    # now get the css info
     cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
     file(xname, 'wb').write(cssstr)
     xname = os.path.join(xmlDir, 'other0000.xml')
@@ -403,6 +441,9 @@ def generateBook(bookDir, raw, fixedimage):
     glyfile.close()
     print " "
 
+    # build up tocentries while processing html
+    tocentries = ''
+
     # start up the html
     htmlFileName = "book.html"
     htmlstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -425,6 +466,77 @@ def generateBook(bookDir, raw, fixedimage):
     # readability when rendering to the screen.  
     scaledpi = 1440.0
 
+    filenames = os.listdir(pageDir)
+    filenames = sorted(filenames)
+    numfiles = len(filenames)
+
+    xmllst = []
+
+    for filename in filenames:
+        # print '     ', filename
+        print ".",
+        fname = os.path.join(pageDir,filename)
+        flat_xml = convert2xml.fromData(dict, fname)
+
+        # keep flat_xml for later svg processing
+        xmllst.append(flat_xml)
+
+        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
+        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
+
+        # first get the html
+        pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
+        tocentries += tocinfo 
+        htmlstr += pagehtml
+
+    # finish up the html string and output it
+    htmlstr += '</body>\n</html>\n'
+    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
+    
+    print " "
+    print 'Extracting Table of Contents from Amazon OCR'
+
+    # first create a table of contents file for the svg images
+    tochtml = '<?xml version="1.0" encoding="utf-8"?>\n'
+    tochtml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
+    tochtml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
+    tochtml += '<head>\n'
+    tochtml += '<title>' + meta_array['Title'] + '</title>\n'
+    tochtml += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
+    tochtml += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
+    if 'ASIN' in meta_array:
+        tochtml += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
+    if 'GUID' in meta_array:
+        tochtml += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
+    tochtml += '</head>\n'
+    tochtml += '<body>\n'
+
+    tochtml += '<h2>Table of Contents</h2>\n'
+    start = pageidnums[0]
+    if (raw):
+        startname = 'page%04d.svg' % start
+    else:
+        startname = 'page%04d.xhtml' % start
+
+    tochtml += '<h3><a href="' + startname + '">Start of Book</a></h3>\n'
+    # build up a table of contents for the svg xhtml output
+    toclst = tocentries.split('\n')
+    toclst.pop()
+    for entry in toclst:
+        print entry
+        title, pagenum = entry.split('|')
+        id = pageidnums[int(pagenum)]
+        if (raw):
+            fname = 'page%04d.svg' % id
+        else:
+            fname = 'page%04d.xhtml' % id
+        tochtml += '<h3><a href="'+ fname + '">' + title + '</a></h3>\n'
+    tochtml += '</body>\n'
+    tochtml += '</html>\n'
+    file(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
+
+
+    # now create index_svg.xhtml that points to all required files
     svgindex = '<?xml version="1.0" encoding="utf-8"?>\n'
     svgindex += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
     svgindex += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
@@ -439,50 +551,42 @@ def generateBook(bookDir, raw, fixedimage):
     svgindex += '</head>\n'
     svgindex += '<body>\n'
 
-    filenames = os.listdir(pageDir)
-    filenames = sorted(filenames)
-    numfiles = len(filenames)
-    counter = 0
-
-    for filename in filenames:
-        # print '     ', filename
-        print ".",
-
-        fname = os.path.join(pageDir,filename)
-        flat_xml = convert2xml.fromData(dict, fname)
-
-        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
-        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
-
-        # first get the html
-        htmlstr += flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
-
-        # now get the svg image of the page
-        svgxml = flatxml2svg.convert2SVG(gd, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi)
-
+    print "Building svg images of each book page"
+    svgindex += '<h2>List of Pages</h2>\n'
+    svgindex += '<div>\n'
+    idlst = sorted(pageIDMap.keys())
+    numids = len(idlst)
+    cnt = len(idlst)
+    previd = None
+    for j in range(cnt):
+        pageid = idlst[j]
+        if j < cnt - 1:
+            nextid = idlst[j+1]
+        else:
+            nextid = None
+        print '.',
+        pagelst = pageIDMap[pageid]
+        flat_svg = ''
+        for page in pagelst:
+            flat_svg += xmllst[page]
+        svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
         if (raw) :
-            pfile = open(os.path.join(svgDir,filename.replace('.dat','.svg')), 'w')
-            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (counter, counter)
+            pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
+            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid)
         else :
-            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % counter), 'w')
-            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (counter, counter)
-
-
+            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
+            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid)
+        previd = pageid
         pfile.write(svgxml)
         pfile.close()
-
         counter += 1
-
-    print " "
-
-    # finish up the html string and output it
-    htmlstr += '</body>\n</html>\n'
-    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
-
-    # finish up the svg index string and output it
+    svgindex += '</div>\n'
+    svgindex += '<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n'
     svgindex += '</body>\n</html>\n'
     file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
 
+    print " "
+
     # build the opf file
     opfname = os.path.join(bookDir, 'book.opf')
     opfstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -504,7 +608,7 @@ def generateBook(bookDir, raw, fixedimage):
     opfstr += '   </metadata>\n'
     opfstr += '<manifest>\n'
     opfstr += '   <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n'
-    opfstr += '   <item id="stylesheet" href="style.css" media-type="text.css"/>\n'
+    opfstr += '   <item id="stylesheet" href="style.css" media-type="text/css"/>\n'
     # adding image files to manifest
     filenames = os.listdir(imgDir)
     filenames = sorted(filenames)
@@ -562,7 +666,7 @@ def main(argv):
         return 1 
 
     raw = 0
-    fixedimage = False
+    fixedimage = True
     for o, a in opts:
         if o =="-h":
             usage()

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/ineptpdf.py

@@ -157,6 +157,7 @@ def _load_crypto_libcrypto():
             return out.raw
 
     class AES(object):
+        MODE_CBC = 0
         @classmethod
         def new(cls, userkey, mode, iv):
             self = AES()

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/k4mobidedrm.py

@@ -16,20 +16,8 @@ from __future__ import with_statement
 #    unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates 
 #    and many many others
 
-# It can run standalone to convert K4M/K4PC/Mobi files, or it can be installed as a
-# plugin for Calibre (http://calibre-ebook.com/about) so that importing
-# K4 or Mobi with DRM is no londer a multi-step process.
-#
-# ***NOTE*** If you are using this script as a calibre plugin for a K4M or K4PC ebook
-# then calibre must be installed on the same machine and in the same account as K4PC or K4M
-# for the plugin version to function properly.
-#
-# To create a Calibre plugin, rename this file so that the filename
-# ends in '_plugin.py', put it into a ZIP file with all its supporting python routines
-# and import that ZIP into Calibre using its plugin configuration GUI.
 
-
-__version__ = '2.8'
+__version__ = '3.9'
 
 class Unbuffered:
     def __init__(self, stream):
@@ -43,11 +31,8 @@ class Unbuffered:
 import sys
 import os, csv, getopt
 import string
-import binascii
-import zlib
 import re
-import zlib, zipfile, tempfile, shutil
-from struct import pack, unpack, unpack_from
+import traceback
 
 class DrmException(Exception):
     pass
@@ -57,19 +42,15 @@ if 'calibre' in sys.modules:
 else:
     inCalibre = False
 
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import mobidedrm
+    from calibre_plugins.k4mobidedrm import topazextract
+    from calibre_plugins.k4mobidedrm import kgenpids
+else:
+    import mobidedrm
+    import topazextract
+    import kgenpids
+        
 
 # cleanup bytestring filenames
 # borrowed from calibre from calibre/src/calibre/__init__.py
@@ -94,13 +75,9 @@ def cleanup_name(name):
     return one
 
 def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
-    import mobidedrm
-    import topazextract
-    import kgenpids
-
     # handle the obvious cases at the beginning
     if not os.path.isfile(infile):
-        print "Error: Input file does not exist"
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: Input file does not exist"
         return 1
 
     mobi = True
@@ -113,75 +90,62 @@ def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
     if mobi:
         mb = mobidedrm.MobiBook(infile)
     else:
-        tempdir = tempfile.mkdtemp()
-        mb = topazextract.TopazBook(infile, tempdir)
+        mb = topazextract.TopazBook(infile)
 
     title = mb.getBookTitle()
     print "Processing Book: ", title
     filenametitle = cleanup_name(title)
     outfilename = bookname
-    if len(bookname)>4 and len(filenametitle)>4 and bookname[:4] != filenametitle[:4]:
+    if len(outfilename)<=8 or len(filenametitle)<=8:
         outfilename = outfilename + "_" + filenametitle
+    elif outfilename[:8] != filenametitle[:8]:
+        outfilename = outfilename[:8] + "_" + filenametitle
+        
+    # avoid excessively long file names
+    if len(outfilename)>150:
+        outfilename = outfilename[:150]
 
     # build pid list
     md1, md2 = mb.getPIDMetaInfo()
     pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
 
     try:
-        if mobi:
-            unlocked_file = mb.processBook(pidlst)
-        else:
-            mb.processBook(pidlst)
+        mb.processBook(pidlst)
 
     except mobidedrm.DrmException, e:
-        print "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+    except topazextract.TpzDRMError, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
         return 1
     except Exception, e:
-        if not mobi:
-            print "Error: " + str(e) + "\nDRM Removal Failed.\n"
-            print "   Creating DeBug Full Zip Archive of Book"
-            zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-            myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-            zipUpDir(myzip, tempdir, '')
-            myzip.close()
-            shutil.rmtree(tempdir, True)
-            return 1
-        pass
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
 
     if mobi:
-        outfile = os.path.join(outdir,outfilename + '_nodrm' + '.mobi')
-        file(outfile, 'wb').write(unlocked_file)
+        if mb.getPrintReplica():
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.azw4')
+        else:
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.mobi')
+        mb.getMobiFile(outfile)
         return 0            
 
-    # topaz:  build up zip archives of results
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
+    # topaz: 
+    print "   Creating NoDRM HTMLZ Archive"
+    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.htmlz')
+    mb.getHTMLZip(zipname)
 
     print "   Creating SVG ZIP Archive"
     zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
+    mb.getSVGZip(zipname)
 
     print "   Creating XML ZIP Archive"
     zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
+    mb.getXMLZip(zipname)
+
+    # remove internal temporary directory of Topaz pieces
+    mb.cleanup()
 
-    shutil.rmtree(tempdir, True)
     return 0
 
 
@@ -204,7 +168,6 @@ def main(argv=sys.argv):
     print ('K4MobiDeDrm v%(__version__)s '
 	   'provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc .' % globals())
 
-    print ' '
     try:
         opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
     except getopt.GetoptError, err:
@@ -236,7 +199,6 @@ def main(argv=sys.argv):
 	kInfoFiles = None
     infile = args[0]
     outdir = args[1]
-
     return decryptBook(infile, outdir, k4, kInfoFiles, serials, pids)
 
 
@@ -244,131 +206,3 @@ if __name__ == '__main__':
     sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 
-if not __name__ == "__main__" and inCalibre:
-    from calibre.customize import FileTypePlugin
-
-    class K4DeDRM(FileTypePlugin):
-        name                = 'K4PC, K4Mac, Kindle Mobi and Topaz DeDRM' # Name of the plugin
-        description         = 'Removes DRM from K4PC and Mac, Kindle Mobi and Topaz files. \
-                                Provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc.'
-        supported_platforms = ['osx', 'windows', 'linux'] # Platforms this plugin will run on
-        author              = 'DiapDealer, SomeUpdates' # The author of this plugin
-        version             = (0, 2, 8)   # The version number of this plugin
-        file_types          = set(['prc','mobi','azw','azw1','tpz']) # The file types that this plugin will be applied to
-        on_import           = True # Run this plugin during the import
-        priority            = 210  # run this plugin before mobidedrm, k4pcdedrm, k4dedrm
-
-        def run(self, path_to_ebook):
-            from calibre.gui2 import is_ok_to_use_qt
-            from PyQt4.Qt import QMessageBox
-            from calibre.ptempfile import PersistentTemporaryDirectory
-
-            import kgenpids
-            import zlib
-            import zipfile
-            import topazextract
-            import mobidedrm
-
-            k4 = True
-	    if sys.platform.startswith('linux'):
-		k4 = False
-            pids = []
-            serials = []
-            kInfoFiles = []
-
-            # Get supplied list of PIDs to try from plugin customization.
-            customvalues = self.site_customization.split(',')
-            for customvalue in customvalues:
-                customvalue = str(customvalue)
-                customvalue = customvalue.strip()
-            	if len(customvalue) == 10 or len(customvalue) == 8:
-                    pids.append(customvalue)
-            	else :
-                    if len(customvalue) == 16 and customvalue[0] == 'B':
-                        serials.append(customvalue)
-                    else:
-                        print "%s is not a valid Kindle serial number or PID." % str(customvalue)
-            		
-            # Load any kindle info files (*.info) included Calibre's config directory.
-            try:
-                # Find Calibre's configuration directory.
-                confpath = os.path.split(os.path.split(self.plugin_path)[0])[0]
-                print 'K4MobiDeDRM: Calibre configuration directory = %s' % confpath
-                files = os.listdir(confpath)
-                filefilter = re.compile("\.info$", re.IGNORECASE)
-                files = filter(filefilter.search, files)
-    
-                if files:
-                    for filename in files:
-                        fpath = os.path.join(confpath, filename)
-                        kInfoFiles.append(fpath)
-                        print 'K4MobiDeDRM: Kindle info file %s found in config folder.' % filename
-            except IOError:
-                print 'K4MobiDeDRM: Error reading kindle info files from config directory.'
-                pass
-
-
-            mobi = True
-            magic3 = file(path_to_ebook,'rb').read(3)
-            if magic3 == 'TPZ':
-                mobi = False
-
-            bookname = os.path.splitext(os.path.basename(path_to_ebook))[0]
-
-            if mobi:
-                mb = mobidedrm.MobiBook(path_to_ebook)
-            else:
-                tempdir = PersistentTemporaryDirectory()
-                mb = topazextract.TopazBook(path_to_ebook, tempdir)
-
-            title = mb.getBookTitle()
-            md1, md2 = mb.getPIDMetaInfo()
-            pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
-
-            try:
-                if mobi:
-                    unlocked_file = mb.processBook(pidlst)
-                else:
-                    mb.processBook(pidlst)
-
-            except mobidedrm.DrmException:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-            except topazextract.TpzDRMError:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-
-            print "Success!"
-            if mobi:
-                of = self.temporary_file(bookname+'.mobi')
-                of.write(unlocked_file)
-                of.close()
-                return of.name
-
-            # topaz:  build up zip archives of results
-            print "   Creating HTML ZIP Archive"
-            of = self.temporary_file(bookname + '.zip')
-            myzip = zipfile.ZipFile(of.name,'w',zipfile.ZIP_DEFLATED, False)
-            myzip.write(os.path.join(tempdir,'book.html'),'book.html')
-            myzip.write(os.path.join(tempdir,'book.opf'),'book.opf')
-            if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-                myzip.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-            myzip.write(os.path.join(tempdir,'style.css'),'style.css')
-            zipUpDir(myzip, tempdir, 'img')
-            myzip.close()
-            return of.name
-
-        def customization_help(self, gui=False):
-            return 'Enter 10 character PIDs and/or Kindle serial numbers, separated by commas.'

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/k4mutils.py

@@ -1,10 +1,13 @@
-# standlone set of Mac OSX specific routines needed for K4DeDRM
+# standlone set of Mac OSX specific routines needed for KindleBooks
 
 from __future__ import with_statement
+
 import sys
 import os
-import subprocess
+import os.path
 
+import subprocess
+from struct import pack, unpack, unpack_from
 
 class DrmException(Exception):
     pass
@@ -66,12 +69,9 @@ def _load_crypto_libcrypto():
                 raise DrmException('AES decryption failed')
             return out.raw
 
-        def keyivgen(self, passwd):
-            salt = '16743'
-            saltlen = 5
+        def keyivgen(self, passwd, salt, iter, keylen):
+            saltlen = len(salt)
             passlen = len(passwd)
-            iter = 0x3e8
-            keylen = 80
             out = create_string_buffer(keylen)
             rv = PKCS5_PBKDF2_HMAC_SHA1(passwd, passlen, salt, saltlen, iter, keylen, out)
             return out.raw
@@ -91,13 +91,79 @@ LibCrypto = _load_crypto()
 # Utility Routines
 #
 
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA256(message):
+    ctx = hashlib.sha256()
+    ctx.update(message)
+    return ctx.digest()
 
 # Various character maps used to decrypt books. Probably supposed to act as obfuscation
 charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
 charMap2 = "ZB0bYyc1xDdW2wEV3Ff7KkPpL8UuGA4gz-Tme9Nn_tHh5SvXCsIiR6rJjQaqlOoM" 
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
 
+# For kinf approach of K4PC/K4Mac
+# On K4PC charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
+# For Mac they seem to re-use charMap2 here
+charMap5 = charMap2
+
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+# For .kinf approach of K4PC and now K4Mac
+# generate table of prime number less than or equal to int n
+def primes(n):
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
 
 
 # uses a sub process to get the Hard Drive Serial Number using ioreg
@@ -129,47 +195,223 @@ def GetVolumeSerialNumber():
                 foundIt = True
                 break
     if not foundIt:
-        sernum = '9999999999'
+        sernum = ''
     return sernum
 
+def GetUserHomeAppSupKindleDirParitionName():
+    home = os.getenv('HOME')
+    dpath =  home + '/Library/Application Support/Kindle'
+    cmdline = '/sbin/mount'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    disk = ''
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.startswith('/dev'):
+            (devpart, mpath) = resline.split(' on ')
+            dpart = devpart[5:]
+            pp = mpath.find('(')
+            if pp >= 0:
+                mpath = mpath[:pp-1]
+            if dpath.startswith(mpath):
+                disk = dpart
+    return disk
+
+# uses a sub process to get the UUID of the specified disk partition using ioreg
+def GetDiskPartitionUUID(diskpart):
+    uuidnum = os.getenv('MYUUIDNUMBER')
+    if uuidnum != None:
+        return uuidnum
+    cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    bsdname = None
+    uuidnum = None
+    foundIt = False
+    nest = 0
+    uuidnest = -1
+    partnest = -2
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.find('{') >= 0:
+            nest += 1
+        if resline.find('}') >= 0:
+            nest -= 1
+        pp = resline.find('"UUID" = "')
+        if pp >= 0:
+            uuidnum = resline[pp+10:-1]
+            uuidnum = uuidnum.strip()
+            uuidnest = nest
+            if partnest == uuidnest and uuidnest > 0:
+                foundIt = True
+                break
+        bb = resline.find('"BSD Name" = "')
+        if bb >= 0:
+            bsdname = resline[bb+14:-1]
+            bsdname = bsdname.strip()
+            if (bsdname == diskpart):
+                partnest = nest
+            else :
+                partnest = -2
+            if partnest == uuidnest and partnest > 0:
+                foundIt = True
+                break
+        if nest == 0:
+            partnest = -2
+            uuidnest = -1
+            uuidnum = None
+            bsdname = None
+    if not foundIt:
+        uuidnum = ''
+    return uuidnum
+    
+def GetMACAddressMunged():
+    macnum = os.getenv('MYMACNUM')
+    if macnum != None:
+        return macnum
+    cmdline = '/sbin/ifconfig en0'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    macnum = None
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        pp = resline.find('ether ')
+        if pp >= 0:
+            macnum = resline[pp+6:-1]
+            macnum = macnum.strip()
+            # print "original mac", macnum
+            # now munge it up the way Kindle app does
+            # by xoring it with 0xa5 and swapping elements 3 and 4
+            maclst = macnum.split(':')
+            n = len(maclst)
+            if n != 6:
+                fountIt = False
+                break
+            for i in range(6):
+                maclst[i] = int('0x' + maclst[i], 0)
+            mlst = [0x00, 0x00, 0x00, 0x00, 0x00, 0x00]
+            mlst[5] = maclst[5] ^ 0xa5
+            mlst[4] = maclst[3] ^ 0xa5
+            mlst[3] = maclst[4] ^ 0xa5
+            mlst[2] = maclst[2] ^ 0xa5
+            mlst[1] = maclst[1] ^ 0xa5
+            mlst[0] = maclst[0] ^ 0xa5
+            macnum = "%0.2x%0.2x%0.2x%0.2x%0.2x%0.2x" % (mlst[0], mlst[1], mlst[2], mlst[3], mlst[4], mlst[5])
+            foundIt = True
+            break
+    if not foundIt:
+        macnum = ''
+    return macnum
+
+
 # uses unix env to get username instead of using sysctlbyname 
 def GetUserName():
     username = os.getenv('USER')
     return username
 
 
-def encode(data, map):
-    result = ""
-    for char in data:
-        value = ord(char)
-        Q = (value ^ 0x80) // len(map)
-        R = value % len(map)
-        result += map[Q]
-        result += map[R]
-    return result
-
-import hashlib
-
-def SHA256(message):
-    ctx = hashlib.sha256()
-    ctx.update(message)
-    return ctx.digest()
-
 # implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used by Kindle for Mac versions < 1.6.0
 def CryptUnprotectData(encryptedData):
-    sp = GetVolumeSerialNumber() + '!@#' + GetUserName()
+    sernum = GetVolumeSerialNumber()
+    if sernum == '':
+        sernum = '9999999999'
+    sp = sernum + '!@#' + GetUserName()
     passwdData = encode(SHA256(sp),charMap1)
+    salt = '16743'
+    iter = 0x3e8
+    keylen = 0x80
     crp = LibCrypto()
-    key_iv = crp.keyivgen(passwdData)
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
     key = key_iv[0:32]
     iv = key_iv[32:48]
     crp.set_decrypt_key(key,iv)
     cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext,charMap1)
+    return cleartext
+
+
+def isNewInstall():
+    home = os.getenv('HOME')
+    # soccer game fan anyone
+    dpath = home + '/Library/Application Support/Kindle/storage/.pes2011'
+    # print dpath, os.path.exists(dpath)
+    if os.path.exists(dpath):
+        return True
+    return False
+    
+
+def GetIDString():
+    # K4Mac now has an extensive set of ids strings it uses
+    # in encoding pids and in creating unique passwords
+    # for use in its own version of CryptUnprotectDataV2
+
+    # BUT Amazon has now become nasty enough to detect when its app
+    # is being run under a debugger and actually changes code paths
+    # including which one of these strings is chosen, all to try 
+    # to prevent reverse engineering
+
+    # Sad really ... they will only hurt their own sales ...
+    # true book lovers really want to keep their books forever
+    # and move them to their devices and DRM prevents that so they 
+    # will just buy from someplace else that they can remove 
+    # the DRM from
+
+    # Amazon should know by now that true book lover's are not like
+    # penniless kids that pirate music, we do not pirate books
+
+    if isNewInstall():
+        mungedmac = GetMACAddressMunged()
+        if len(mungedmac) > 7:
+            return mungedmac
+    sernum = GetVolumeSerialNumber()
+    if len(sernum) > 7:
+        return sernum
+    diskpart = GetUserHomeAppSupKindleDirParitionName()
+    uuidnum = GetDiskPartitionUUID(diskpart)
+    if len(uuidnum) > 7:
+        return uuidnum
+    mungedmac = GetMACAddressMunged()
+    if len(mungedmac) > 7:
+        return mungedmac
+    return '9999999999'
+
+
+# implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used for Kindle for Mac Versions >= 1.6.0
+def CryptUnprotectDataV2(encryptedData):
+    sp = GetUserName() + ':&%:' + GetIDString()
+    passwdData = encode(SHA256(sp),charMap5)
+    # salt generation as per the code
+    salt = 0x0512981d * 2 * 1 * 1
+    salt = str(salt) + GetUserName()
+    salt = encode(salt,charMap5)
+    crp = LibCrypto()
+    iter = 0x800
+    keylen = 0x400
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
+    key = key_iv[0:32]
+    iv = key_iv[32:48]
+    crp.set_decrypt_key(key,iv)
+    cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext, charMap5)
     return cleartext
 
 
 # Locate the .kindle-info files
 def getKindleInfoFiles(kInfoFiles):
+    # first search for current .kindle-info files
     home = os.getenv('HOME')
     cmdline = 'find "' + home + '/Library/Application Support" -name ".kindle-info"'
     cmdline = cmdline.encode(sys.getfilesystemencoding())
@@ -178,23 +420,132 @@ def getKindleInfoFiles(kInfoFiles):
     reslst = out1.split('\n')
     kinfopath = 'NONE'
     found = False
-    cnt = len(reslst)
+    for resline in reslst:
+        if os.path.isfile(resline):
+            kInfoFiles.append(resline)
+            found = True
+    # add any .kinf files 
+    cmdline = 'find "' + home + '/Library/Application Support" -name ".rainier*-kinf"'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p1.communicate()
+    reslst = out1.split('\n')
     for resline in reslst:
         if os.path.isfile(resline):
             kInfoFiles.append(resline)
             found = True
     if not found:
-        print('No .kindle-info files have been found.')
+        print('No kindle-info files have been found.')
     return kInfoFiles
 
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
     DB = {}
+    cnt = 0
     infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
+    hdr = infoReader.read(1)
     data = infoReader.read()
-    items = data.split('[')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
+
+    if data.find('[') != -1 :
+        # older style kindle-info file
+        items = data.split('[')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                cleartext = CryptUnprotectData(encryptedValue)
+                DB[keyname] = cleartext
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file used by K4Mac >= 1.6.0
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+    
+        # get the first item record
+        item = items.pop(0)
+    
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+        keyname = "unknown"
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        # "entropy" not used for K4Mac only K4PC
+        # entropy = SHA1(keyhash)
+    
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+    
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+    
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+    
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+    
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+    
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        noffset = contlen - primes(int(contlen/3))[-1]
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+    
+        # decode using charMap5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        cleartext = CryptUnprotectDataV2(encryptedValue)
+        # Debugging
+        # print keyname
+        # print cleartext
+        # print cleartext.encode('hex')
+        # print
+        DB[keyname] = cleartext
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
     return DB

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/k4pcutils.py

@@ -1,8 +1,10 @@
+#!/usr/bin/env python
 # K4PC Windows specific routines
 
 from __future__ import with_statement
 
 import sys, os
+from struct import pack, unpack, unpack_from
 
 from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
     create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
@@ -10,25 +12,86 @@ from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
 
 import _winreg as winreg
 
-import traceback
-
 MAX_PATH = 255
 
 kernel32 = windll.kernel32
 advapi32 = windll.advapi32
 crypt32 = windll.crypt32
 
+import traceback
 
-# Various character maps used to decrypt books. Probably supposed to act as obfuscation
-charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+
+# simple primes table (<= n) calculator
+def primes(n): 
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
+
+
+# Various character maps used to decrypt kindle info values.
+# Probably supposed to act as obfuscation
 charMap2 = "AaZzB0bYyCc1XxDdW2wEeVv3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_"
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
+charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
 
 class DrmException(Exception):
     pass
-    
 
+# Encode the bytes in data with the characters in map
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+  
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+
+# interface with Windows OS Routines
 class DataBlob(Structure):
     _fields_ = [('cbData', c_uint),
                 ('pbData', c_void_p)]
@@ -59,59 +122,187 @@ def GetVolumeSerialNumber():
     return GetVolumeSerialNumber
 GetVolumeSerialNumber = GetVolumeSerialNumber()
 
+def GetIDString():
+    return GetVolumeSerialNumber()
+
+def getLastError():
+    GetLastError = kernel32.GetLastError
+    GetLastError.argtypes = None
+    GetLastError.restype = c_uint
+    def getLastError():
+        return GetLastError()
+    return getLastError
+getLastError = getLastError()
 
 def GetUserName():
     GetUserNameW = advapi32.GetUserNameW
     GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
     GetUserNameW.restype = c_uint
     def GetUserName():
-        buffer = create_unicode_buffer(32)
+        buffer = create_unicode_buffer(2)
         size = c_uint(len(buffer))
         while not GetUserNameW(buffer, byref(size)):
+            errcd = getLastError()
+            if errcd == 234:
+                # bad wine implementation up through wine 1.3.21
+                return "AlternateUserName"
             buffer = create_unicode_buffer(len(buffer) * 2)
             size.value = len(buffer)
         return buffer.value.encode('utf-16-le')[::2]
     return GetUserName
 GetUserName = GetUserName()
 
-
 def CryptUnprotectData():
     _CryptUnprotectData = crypt32.CryptUnprotectData
     _CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
                                    c_void_p, c_void_p, c_uint, DataBlob_p]
     _CryptUnprotectData.restype = c_uint
-    def CryptUnprotectData(indata, entropy):
+    def CryptUnprotectData(indata, entropy, flags):
         indatab = create_string_buffer(indata)
         indata = DataBlob(len(indata), cast(indatab, c_void_p))
         entropyb = create_string_buffer(entropy)
         entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
         outdata = DataBlob()
         if not _CryptUnprotectData(byref(indata), None, byref(entropy),
-                                   None, None, 0, byref(outdata)):
+                                   None, None, flags, byref(outdata)):
             raise DrmException("Failed to Unprotect Data")
         return string_at(outdata.pbData, outdata.cbData)
     return CryptUnprotectData
 CryptUnprotectData = CryptUnprotectData()
 
-# Locate the .kindle-info files
+
+# Locate all of the kindle-info style files and return as list
 def getKindleInfoFiles(kInfoFiles):
     regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders\\")
     path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
+
+    # first look for older kindle-info files
     kinfopath = path +'\\Amazon\\Kindle For PC\\{AMAwzsaPaaZAzmZzZQzgZCAkZ3AjA_AY}\\kindle.info'
     if not os.path.isfile(kinfopath):
-        print('The kindle.info files has not been found.')
+        print('No kindle.info files have not been found.')
     else:
         kInfoFiles.append(kinfopath)
+
+    # now look for newer (K4PC 1.5.0 and later rainier.2.1.1.kinf file
+
+    kinfopath = path +'\\Amazon\\Kindle For PC\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.5.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
+    # now look for even newer (K4PC 1.6.0 and later) rainier.2.1.1.kinf file
+    kinfopath = path +'\\Amazon\\Kindle\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.6.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
     return kInfoFiles
 
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
+
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
     DB = {}
+    cnt = 0
     infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
+    hdr = infoReader.read(1)
     data = infoReader.read()
-    items = data.split('{')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
+
+    if data.find('{') != -1 :
+
+        # older style kindle-info file
+        items = data.split('{')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                DB[keyname] = CryptUnprotectData(encryptedValue, "", 0)
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+
+        # get the first item record
+        item = items.pop(0)
+
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        entropy = SHA1(keyhash)
+
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+        noffset = contlen - primes(int(contlen/3))[-1]
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+
+        # decode using Map5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        DB[keyname] = CryptUnprotectData(encryptedValue, entropy, 1)
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
     return DB
+
+

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/kgenpids.py

@@ -11,16 +11,28 @@ from struct import pack, unpack, unpack_from
 class DrmException(Exception):
     pass
 
-global kindleDatabase
 global charMap1
-global charMap2
 global charMap3
 global charMap4
 
-if sys.platform.startswith('win'):
-    from k4pcutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
-if sys.platform.startswith('darwin'):
-    from k4mutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre:
+    if sys.platform.startswith('win'):
+        from calibre_plugins.k4mobidedrm.k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from calibre_plugins.k4mobidedrm.k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+else:
+    if sys.platform.startswith('win'):
+        from k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
 
 charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
 charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
@@ -66,50 +78,7 @@ def decode(data,map):
         value = (((high * len(map)) ^ 0x80) & 0xFF) + low
         result += pack("B",value)
     return result
-
-# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForHash(hashedKey):
-    global kindleDatabase
-    global charMap1
-    global charMap2
-    encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
-    if sys.platform.startswith('win'):
-        return CryptUnprotectData(encryptedValue,"")
-    else:
-        cleartext = CryptUnprotectData(encryptedValue)
-        return decode(cleartext, charMap1)
- 
-# Get a record from the Kindle.info file for the string in "key" (plaintext). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForKey(key):
-    global charMap2
-    return getKindleInfoValueForHash(encodeHash(key,charMap2))
-
-# Find if the original string for a hashed/encoded string is known. 
-# If so return the original string othwise return an empty string.
-def findNameForHash(hash):
-    global charMap2
-    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
-    result = ""
-    for name in names:
-        if hash == encodeHash(name, charMap2):
-           result = name
-           break
-    return result
     
-# Print all the records from the kindle.info file (option -i)
-def printKindleInfo():
-    for record in kindleDatabase:
-        name = findNameForHash(record)
-        if name != "" :
-            print (name)
-            print ("--------------------------")
-        else :
-            print ("Unknown Record")
-        print getKindleInfoValueForHash(record)
-        print "\n"
-
 #
 # PID generation routines
 #
@@ -222,15 +191,15 @@ def getKindlePid(pidlst, rec209, token, serialnum):
     return pidlst
 
 
-# Parse the EXTH header records and parse the Kindleinfo
-# file to calculate the book pid.
+# parse the Kindleinfo file to calculate the book pid.
+
+keynames = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
 
 def getK4Pids(pidlst, rec209, token, kInfoFile):
-    global kindleDatabase
     global charMap1
     kindleDatabase = None
     try:
-        kindleDatabase = parseKindleInfo(kInfoFile)
+        kindleDatabase = getDBfromFile(kInfoFile)
     except Exception, message:
         print(message)
         kindleDatabase = None
@@ -241,22 +210,22 @@ def getK4Pids(pidlst, rec209, token, kInfoFile):
         
     try:
         # Get the Mazama Random number
-        MazamaRandomNumber = getKindleInfoValueForKey("MazamaRandomNumber")
+        MazamaRandomNumber = kindleDatabase["MazamaRandomNumber"]
 
         # Get the kindle account token
-        kindleAccountToken = getKindleInfoValueForKey("kindle.account.tokens")
+        kindleAccountToken = kindleDatabase["kindle.account.tokens"]
     except KeyError:
         print "Keys not found in " + kInfoFile
         return pidlst
         
-    # Get the HDD serial
-    encodedSystemVolumeSerialNumber = encodeHash(GetVolumeSerialNumber(),charMap1)
+    # Get the ID string used
+    encodedIDString = encodeHash(GetIDString(),charMap1)
 
     # Get the current user name
     encodedUsername = encodeHash(GetUserName(),charMap1)
 
     # concat, hash and encode to calculate the DSN
-    DSN = encode(SHA1(MazamaRandomNumber+encodedSystemVolumeSerialNumber+encodedUsername),charMap1)
+    DSN = encode(SHA1(MazamaRandomNumber+encodedIDString+encodedUsername),charMap1)
        
     # Compute the device PID (for which I can tell, is used for nothing).
     table =  generatePidEncryptionTable()

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/mobidedrm.py

@@ -49,10 +49,13 @@
 #  0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
 #  0.28 - slight additional changes to metadata token generation (None -> '')
 #  0.29 - It seems that the ideas about when multibyte trailing characters were
-#         included in the encryption were wrong. They aren't for DOC compressed
-#         files, but they are for HUFF/CDIC compress files!
+#         included in the encryption were wrong. They are for DOC compressed
+#         files, but they are not for HUFF/CDIC compress files!
+#  0.30 - Modified interface slightly to work better with new calibre plugin style
+#  0.31 - The multibyte encrytion info is true for version 7 files too.
+#  0.32 - Added support for "Print Replica" Kindle ebooks
 
-__version__ = '0.29'
+__version__ = '0.32'
 
 import sys
 
@@ -161,8 +164,12 @@ class MobiBook:
         return self.data_file[off:endoff]
 
     def __init__(self, infile):
+        print ('MobiDeDrm v%(__version__)s. '
+           'Copyright 2008-2011 The Dark Reverser et al.' % globals())
+
         # initial sanity check on file
         self.data_file = file(infile, 'rb').read()
+        self.mobi_data = ''
         self.header = self.data_file[0:78]
         if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
             raise DrmException("invalid file format")
@@ -190,14 +197,15 @@ class MobiBook:
             self.meta_array = {}
             return
         self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
+        self.mobi_codepage, = struct.unpack('>L',self.sect[0x1c:0x20])
         self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
         print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
         self.extra_data_flags = 0
         if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
             self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
             print "Extra Data Flags = %d" % self.extra_data_flags
-        if (self.mobi_version < 7) and (self.compression != 17480):
-            # multibyte utf8 data is included in the encryption for mobi_version 6 and below
+        if (self.compression != 17480):
+            # multibyte utf8 data is included in the encryption for PalmDoc compression
             # so clear that byte so that we leave it to be decrypted.
             self.extra_data_flags &= 0xFFFE
 
@@ -227,8 +235,13 @@ class MobiBook:
         except:
             self.meta_array = {}
             pass
+        self.print_replica = False
             
     def getBookTitle(self):
+        codec_map = {
+            1252 : 'windows-1252',
+            65001 : 'utf-8',
+        }
         title = ''
         if 503 in self.meta_array:
             title = self.meta_array[503]
@@ -239,7 +252,10 @@ class MobiBook:
         if title == '':
             title = self.header[:32]
             title = title.split("\0")[0]
-        return title
+        codec = 'windows-1252'
+        if self.mobi_codepage in codec_map.keys():
+            codec = codec_map[self.mobi_codepage]
+        return unicode(title, codec).encode('utf-8')
 
     def getPIDMetaInfo(self):
         rec209 = ''
@@ -301,15 +317,29 @@ class MobiBook:
                         break
         return [found_key,pid]
 
+    def getMobiFile(self, outpath):
+        file(outpath,'wb').write(self.mobi_data)
+        
+    def getPrintReplica(self):
+        return self.print_replica
+
     def processBook(self, pidlist):
         crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
         print 'Crypto Type is: ', crypto_type
         self.crypto_type = crypto_type
         if crypto_type == 0:
             print "This book is not encrypted."
-            return self.data_file
+            # we must still check for Print Replica
+            self.print_replica = (self.loadSection(1)[0:4] == '%MOP')
+            self.mobi_data = self.data_file
+            return
         if crypto_type != 2 and crypto_type != 1:
             raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
+        if 406 in self.meta_array:
+            data406 = self.meta_array[406]
+            val406, = struct.unpack('>Q',data406)
+            if val406 != 0:
+                raise DrmException("Cannot decode library or rented ebooks.")
 
         goodpids = []
         for pid in pidlist:
@@ -353,39 +383,44 @@ class MobiBook:
 
         # decrypt sections
         print "Decrypting. Please wait . . .",
-        new_data = self.data_file[:self.sections[1][0]]
+        self.mobi_data = self.data_file[:self.sections[1][0]]
         for i in xrange(1, self.records+1):
             data = self.loadSection(i)
             extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
             if i%100 == 0:
                 print ".",
             # print "record %d, extra_size %d" %(i,extra_size)
-            new_data += PC1(found_key, data[0:len(data) - extra_size])
+            decoded_data = PC1(found_key, data[0:len(data) - extra_size])
+            if i==1:
+                self.print_replica = (decoded_data[0:4] == '%MOP')
+            self.mobi_data += decoded_data
             if extra_size > 0:
-                new_data += data[-extra_size:]
+                self.mobi_data += data[-extra_size:]
         if self.num_sections > self.records+1:
-            new_data += self.data_file[self.sections[self.records+1][0]:]
-        self.data_file = new_data
+            self.mobi_data += self.data_file[self.sections[self.records+1][0]:]
         print "done"
-        return self.data_file
+        return
 
 def getUnencryptedBook(infile,pid):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook([pid])
+    book.processBook([pid])
+    return book.mobi_data
 
 def getUnencryptedBookWithList(infile,pidlist):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook(pidlist)
+    book.processBook(pidlist)
+    return book.mobi_data
+
 
 def main(argv=sys.argv):
     print ('MobiDeDrm v%(__version__)s. '
-	   'Copyright 2008-2010 The Dark Reverser.' % globals())
+        'Copyright 2008-2011 The Dark Reverser et al.' % globals())
     if len(argv)<3 or len(argv)>4:
-        print "Removes protection from Mobipocket books"
+        print "Removes protection from Kindle/Mobipocket and Kindle/Print Replica ebooks"
         print "Usage:"
         print "    %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
         return 1
@@ -393,9 +428,9 @@ def main(argv=sys.argv):
         infile = argv[1]
         outfile = argv[2]
         if len(argv) is 4:
-        	pidlist = argv[3].split(',')
+            pidlist = argv[3].split(',')
         else:
-        	pidlist = {}
+            pidlist = {}
         try:
             stripped_file = getUnencryptedBookWithList(infile, pidlist)
             file(outfile, 'wb').write(stripped_file)

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/stylexml2css.py

@@ -81,6 +81,14 @@ class DocParser(object):
             pos = foundpos + 1
         return startpos
 
+    # returns a vector of integers for the tagpath
+    def getData(self, tagpath, pos, end):
+        argres=[]
+        (foundat, argt) = self.findinDoc(tagpath, pos, end)
+        if (argt != None) and (len(argt) > 0) :
+            argList = argt.split('|')
+            argres = [ int(strval) for strval in argList]
+        return argres
 
     def process(self):
 
@@ -237,7 +245,11 @@ def convert2CSS(flatxml, fontsize, ph, pw):
 
     # create a document parser
     dp = DocParser(flatxml, fontsize, ph, pw)
-
     csspage = dp.process()
-
     return csspage
+
+
+def getpageIDMap(flatxml):
+    dp = DocParser(flatxml, 0, 0, 0)
+    pageidnumbers = dp.getData('info.original.pid', 0, -1)
+    return pageidnumbers

DeDRM_Windows_Application/DeDRM_WinApp/DeDRM_lib/lib/topazextract.py

@@ -10,7 +10,12 @@ class Unbuffered:
         return getattr(self.stream, attr)
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
+
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
 import os, csv, getopt
 import zlib, zipfile, tempfile, shutil
 from struct import pack
@@ -18,10 +23,32 @@ from struct import unpack
 
 class TpzDRMError(Exception):
     pass
+
     
 # local support routines
-import kgenpids
-import genbook
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import kgenpids
+    from calibre_plugins.k4mobidedrm import genbook
+else:
+    import kgenpids
+    import genbook
+
+
+# recursive zip creation support routine
+def zipUpDir(myzip, tdir, localname):
+    currentdir = tdir
+    if localname != "":
+        currentdir = os.path.join(currentdir,localname)
+    list = os.listdir(currentdir)
+    for file in list:
+        afilename = file
+        localfilePath = os.path.join(localname, afilename)
+        realfilePath = os.path.join(currentdir,file)
+        if os.path.isfile(realfilePath):
+            myzip.write(realfilePath, localfilePath)
+        elif os.path.isdir(realfilePath):
+            zipUpDir(myzip, tdir, localfilePath)
+
 #
 # Utility routines
 #
@@ -110,9 +137,10 @@ def decryptDkeyRecords(data,PID):
 
 
 class TopazBook:
-    def __init__(self, filename, outdir):
+    def __init__(self, filename):
         self.fo = file(filename, 'rb')
-        self.outdir = outdir
+        self.outdir = tempfile.mkdtemp()
+        # self.outdir = 'rawdat'
         self.bookPayloadOffset = 0
         self.bookHeaderRecords = {}
         self.bookMetadata = {}
@@ -317,21 +345,34 @@ class TopazBook:
                         file(outputFile, 'wb').write(record)
         print " "
 
+    def getHTMLZip(self, zipname):
+        htmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        htmlzip.write(os.path.join(self.outdir,'book.html'),'book.html')
+        htmlzip.write(os.path.join(self.outdir,'book.opf'),'book.opf')
+        if os.path.isfile(os.path.join(self.outdir,'cover.jpg')):
+            htmlzip.write(os.path.join(self.outdir,'cover.jpg'),'cover.jpg')
+        htmlzip.write(os.path.join(self.outdir,'style.css'),'style.css')
+        zipUpDir(htmlzip, self.outdir, 'img')
+        htmlzip.close()
 
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
+    def getSVGZip(self, zipname):
+        svgzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        svgzip.write(os.path.join(self.outdir,'index_svg.xhtml'),'index_svg.xhtml')
+        zipUpDir(svgzip, self.outdir, 'svg')
+        zipUpDir(svgzip, self.outdir, 'img')
+        svgzip.close()
 
+    def getXMLZip(self, zipname):
+        xmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        targetdir = os.path.join(self.outdir,'xml')
+        zipUpDir(xmlzip, targetdir, '')
+        zipUpDir(xmlzip, self.outdir, 'img')
+        xmlzip.close()
+
+    def cleanup(self):
+        if os.path.isdir(self.outdir):
+            pass
+            # shutil.rmtree(self.outdir, True)
 
 def usage(progname):
     print "Removes DRM protection from Topaz ebooks and extract the contents"
@@ -383,58 +424,46 @@ def main(argv=sys.argv):
         return 1
 
     bookname = os.path.splitext(os.path.basename(infile))[0]
-    tempdir = tempfile.mkdtemp()
 
-    tb = TopazBook(infile, tempdir)
+    tb = TopazBook(infile)
     title = tb.getBookTitle()
     print "Processing Book: ", title
     keysRecord, keysRecordRecord = tb.getPIDMetaInfo()
     pidlst = kgenpids.getPidList(keysRecord, keysRecordRecord, k4, pids, serials, kInfoFiles) 
 
     try:
+        print "Decrypting Book"
         tb.processBook(pidlst)
+
+        print "   Creating HTML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_nodrm' + '.htmlz')
+        tb.getHTMLZip(zipname)
+
+        print "   Creating SVG ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
+        tb.getSVGZip(zipname)
+
+        print "   Creating XML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
+        tb.getXMLZip(zipname)
+
+        # removing internal temporary directory of pieces
+        tb.cleanup()
+
     except TpzDRMError, e:
         print str(e)
-        print "   Creating DeBug Full Zip Archive of Book"
-        zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-        myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-        zipUpDir(myzip, tempdir, '')
-        myzip.close()
-        shutil.rmtree(tempdir, True)
+        # tb.cleanup()
         return 1
 
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
-
-    print "   Creating SVG ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
-
-    print "   Creating XML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
-
-    shutil.rmtree(tempdir, True)
+    except Exception, e:
+        print str(e)
+        # tb.cleanup
+        return 1
 
     return 0
                 
 
 if __name__ == '__main__':
+    sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 

KindleBooks/KindleBooks.pyw

@@ -109,7 +109,7 @@ class MainDialog(Tkinter.Frame):
     # post output from subprocess in scrolled text widget
     def showCmdOutput(self, msg):
         if msg and msg !='':
-            msg = msg.encode('utf-8')
+            # msg = msg.encode('utf-8')
             if sys.platform.startswith('win'):
                 msg = msg.replace('\r\n','\n')
             self.stext.insert(Tkconstants.END,msg)
@@ -149,7 +149,7 @@ class MainDialog(Tkinter.Frame):
         mobipath = tkFileDialog.askopenfilename(
             initialdir = cpath,
             parent=None, title='Select Kindle/Mobi/Topaz  eBook File',
-            defaultextension='.prc', filetypes=[('Mobi eBook File', '.prc'), ('Mobi eBook File', '.azw'),('Mobi eBook File', '.mobi'),('Mobi eBook File', '.tpz'),('Mobi eBook File', '.azw1'),('All Files', '.*')])
+            defaultextension='.prc', filetypes=[('Mobi eBook File', '.prc'), ('Mobi eBook File', '.azw'),('Mobi eBook File', '.mobi'),('Mobi eBook File', '.tpz'),('Mobi eBook File', '.azw1'),('Mobi azw4 eBook File', '.azw4'),('All Files', '.*')])
         if mobipath:
             mobipath = os.path.normpath(mobipath)
             self.mobipath.delete(0, Tkconstants.END)

KindleBooks/lib/convert2xml.py

@@ -20,6 +20,8 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # Get a 7 bit encoded number from string. The most 
 # significant byte comes first and has the high bit (8th) set
@@ -138,7 +140,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside of string table limits')
+            # sys.exit(-1)
 
     def getSize(self):
         return self.size
@@ -258,6 +261,11 @@ class PageParser(object):
         'paragraph.class'     : (1, 'scalar_text', 0, 0),
         'paragraph.firstWord' : (1, 'scalar_number', 0, 0),
         'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.lastWord'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridSize'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'paragraph.gridTopCenter' : (1, 'scalar_number', 0, 0),
+
 
         'word_semantic'           : (1, 'snippets', 1, 1),
         'word_semantic.type'      : (1, 'scalar_text', 0, 0),
@@ -272,11 +280,17 @@ class PageParser(object):
 
         '_span'           : (1, 'snippets', 1, 0),
         '_span.firstWord' : (1, 'scalar_number', 0, 0),
-        '-span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.lastWord'  : (1, 'scalar_number', 0, 0),
+        '_span.gridSize'  : (1, 'scalar_number', 0, 0),
+        '_span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        '_span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'span'           : (1, 'snippets', 1, 0),
         'span.firstWord' : (1, 'scalar_number', 0, 0),
         'span.lastWord'  : (1, 'scalar_number', 0, 0),
+        'span.gridSize'  : (1, 'scalar_number', 0, 0),
+        'span.gridBottomCenter'  : (1, 'scalar_number', 0, 0),
+        'span.gridTopCenter' : (1, 'scalar_number', 0, 0),
 
         'extratokens'            : (1, 'snippets', 1, 0),
         'extratokens.type'       : (1, 'scalar_text', 0, 0),

KindleBooks/lib/flatxml2html.py

@@ -271,6 +271,9 @@ class DocParser(object):
 
         pclass = self.getClass(pclass)
 
+        # if paragraph uses extratokens (extra glyphs) then make it fixed
+        (pos, extraglyphs) = self.findinDoc('paragraph.extratokens',start,end)
+
         # build up a description of the paragraph in result and return it
         # first check for the  basic - all words paragraph
         (pos, sfirst) = self.findinDoc('paragraph.firstWord',start,end)
@@ -280,6 +283,7 @@ class DocParser(object):
             last = int(slast)
             
             makeImage = (regtype == 'vertical') or (regtype == 'table')
+            makeImage = makeImage or (extraglyphs != None) 
             if self.fixedimage:
                 makeImage = makeImage or (regtype == 'fixed')
 
@@ -353,6 +357,8 @@ class DocParser(object):
 
         word_class = ''
 
+        word_semantic_type = ''
+
         while (line < end) :
 
             (name, argres) = self.lineinDoc(line)
@@ -512,6 +518,72 @@ class DocParser(object):
         return parares
 
 
+    def buildTOCEntry(self, pdesc) :
+        parares = ''
+        sep =''
+        tocentry = ''
+        handle_links = len(self.link_id) > 0
+
+        lstart = 0
+
+        cnt = len(pdesc)
+        for j in xrange( 0, cnt) :
+
+            (wtype, num) = pdesc[j]
+
+            if wtype == 'ocr' :
+                word = self.ocrtext[num]
+                sep = ' '
+
+                if handle_links:
+                    link = self.link_id[num]
+                    if (link > 0):
+                        linktype = self.link_type[link-1]
+                        title = self.link_title[link-1]
+                        title = title.rstrip('. ')
+                        alt_title = parares[lstart:]
+                        alt_title = alt_title.strip()
+                        # now strip off the actual printed page number
+                        alt_title = alt_title.rstrip('01234567890ivxldIVXLD-.')
+                        alt_title = alt_title.rstrip('. ')
+                        # skip over any external links - can't have them in a books toc
+                        if linktype == 'external' :
+                            title = ''
+                            alt_title = ''
+                            linkpage = ''
+                        else : 
+                            if len(self.link_page) >= link :
+                                ptarget = self.link_page[link-1] - 1
+                                linkpage = '%04d' % ptarget
+                            else :
+                                # just link to the current page
+                                linkpage = self.id[4:]
+                        if len(alt_title) >= len(title):
+                            title = alt_title
+                        if title != '' and linkpage != '':
+                            tocentry += title + '|' + linkpage + '\n'
+                        lstart = len(parares)
+                        if word == '_link_' : word = ''
+                    elif (link < 0) :
+                        if word == '_link_' : word = ''
+
+                if word == '_lb_':
+                    word = ''
+                    sep = ''
+
+                if num in self.dehyphen_rootid :
+                    word = word[0:-1]
+                    sep = ''
+
+                parares += word + sep
+
+            else :
+                continue
+
+        return tocentry
+
+
+
     
     # walk the document tree collecting the information needed
     # to build an html page using the ocrText
@@ -519,6 +591,7 @@ class DocParser(object):
     def process(self):
 
         htmlpage = ''
+        tocinfo = ''
 
         # get the ocr text
         (pos, argres) = self.findinDoc('info.word.ocrText',0,-1)
@@ -644,9 +717,9 @@ class DocParser(object):
                         ptype = 'end'
                         first_para_continued = False
                     (pclass, pdesc) = self.getParaDescription(start,end, regtype)
+                    tocinfo += self.buildTOCEntry(pdesc)
                     htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
 
-
                 elif (regtype == 'vertical') or (regtype == 'table') :
                     ptype = 'full'
                     if inGroup:
@@ -704,12 +777,11 @@ class DocParser(object):
                 htmlpage = htmlpage[0:-4]
             last_para_continued = False
 
-        return htmlpage
-
+        return htmlpage, tocinfo
 
 
 def convert2HTML(flatxml, classlst, fileid, bookDir, gdict, fixedimage):
     # create a document parser
     dp = DocParser(flatxml, classlst, fileid, bookDir, gdict, fixedimage)
-    htmlpage = dp.process()
-    return htmlpage
+    htmlpage, tocinfo = dp.process()
+    return htmlpage, tocinfo

KindleBooks/lib/flatxml2svg.py

@@ -10,17 +10,94 @@ from struct import unpack
 
 
 class PParser(object):
-    def __init__(self, gd, flatxml):
+    def __init__(self, gd, flatxml, meta_array):
         self.gd = gd
         self.flatdoc = flatxml.split('\n')
+        self.docSize = len(self.flatdoc)
         self.temp = []
-        foo = self.getData('page.h') or self.getData('book.h')
-        self.ph = foo[0]
-        foo = self.getData('page.w') or self.getData('book.w')
-        self.pw = foo[0]
-        self.gx = self.getData('info.glyph.x')
-        self.gy = self.getData('info.glyph.y')
-        self.gid = self.getData('info.glyph.glyphID')
+        
+        self.ph = -1
+        self.pw = -1
+        startpos = self.posinDoc('page.h') or self.posinDoc('book.h')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.ph = max(self.ph, int(argres))
+        startpos = self.posinDoc('page.w') or self.posinDoc('book.w')
+        for p in startpos:
+            (name, argres) = self.lineinDoc(p)
+            self.pw = max(self.pw, int(argres))
+        
+        if self.ph <= 0:
+            self.ph = int(meta_array.get('pageHeight', '11000'))
+        if self.pw <= 0:
+            self.pw = int(meta_array.get('pageWidth', '8500'))
+
+        res = []
+        startpos = self.posinDoc('info.glyph.x')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.x', p)
+            res.extend(argres)
+        self.gx = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.y')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.y', p)
+            res.extend(argres)
+        self.gy = res
+
+        res = []
+        startpos = self.posinDoc('info.glyph.glyphID')
+        for p in startpos:
+            argres = self.getDataatPos('info.glyph.glyphID', p)
+            res.extend(argres)
+        self.gid = res
+
+
+    # return tag at line pos in document
+    def lineinDoc(self, pos) :
+        if (pos >= 0) and (pos < self.docSize) :
+            item = self.flatdoc[pos]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+        return name, argres
+
+    # find tag in doc if within pos to end inclusive
+    def findinDoc(self, tagpath, pos, end) :
+        result = None
+        if end == -1 :
+            end = self.docSize
+        else:
+            end = min(self.docSize, end)
+        foundat = -1
+        for j in xrange(pos, end):
+            item = self.flatdoc[j]
+            if item.find('=') >= 0:
+                (name, argres) = item.split('=',1)
+            else :
+                name = item
+                argres = ''
+            if name.endswith(tagpath) :
+                result = argres
+                foundat = j
+                break
+        return foundat, result
+
+    # return list of start positions for the tagpath
+    def posinDoc(self, tagpath):
+        startpos = []
+        pos = 0
+        res = ""
+        while res != None :
+            (foundpos, res) = self.findinDoc(tagpath, pos, -1)
+            if res != None :
+                startpos.append(foundpos)
+            pos = foundpos + 1
+        return startpos
+
     def getData(self, path):
         result = None
         cnt = len(self.flatdoc)
@@ -39,6 +116,23 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
+    def getDataatPos(self, path, pos):
+        result = None
+        item = self.flatdoc[pos]
+        if item.find('=') >= 0:
+            (name, argt) = item.split('=')
+            argres = argt.split('|')
+        else:
+            name = item
+            argres = []
+        if (len(argres) > 0) :
+            for j in xrange(0,len(argres)):
+                argres[j] = int(argres[j])
+        if (name.endswith(path)):
+            result = argres
+        return result
+
     def getDataTemp(self, path):
         result = None
         cnt = len(self.temp)
@@ -58,6 +152,7 @@ class PParser(object):
             for j in xrange(0,len(argres)):
                 argres[j] = int(argres[j])
         return result
+
     def getImages(self):
         result = []
         self.temp = self.flatdoc
@@ -69,6 +164,7 @@ class PParser(object):
             src = self.getDataTemp('img.src')[0]
             result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
         return result
+
     def getGlyphs(self):
         result = []
         if (self.gid != None) and (len(self.gid) > 0):
@@ -84,25 +180,25 @@ class PParser(object):
         return result
 
 
-def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi):
+def convert2SVG(gdict, flat_xml, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi):
     ml = ''
-    pp = PParser(gdict, flat_xml)
+    pp = PParser(gdict, flat_xml, meta_array)
     ml += '<?xml version="1.0" standalone="no"?>\n'
     if (raw):
         ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
         ml += '<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1)
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
     else:
         ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
         ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
-        ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
+        ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
         ml += '<script><![CDATA[\n'
         ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
         ml += 'var dpi=%d;\n' % scaledpi
-        if (counter) :
-            ml += 'var prevpage="page%04d.xhtml";\n' % (counter - 1)
-        if (counter < numfiles-1) :
-            ml += 'var nextpage="page%04d.xhtml";\n' % (counter + 1)
+        if (previd) :
+            ml += 'var prevpage="page%04d.xhtml";\n' % (previd)
+        if (nextid) :
+            ml += 'var nextpage="page%04d.xhtml";\n' % (nextid)
         ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
         ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
         ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
@@ -115,10 +211,11 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         ml += '</head>\n'
         ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
         ml += '<div style="white-space:nowrap;">\n'
-        if (counter == 0) :
+        if previd == None:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else:
             ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n'
+        
         ml += '<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph)
     if (pp.gid != None): 
         ml += '<defs>\n'
@@ -134,12 +231,14 @@ def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, sca
         for j in xrange(0,len(pp.gid)):
             ml += '<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j])
     if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
-        ml += '<text x="10" y="10" font-family="Helvetica" font-size="100" stroke="black">This page intentionally left blank.</text>\n<text x="10" y="110" font-family="Helvetica" font-size="50" stroke="black">Until this notice unintentionally gave it content.  (gensvg.py)</text>\n'
+        xpos = "%d" % (pp.pw // 3)
+        ypos = "%d" % (pp.ph // 3)
+        ml += '<text x="' + xpos + '" y="' + ypos + '" font-size="' + meta_array['fontSize'] + '" font-family="Helvetica" stroke="black">This page intentionally left blank.</text>\n'
     if (raw) :
         ml += '</svg>'
     else :
         ml += '</svg></a>\n'
-        if (counter == numfiles - 1) :
+        if nextid == None:
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
         else :
             ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n'

KindleBooks/lib/genbook.py

@@ -19,12 +19,25 @@ import getopt
 from struct import pack
 from struct import unpack
 
+class TpzDRMError(Exception):
+    pass
 
 # local support routines
-import convert2xml
-import flatxml2html
-import flatxml2svg
-import stylexml2css
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre :
+    from calibre_plugins.k4mobidedrm import convert2xml
+    from calibre_plugins.k4mobidedrm import flatxml2html
+    from calibre_plugins.k4mobidedrm import flatxml2svg
+    from calibre_plugins.k4mobidedrm import stylexml2css
+else :
+    import convert2xml
+    import flatxml2html
+    import flatxml2svg
+    import stylexml2css
 
 
 # Get a 7 bit encoded number from a file
@@ -103,7 +116,8 @@ class Dictionary(object):
             return self.stable[self.pos]
         else:
             print "Error - %d outside of string table limits" % val
-            sys.exit(-1)
+            raise TpzDRMError('outside or string table limits')
+            # sys.exit(-1)
     def getSize(self):
         return self.size
     def getPos(self):
@@ -360,10 +374,34 @@ def generateBook(bookDir, raw, fixedimage):
     (ph, pw) = getPageDim(flat_xml)
     if (ph == '-1') or (ph == '0') : ph = '11000'
     if (pw == '-1') or (pw == '0') : pw = '8500'
+    meta_array['pageHeight'] = ph
+    meta_array['pageWidth'] = pw
+    if 'fontSize' not in meta_array.keys():
+        meta_array['fontSize'] = fontsize
 
-    # print '     ', 'other0000.dat'
+    # process other.dat for css info and for map of page files to svg images
+    # this map is needed because some pages actually are made up of multiple
+    # pageXXXX.xml files
     xname = os.path.join(bookDir, 'style.css')
     flat_xml = convert2xml.fromData(dict, otherFile)
+
+    # extract info.original.pid to get original page information
+    pageIDMap = {}
+    pageidnums = stylexml2css.getpageIDMap(flat_xml)
+    if len(pageidnums) == 0:
+        filenames = os.listdir(pageDir)
+        numfiles = len(filenames)
+        for k in range(numfiles):
+            pageidnums.append(k)
+    # create a map from page ids to list of page file nums to process for that page
+    for i in range(len(pageidnums)):
+        id = pageidnums[i]
+        if id in pageIDMap.keys():
+            pageIDMap[id].append(i)
+        else:
+            pageIDMap[id] = [i]
+
+    # now get the css info
     cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
     file(xname, 'wb').write(cssstr)
     xname = os.path.join(xmlDir, 'other0000.xml')
@@ -403,6 +441,9 @@ def generateBook(bookDir, raw, fixedimage):
     glyfile.close()
     print " "
 
+    # build up tocentries while processing html
+    tocentries = ''
+
     # start up the html
     htmlFileName = "book.html"
     htmlstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -425,6 +466,77 @@ def generateBook(bookDir, raw, fixedimage):
     # readability when rendering to the screen.  
     scaledpi = 1440.0
 
+    filenames = os.listdir(pageDir)
+    filenames = sorted(filenames)
+    numfiles = len(filenames)
+
+    xmllst = []
+
+    for filename in filenames:
+        # print '     ', filename
+        print ".",
+        fname = os.path.join(pageDir,filename)
+        flat_xml = convert2xml.fromData(dict, fname)
+
+        # keep flat_xml for later svg processing
+        xmllst.append(flat_xml)
+
+        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
+        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
+
+        # first get the html
+        pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
+        tocentries += tocinfo 
+        htmlstr += pagehtml
+
+    # finish up the html string and output it
+    htmlstr += '</body>\n</html>\n'
+    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
+    
+    print " "
+    print 'Extracting Table of Contents from Amazon OCR'
+
+    # first create a table of contents file for the svg images
+    tochtml = '<?xml version="1.0" encoding="utf-8"?>\n'
+    tochtml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
+    tochtml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
+    tochtml += '<head>\n'
+    tochtml += '<title>' + meta_array['Title'] + '</title>\n'
+    tochtml += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
+    tochtml += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
+    if 'ASIN' in meta_array:
+        tochtml += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
+    if 'GUID' in meta_array:
+        tochtml += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
+    tochtml += '</head>\n'
+    tochtml += '<body>\n'
+
+    tochtml += '<h2>Table of Contents</h2>\n'
+    start = pageidnums[0]
+    if (raw):
+        startname = 'page%04d.svg' % start
+    else:
+        startname = 'page%04d.xhtml' % start
+
+    tochtml += '<h3><a href="' + startname + '">Start of Book</a></h3>\n'
+    # build up a table of contents for the svg xhtml output
+    toclst = tocentries.split('\n')
+    toclst.pop()
+    for entry in toclst:
+        print entry
+        title, pagenum = entry.split('|')
+        id = pageidnums[int(pagenum)]
+        if (raw):
+            fname = 'page%04d.svg' % id
+        else:
+            fname = 'page%04d.xhtml' % id
+        tochtml += '<h3><a href="'+ fname + '">' + title + '</a></h3>\n'
+    tochtml += '</body>\n'
+    tochtml += '</html>\n'
+    file(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
+
+
+    # now create index_svg.xhtml that points to all required files
     svgindex = '<?xml version="1.0" encoding="utf-8"?>\n'
     svgindex += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
     svgindex += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
@@ -439,50 +551,42 @@ def generateBook(bookDir, raw, fixedimage):
     svgindex += '</head>\n'
     svgindex += '<body>\n'
 
-    filenames = os.listdir(pageDir)
-    filenames = sorted(filenames)
-    numfiles = len(filenames)
-    counter = 0
-
-    for filename in filenames:
-        # print '     ', filename
-        print ".",
-
-        fname = os.path.join(pageDir,filename)
-        flat_xml = convert2xml.fromData(dict, fname)
-
-        xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
-        file(xname, 'wb').write(convert2xml.getXML(dict, fname))
-
-        # first get the html
-        htmlstr += flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
-
-        # now get the svg image of the page
-        svgxml = flatxml2svg.convert2SVG(gd, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi)
-
+    print "Building svg images of each book page"
+    svgindex += '<h2>List of Pages</h2>\n'
+    svgindex += '<div>\n'
+    idlst = sorted(pageIDMap.keys())
+    numids = len(idlst)
+    cnt = len(idlst)
+    previd = None
+    for j in range(cnt):
+        pageid = idlst[j]
+        if j < cnt - 1:
+            nextid = idlst[j+1]
+        else:
+            nextid = None
+        print '.',
+        pagelst = pageIDMap[pageid]
+        flat_svg = ''
+        for page in pagelst:
+            flat_svg += xmllst[page]
+        svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
         if (raw) :
-            pfile = open(os.path.join(svgDir,filename.replace('.dat','.svg')), 'w')
-            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (counter, counter)
+            pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
+            svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid)
         else :
-            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % counter), 'w')
-            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (counter, counter)
-
-
+            pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
+            svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid)
+        previd = pageid
         pfile.write(svgxml)
         pfile.close()
-
         counter += 1
-
-    print " "
-
-    # finish up the html string and output it
-    htmlstr += '</body>\n</html>\n'
-    file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
-
-    # finish up the svg index string and output it
+    svgindex += '</div>\n'
+    svgindex += '<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n'
     svgindex += '</body>\n</html>\n'
     file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
 
+    print " "
+
     # build the opf file
     opfname = os.path.join(bookDir, 'book.opf')
     opfstr = '<?xml version="1.0" encoding="utf-8"?>\n'
@@ -504,7 +608,7 @@ def generateBook(bookDir, raw, fixedimage):
     opfstr += '   </metadata>\n'
     opfstr += '<manifest>\n'
     opfstr += '   <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n'
-    opfstr += '   <item id="stylesheet" href="style.css" media-type="text.css"/>\n'
+    opfstr += '   <item id="stylesheet" href="style.css" media-type="text/css"/>\n'
     # adding image files to manifest
     filenames = os.listdir(imgDir)
     filenames = sorted(filenames)
@@ -562,7 +666,7 @@ def main(argv):
         return 1 
 
     raw = 0
-    fixedimage = False
+    fixedimage = True
     for o, a in opts:
         if o =="-h":
             usage()

KindleBooks/lib/k4mobidedrm.py

@@ -0,0 +1,208 @@
+#!/usr/bin/env python
+
+from __future__ import with_statement
+
+# engine to remove drm from Kindle for Mac and Kindle for PC books
+# for personal use for archiving and converting your ebooks
+
+# PLEASE DO NOT PIRATE EBOOKS! 
+
+# We want all authors and publishers, and eBook stores to live
+# long and prosperous lives but at the same time  we just want to 
+# be able to read OUR books on whatever device we want and to keep 
+# readable for a long, long time
+
+#  This borrows very heavily from works by CMBDTC, IHeartCabbages, skindle, 
+#    unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates 
+#    and many many others
+
+
+__version__ = '3.9'
+
+class Unbuffered:
+    def __init__(self, stream):
+        self.stream = stream
+    def write(self, data):
+        self.stream.write(data)
+        self.stream.flush()
+    def __getattr__(self, attr):
+        return getattr(self.stream, attr)
+
+import sys
+import os, csv, getopt
+import string
+import re
+import traceback
+
+class DrmException(Exception):
+    pass
+
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import mobidedrm
+    from calibre_plugins.k4mobidedrm import topazextract
+    from calibre_plugins.k4mobidedrm import kgenpids
+else:
+    import mobidedrm
+    import topazextract
+    import kgenpids
+        
+
+# cleanup bytestring filenames
+# borrowed from calibre from calibre/src/calibre/__init__.py
+# added in removal of non-printing chars
+# and removal of . at start
+# convert spaces to underscores
+def cleanup_name(name):
+    _filename_sanitize = re.compile(r'[\xae\0\\|\?\*<":>\+/]')
+    substitute='_'
+    one = ''.join(char for char in name if char in string.printable)
+    one = _filename_sanitize.sub(substitute, one)
+    one = re.sub(r'\s', ' ', one).strip()
+    one = re.sub(r'^\.+$', '_', one)
+    one = one.replace('..', substitute)
+    # Windows doesn't like path components that end with a period
+    if one.endswith('.'):
+        one = one[:-1]+substitute
+    # Mac and Unix don't like file names that begin with a full stop
+    if len(one) > 0 and one[0] == '.':
+        one = substitute+one[1:]
+    one = one.replace(' ','_')
+    return one
+
+def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
+    # handle the obvious cases at the beginning
+    if not os.path.isfile(infile):
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: Input file does not exist"
+        return 1
+
+    mobi = True
+    magic3 = file(infile,'rb').read(3)
+    if magic3 == 'TPZ':
+        mobi = False
+
+    bookname = os.path.splitext(os.path.basename(infile))[0]
+
+    if mobi:
+        mb = mobidedrm.MobiBook(infile)
+    else:
+        mb = topazextract.TopazBook(infile)
+
+    title = mb.getBookTitle()
+    print "Processing Book: ", title
+    filenametitle = cleanup_name(title)
+    outfilename = bookname
+    if len(outfilename)<=8 or len(filenametitle)<=8:
+        outfilename = outfilename + "_" + filenametitle
+    elif outfilename[:8] != filenametitle[:8]:
+        outfilename = outfilename[:8] + "_" + filenametitle
+        
+    # avoid excessively long file names
+    if len(outfilename)>150:
+        outfilename = outfilename[:150]
+
+    # build pid list
+    md1, md2 = mb.getPIDMetaInfo()
+    pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
+
+    try:
+        mb.processBook(pidlst)
+
+    except mobidedrm.DrmException, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+    except topazextract.TpzDRMError, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+    except Exception, e:
+        print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
+        return 1
+
+    if mobi:
+        if mb.getPrintReplica():
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.azw4')
+        else:
+            outfile = os.path.join(outdir, outfilename + '_nodrm' + '.mobi')
+        mb.getMobiFile(outfile)
+        return 0            
+
+    # topaz: 
+    print "   Creating NoDRM HTMLZ Archive"
+    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.htmlz')
+    mb.getHTMLZip(zipname)
+
+    print "   Creating SVG ZIP Archive"
+    zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
+    mb.getSVGZip(zipname)
+
+    print "   Creating XML ZIP Archive"
+    zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
+    mb.getXMLZip(zipname)
+
+    # remove internal temporary directory of Topaz pieces
+    mb.cleanup()
+
+    return 0
+
+
+def usage(progname):
+    print "Removes DRM protection from K4PC/M, Kindle, Mobi and Topaz ebooks"
+    print "Usage:"
+    print "    %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir>  " % progname
+
+#
+# Main
+#   
+def main(argv=sys.argv):
+    progname = os.path.basename(argv[0])
+
+    k4 = False
+    kInfoFiles = []
+    serials = []
+    pids = []
+    
+    print ('K4MobiDeDrm v%(__version__)s '
+	   'provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc .' % globals())
+
+    try:
+        opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
+    except getopt.GetoptError, err:
+        print str(err)
+        usage(progname)
+        sys.exit(2)
+    if len(args)<2:
+        usage(progname)
+        sys.exit(2)
+        
+    for o, a in opts:
+        if o == "-k":
+            if a == None :
+                raise DrmException("Invalid parameter for -k")
+            kInfoFiles.append(a)
+        if o == "-p":
+            if a == None :
+                raise DrmException("Invalid parameter for -p")
+            pids = a.split(',')
+        if o == "-s":
+            if a == None :
+                raise DrmException("Invalid parameter for -s")
+            serials = a.split(',')
+
+    # try with built in Kindle Info files
+    k4 = True
+    if sys.platform.startswith('linux'):
+	k4 = False
+	kInfoFiles = None
+    infile = args[0]
+    outdir = args[1]
+    return decryptBook(infile, outdir, k4, kInfoFiles, serials, pids)
+
+
+if __name__ == '__main__':
+    sys.stdout=Unbuffered(sys.stdout)
+    sys.exit(main())
+

KindleBooks/lib/k4mutils.py

@@ -0,0 +1,551 @@
+# standlone set of Mac OSX specific routines needed for KindleBooks
+
+from __future__ import with_statement
+
+import sys
+import os
+import os.path
+
+import subprocess
+from struct import pack, unpack, unpack_from
+
+class DrmException(Exception):
+    pass
+
+
+# interface to needed routines in openssl's libcrypto
+def _load_crypto_libcrypto():
+    from ctypes import CDLL, byref, POINTER, c_void_p, c_char_p, c_int, c_long, \
+        Structure, c_ulong, create_string_buffer, addressof, string_at, cast
+    from ctypes.util import find_library
+
+    libcrypto = find_library('crypto')
+    if libcrypto is None:
+        raise DrmException('libcrypto not found')
+    libcrypto = CDLL(libcrypto)
+
+    AES_MAXNR = 14
+    c_char_pp = POINTER(c_char_p)
+    c_int_p = POINTER(c_int)
+
+    class AES_KEY(Structure):
+        _fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))), ('rounds', c_int)]
+    AES_KEY_p = POINTER(AES_KEY)
+    
+    def F(restype, name, argtypes):
+        func = getattr(libcrypto, name)
+        func.restype = restype
+        func.argtypes = argtypes
+        return func
+    
+    AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,c_int])
+
+    AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',[c_char_p, c_int, AES_KEY_p])
+
+    PKCS5_PBKDF2_HMAC_SHA1 = F(c_int, 'PKCS5_PBKDF2_HMAC_SHA1', 
+                                [c_char_p, c_ulong, c_char_p, c_ulong, c_ulong, c_ulong, c_char_p])
+    
+    class LibCrypto(object):
+        def __init__(self):
+            self._blocksize = 0
+            self._keyctx = None
+            self.iv = 0
+
+        def set_decrypt_key(self, userkey, iv):
+            self._blocksize = len(userkey)
+            if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
+                raise DrmException('AES improper key used')
+                return
+            keyctx = self._keyctx = AES_KEY()
+            self.iv = iv
+            rv = AES_set_decrypt_key(userkey, len(userkey) * 8, keyctx)
+            if rv < 0:
+                raise DrmException('Failed to initialize AES key')
+
+        def decrypt(self, data):
+            out = create_string_buffer(len(data))
+            rv = AES_cbc_encrypt(data, out, len(data), self._keyctx, self.iv, 0)
+            if rv == 0:
+                raise DrmException('AES decryption failed')
+            return out.raw
+
+        def keyivgen(self, passwd, salt, iter, keylen):
+            saltlen = len(salt)
+            passlen = len(passwd)
+            out = create_string_buffer(keylen)
+            rv = PKCS5_PBKDF2_HMAC_SHA1(passwd, passlen, salt, saltlen, iter, keylen, out)
+            return out.raw
+    return LibCrypto
+
+def _load_crypto():
+    LibCrypto = None
+    try:
+        LibCrypto = _load_crypto_libcrypto()
+    except (ImportError, DrmException):
+        pass
+    return LibCrypto
+
+LibCrypto = _load_crypto()
+
+#
+# Utility Routines
+#
+
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA256(message):
+    ctx = hashlib.sha256()
+    ctx.update(message)
+    return ctx.digest()
+
+# Various character maps used to decrypt books. Probably supposed to act as obfuscation
+charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
+charMap2 = "ZB0bYyc1xDdW2wEV3Ff7KkPpL8UuGA4gz-Tme9Nn_tHh5SvXCsIiR6rJjQaqlOoM" 
+
+# For kinf approach of K4PC/K4Mac
+# On K4PC charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
+# For Mac they seem to re-use charMap2 here
+charMap5 = charMap2
+
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+# For .kinf approach of K4PC and now K4Mac
+# generate table of prime number less than or equal to int n
+def primes(n):
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
+
+
+# uses a sub process to get the Hard Drive Serial Number using ioreg
+# returns with the serial number of drive whose BSD Name is "disk0"
+def GetVolumeSerialNumber():
+    sernum = os.getenv('MYSERIALNUMBER')
+    if sernum != None:
+        return sernum
+    cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    bsdname = None
+    sernum = None
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        pp = resline.find('"Serial Number" = "')
+        if pp >= 0:
+            sernum = resline[pp+19:-1]
+            sernum = sernum.strip()
+        bb = resline.find('"BSD Name" = "')
+        if bb >= 0:
+            bsdname = resline[bb+14:-1]
+            bsdname = bsdname.strip()
+            if (bsdname == 'disk0') and (sernum != None):
+                foundIt = True
+                break
+    if not foundIt:
+        sernum = ''
+    return sernum
+
+def GetUserHomeAppSupKindleDirParitionName():
+    home = os.getenv('HOME')
+    dpath =  home + '/Library/Application Support/Kindle'
+    cmdline = '/sbin/mount'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    disk = ''
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.startswith('/dev'):
+            (devpart, mpath) = resline.split(' on ')
+            dpart = devpart[5:]
+            pp = mpath.find('(')
+            if pp >= 0:
+                mpath = mpath[:pp-1]
+            if dpath.startswith(mpath):
+                disk = dpart
+    return disk
+
+# uses a sub process to get the UUID of the specified disk partition using ioreg
+def GetDiskPartitionUUID(diskpart):
+    uuidnum = os.getenv('MYUUIDNUMBER')
+    if uuidnum != None:
+        return uuidnum
+    cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    bsdname = None
+    uuidnum = None
+    foundIt = False
+    nest = 0
+    uuidnest = -1
+    partnest = -2
+    for j in xrange(cnt):
+        resline = reslst[j]
+        if resline.find('{') >= 0:
+            nest += 1
+        if resline.find('}') >= 0:
+            nest -= 1
+        pp = resline.find('"UUID" = "')
+        if pp >= 0:
+            uuidnum = resline[pp+10:-1]
+            uuidnum = uuidnum.strip()
+            uuidnest = nest
+            if partnest == uuidnest and uuidnest > 0:
+                foundIt = True
+                break
+        bb = resline.find('"BSD Name" = "')
+        if bb >= 0:
+            bsdname = resline[bb+14:-1]
+            bsdname = bsdname.strip()
+            if (bsdname == diskpart):
+                partnest = nest
+            else :
+                partnest = -2
+            if partnest == uuidnest and partnest > 0:
+                foundIt = True
+                break
+        if nest == 0:
+            partnest = -2
+            uuidnest = -1
+            uuidnum = None
+            bsdname = None
+    if not foundIt:
+        uuidnum = ''
+    return uuidnum
+    
+def GetMACAddressMunged():
+    macnum = os.getenv('MYMACNUM')
+    if macnum != None:
+        return macnum
+    cmdline = '/sbin/ifconfig en0'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p.communicate()
+    reslst = out1.split('\n')
+    cnt = len(reslst)
+    macnum = None
+    foundIt = False
+    for j in xrange(cnt):
+        resline = reslst[j]
+        pp = resline.find('ether ')
+        if pp >= 0:
+            macnum = resline[pp+6:-1]
+            macnum = macnum.strip()
+            # print "original mac", macnum
+            # now munge it up the way Kindle app does
+            # by xoring it with 0xa5 and swapping elements 3 and 4
+            maclst = macnum.split(':')
+            n = len(maclst)
+            if n != 6:
+                fountIt = False
+                break
+            for i in range(6):
+                maclst[i] = int('0x' + maclst[i], 0)
+            mlst = [0x00, 0x00, 0x00, 0x00, 0x00, 0x00]
+            mlst[5] = maclst[5] ^ 0xa5
+            mlst[4] = maclst[3] ^ 0xa5
+            mlst[3] = maclst[4] ^ 0xa5
+            mlst[2] = maclst[2] ^ 0xa5
+            mlst[1] = maclst[1] ^ 0xa5
+            mlst[0] = maclst[0] ^ 0xa5
+            macnum = "%0.2x%0.2x%0.2x%0.2x%0.2x%0.2x" % (mlst[0], mlst[1], mlst[2], mlst[3], mlst[4], mlst[5])
+            foundIt = True
+            break
+    if not foundIt:
+        macnum = ''
+    return macnum
+
+
+# uses unix env to get username instead of using sysctlbyname 
+def GetUserName():
+    username = os.getenv('USER')
+    return username
+
+
+# implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used by Kindle for Mac versions < 1.6.0
+def CryptUnprotectData(encryptedData):
+    sernum = GetVolumeSerialNumber()
+    if sernum == '':
+        sernum = '9999999999'
+    sp = sernum + '!@#' + GetUserName()
+    passwdData = encode(SHA256(sp),charMap1)
+    salt = '16743'
+    iter = 0x3e8
+    keylen = 0x80
+    crp = LibCrypto()
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
+    key = key_iv[0:32]
+    iv = key_iv[32:48]
+    crp.set_decrypt_key(key,iv)
+    cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext,charMap1)
+    return cleartext
+
+
+def isNewInstall():
+    home = os.getenv('HOME')
+    # soccer game fan anyone
+    dpath = home + '/Library/Application Support/Kindle/storage/.pes2011'
+    # print dpath, os.path.exists(dpath)
+    if os.path.exists(dpath):
+        return True
+    return False
+    
+
+def GetIDString():
+    # K4Mac now has an extensive set of ids strings it uses
+    # in encoding pids and in creating unique passwords
+    # for use in its own version of CryptUnprotectDataV2
+
+    # BUT Amazon has now become nasty enough to detect when its app
+    # is being run under a debugger and actually changes code paths
+    # including which one of these strings is chosen, all to try 
+    # to prevent reverse engineering
+
+    # Sad really ... they will only hurt their own sales ...
+    # true book lovers really want to keep their books forever
+    # and move them to their devices and DRM prevents that so they 
+    # will just buy from someplace else that they can remove 
+    # the DRM from
+
+    # Amazon should know by now that true book lover's are not like
+    # penniless kids that pirate music, we do not pirate books
+
+    if isNewInstall():
+        mungedmac = GetMACAddressMunged()
+        if len(mungedmac) > 7:
+            return mungedmac
+    sernum = GetVolumeSerialNumber()
+    if len(sernum) > 7:
+        return sernum
+    diskpart = GetUserHomeAppSupKindleDirParitionName()
+    uuidnum = GetDiskPartitionUUID(diskpart)
+    if len(uuidnum) > 7:
+        return uuidnum
+    mungedmac = GetMACAddressMunged()
+    if len(mungedmac) > 7:
+        return mungedmac
+    return '9999999999'
+
+
+# implements an Pseudo Mac Version of Windows built-in Crypto routine
+# used for Kindle for Mac Versions >= 1.6.0
+def CryptUnprotectDataV2(encryptedData):
+    sp = GetUserName() + ':&%:' + GetIDString()
+    passwdData = encode(SHA256(sp),charMap5)
+    # salt generation as per the code
+    salt = 0x0512981d * 2 * 1 * 1
+    salt = str(salt) + GetUserName()
+    salt = encode(salt,charMap5)
+    crp = LibCrypto()
+    iter = 0x800
+    keylen = 0x400
+    key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
+    key = key_iv[0:32]
+    iv = key_iv[32:48]
+    crp.set_decrypt_key(key,iv)
+    cleartext = crp.decrypt(encryptedData)
+    cleartext = decode(cleartext, charMap5)
+    return cleartext
+
+
+# Locate the .kindle-info files
+def getKindleInfoFiles(kInfoFiles):
+    # first search for current .kindle-info files
+    home = os.getenv('HOME')
+    cmdline = 'find "' + home + '/Library/Application Support" -name ".kindle-info"'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p1.communicate()
+    reslst = out1.split('\n')
+    kinfopath = 'NONE'
+    found = False
+    for resline in reslst:
+        if os.path.isfile(resline):
+            kInfoFiles.append(resline)
+            found = True
+    # add any .kinf files 
+    cmdline = 'find "' + home + '/Library/Application Support" -name ".rainier*-kinf"'
+    cmdline = cmdline.encode(sys.getfilesystemencoding())
+    p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
+    out1, out2 = p1.communicate()
+    reslst = out1.split('\n')
+    for resline in reslst:
+        if os.path.isfile(resline):
+            kInfoFiles.append(resline)
+            found = True
+    if not found:
+        print('No kindle-info files have been found.')
+    return kInfoFiles
+
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
+    DB = {}
+    cnt = 0
+    infoReader = open(kInfoFile, 'r')
+    hdr = infoReader.read(1)
+    data = infoReader.read()
+
+    if data.find('[') != -1 :
+        # older style kindle-info file
+        items = data.split('[')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                cleartext = CryptUnprotectData(encryptedValue)
+                DB[keyname] = cleartext
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file used by K4Mac >= 1.6.0
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+    
+        # get the first item record
+        item = items.pop(0)
+    
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+        keyname = "unknown"
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        # "entropy" not used for K4Mac only K4PC
+        # entropy = SHA1(keyhash)
+    
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+    
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+    
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+    
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+    
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+    
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        noffset = contlen - primes(int(contlen/3))[-1]
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+    
+        # decode using charMap5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        cleartext = CryptUnprotectDataV2(encryptedValue)
+        # Debugging
+        # print keyname
+        # print cleartext
+        # print cleartext.encode('hex')
+        # print
+        DB[keyname] = cleartext
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
+    return DB

KindleBooks/lib/k4pcutils.py

@@ -0,0 +1,308 @@
+#!/usr/bin/env python
+# K4PC Windows specific routines
+
+from __future__ import with_statement
+
+import sys, os
+from struct import pack, unpack, unpack_from
+
+from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
+    create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
+    string_at, Structure, c_void_p, cast
+
+import _winreg as winreg
+
+MAX_PATH = 255
+
+kernel32 = windll.kernel32
+advapi32 = windll.advapi32
+crypt32 = windll.crypt32
+
+import traceback
+
+# crypto digestroutines
+import hashlib
+
+def MD5(message):
+    ctx = hashlib.md5()
+    ctx.update(message)
+    return ctx.digest()
+
+def SHA1(message):
+    ctx = hashlib.sha1()
+    ctx.update(message)
+    return ctx.digest()
+
+
+# simple primes table (<= n) calculator
+def primes(n): 
+    if n==2: return [2]
+    elif n<2: return []
+    s=range(3,n+1,2)
+    mroot = n ** 0.5
+    half=(n+1)/2-1
+    i=0
+    m=3
+    while m <= mroot:
+        if s[i]:
+            j=(m*m-3)/2
+            s[j]=0
+            while j<half:
+                s[j]=0
+                j+=m
+        i=i+1
+        m=2*i+3
+    return [2]+[x for x in s if x]
+
+
+# Various character maps used to decrypt kindle info values.
+# Probably supposed to act as obfuscation
+charMap2 = "AaZzB0bYyCc1XxDdW2wEeVv3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_"
+charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
+
+class DrmException(Exception):
+    pass
+
+# Encode the bytes in data with the characters in map
+def encode(data, map):
+    result = ""
+    for char in data:
+        value = ord(char)
+        Q = (value ^ 0x80) // len(map)
+        R = value % len(map)
+        result += map[Q]
+        result += map[R]
+    return result
+  
+# Hash the bytes in data and then encode the digest with the characters in map
+def encodeHash(data,map):
+    return encode(MD5(data),map)
+
+# Decode the string in data with the characters in map. Returns the decoded bytes
+def decode(data,map):
+    result = ""
+    for i in range (0,len(data)-1,2):
+        high = map.find(data[i])
+        low = map.find(data[i+1])
+        if (high == -1) or (low == -1) :
+            break
+        value = (((high * len(map)) ^ 0x80) & 0xFF) + low
+        result += pack("B",value)
+    return result
+
+
+# interface with Windows OS Routines
+class DataBlob(Structure):
+    _fields_ = [('cbData', c_uint),
+                ('pbData', c_void_p)]
+DataBlob_p = POINTER(DataBlob)
+
+
+def GetSystemDirectory():
+    GetSystemDirectoryW = kernel32.GetSystemDirectoryW
+    GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
+    GetSystemDirectoryW.restype = c_uint
+    def GetSystemDirectory():
+        buffer = create_unicode_buffer(MAX_PATH + 1)
+        GetSystemDirectoryW(buffer, len(buffer))
+        return buffer.value
+    return GetSystemDirectory
+GetSystemDirectory = GetSystemDirectory()
+
+def GetVolumeSerialNumber():
+    GetVolumeInformationW = kernel32.GetVolumeInformationW
+    GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
+                                      POINTER(c_uint), POINTER(c_uint),
+                                      POINTER(c_uint), c_wchar_p, c_uint]
+    GetVolumeInformationW.restype = c_uint
+    def GetVolumeSerialNumber(path = GetSystemDirectory().split('\\')[0] + '\\'):
+        vsn = c_uint(0)
+        GetVolumeInformationW(path, None, 0, byref(vsn), None, None, None, 0)
+        return str(vsn.value)
+    return GetVolumeSerialNumber
+GetVolumeSerialNumber = GetVolumeSerialNumber()
+
+def GetIDString():
+    return GetVolumeSerialNumber()
+
+def getLastError():
+    GetLastError = kernel32.GetLastError
+    GetLastError.argtypes = None
+    GetLastError.restype = c_uint
+    def getLastError():
+        return GetLastError()
+    return getLastError
+getLastError = getLastError()
+
+def GetUserName():
+    GetUserNameW = advapi32.GetUserNameW
+    GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
+    GetUserNameW.restype = c_uint
+    def GetUserName():
+        buffer = create_unicode_buffer(2)
+        size = c_uint(len(buffer))
+        while not GetUserNameW(buffer, byref(size)):
+            errcd = getLastError()
+            if errcd == 234:
+                # bad wine implementation up through wine 1.3.21
+                return "AlternateUserName"
+            buffer = create_unicode_buffer(len(buffer) * 2)
+            size.value = len(buffer)
+        return buffer.value.encode('utf-16-le')[::2]
+    return GetUserName
+GetUserName = GetUserName()
+
+def CryptUnprotectData():
+    _CryptUnprotectData = crypt32.CryptUnprotectData
+    _CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
+                                   c_void_p, c_void_p, c_uint, DataBlob_p]
+    _CryptUnprotectData.restype = c_uint
+    def CryptUnprotectData(indata, entropy, flags):
+        indatab = create_string_buffer(indata)
+        indata = DataBlob(len(indata), cast(indatab, c_void_p))
+        entropyb = create_string_buffer(entropy)
+        entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
+        outdata = DataBlob()
+        if not _CryptUnprotectData(byref(indata), None, byref(entropy),
+                                   None, None, flags, byref(outdata)):
+            raise DrmException("Failed to Unprotect Data")
+        return string_at(outdata.pbData, outdata.cbData)
+    return CryptUnprotectData
+CryptUnprotectData = CryptUnprotectData()
+
+
+# Locate all of the kindle-info style files and return as list
+def getKindleInfoFiles(kInfoFiles):
+    regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders\\")
+    path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
+
+    # first look for older kindle-info files
+    kinfopath = path +'\\Amazon\\Kindle For PC\\{AMAwzsaPaaZAzmZzZQzgZCAkZ3AjA_AY}\\kindle.info'
+    if not os.path.isfile(kinfopath):
+        print('No kindle.info files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
+    # now look for newer (K4PC 1.5.0 and later rainier.2.1.1.kinf file
+
+    kinfopath = path +'\\Amazon\\Kindle For PC\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.5.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
+    # now look for even newer (K4PC 1.6.0 and later) rainier.2.1.1.kinf file
+    kinfopath = path +'\\Amazon\\Kindle\\storage\\rainier.2.1.1.kinf'
+    if not os.path.isfile(kinfopath):
+        print('No K4PC 1.6.X .kinf files have not been found.')
+    else:
+        kInfoFiles.append(kinfopath)
+
+    return kInfoFiles
+
+
+# determine type of kindle info provided and return a 
+# database of keynames and values
+def getDBfromFile(kInfoFile):
+    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
+    DB = {}
+    cnt = 0
+    infoReader = open(kInfoFile, 'r')
+    hdr = infoReader.read(1)
+    data = infoReader.read()
+
+    if data.find('{') != -1 :
+
+        # older style kindle-info file
+        items = data.split('{')
+        for item in items:
+            if item != '':
+                keyhash, rawdata = item.split(':')
+                keyname = "unknown"
+                for name in names:
+                    if encodeHash(name,charMap2) == keyhash:
+                        keyname = name
+                        break
+                if keyname == "unknown":
+                    keyname = keyhash
+                encryptedValue = decode(rawdata,charMap2)
+                DB[keyname] = CryptUnprotectData(encryptedValue, "", 0)
+                cnt = cnt + 1
+        if cnt == 0:
+            DB = None
+        return DB
+
+    # else newer style .kinf file
+    # the .kinf file uses "/" to separate it into records
+    # so remove the trailing "/" to make it easy to use split
+    data = data[:-1]
+    items = data.split('/')
+
+    # loop through the item records until all are processed
+    while len(items) > 0:
+
+        # get the first item record
+        item = items.pop(0)
+
+        # the first 32 chars of the first record of a group
+        # is the MD5 hash of the key name encoded by charMap5
+        keyhash = item[0:32]
+
+        # the raw keyhash string is also used to create entropy for the actual
+        # CryptProtectData Blob that represents that keys contents
+        entropy = SHA1(keyhash)
+
+        # the remainder of the first record when decoded with charMap5 
+        # has the ':' split char followed by the string representation
+        # of the number of records that follow
+        # and make up the contents
+        srcnt = decode(item[34:],charMap5)
+        rcnt = int(srcnt)
+
+        # read and store in rcnt records of data
+        # that make up the contents value
+        edlst = []
+        for i in xrange(rcnt):
+            item = items.pop(0)
+            edlst.append(item)
+
+        keyname = "unknown"
+        for name in names:
+            if encodeHash(name,charMap5) == keyhash:
+                keyname = name
+                break
+        if keyname == "unknown":
+            keyname = keyhash
+
+        # the charMap5 encoded contents data has had a length 
+        # of chars (always odd) cut off of the front and moved
+        # to the end to prevent decoding using charMap5 from 
+        # working properly, and thereby preventing the ensuing 
+        # CryptUnprotectData call from succeeding.
+
+        # The offset into the charMap5 encoded contents seems to be:
+        # len(contents) - largest prime number less than or equal to int(len(content)/3)
+        # (in other words split "about" 2/3rds of the way through)
+
+        # move first offsets chars to end to align for decode by charMap5
+        encdata = "".join(edlst)
+        contlen = len(encdata)
+        noffset = contlen - primes(int(contlen/3))[-1]
+
+        # now properly split and recombine 
+        # by moving noffset chars from the start of the 
+        # string to the end of the string 
+        pfx = encdata[0:noffset]
+        encdata = encdata[noffset:]
+        encdata = encdata + pfx
+
+        # decode using Map5 to get the CryptProtect Data
+        encryptedValue = decode(encdata,charMap5)
+        DB[keyname] = CryptUnprotectData(encryptedValue, entropy, 1)
+        cnt = cnt + 1
+
+    if cnt == 0:
+        DB = None
+    return DB
+
+

KindleBooks/lib/kgenpids.py

@@ -11,16 +11,28 @@ from struct import pack, unpack, unpack_from
 class DrmException(Exception):
     pass
 
-global kindleDatabase
 global charMap1
-global charMap2
 global charMap3
 global charMap4
 
-if sys.platform.startswith('win'):
-    from k4pcutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
-if sys.platform.startswith('darwin'):
-    from k4mutils import getKindleInfoFiles, parseKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
+if inCalibre:
+    if sys.platform.startswith('win'):
+        from calibre_plugins.k4mobidedrm.k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from calibre_plugins.k4mobidedrm.k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+else:
+    if sys.platform.startswith('win'):
+        from k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
+    if sys.platform.startswith('darwin'):
+        from k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
+
 
 charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
 charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
@@ -66,50 +78,7 @@ def decode(data,map):
         value = (((high * len(map)) ^ 0x80) & 0xFF) + low
         result += pack("B",value)
     return result
-
-# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForHash(hashedKey):
-    global kindleDatabase
-    global charMap1
-    global charMap2
-    encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
-    if sys.platform.startswith('win'):
-        return CryptUnprotectData(encryptedValue,"")
-    else:
-        cleartext = CryptUnprotectData(encryptedValue)
-        return decode(cleartext, charMap1)
- 
-# Get a record from the Kindle.info file for the string in "key" (plaintext). 
-# Return the decoded and decrypted record
-def getKindleInfoValueForKey(key):
-    global charMap2
-    return getKindleInfoValueForHash(encodeHash(key,charMap2))
-
-# Find if the original string for a hashed/encoded string is known. 
-# If so return the original string othwise return an empty string.
-def findNameForHash(hash):
-    global charMap2
-    names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
-    result = ""
-    for name in names:
-        if hash == encodeHash(name, charMap2):
-           result = name
-           break
-    return result
     
-# Print all the records from the kindle.info file (option -i)
-def printKindleInfo():
-    for record in kindleDatabase:
-        name = findNameForHash(record)
-        if name != "" :
-            print (name)
-            print ("--------------------------")
-        else :
-            print ("Unknown Record")
-        print getKindleInfoValueForHash(record)
-        print "\n"
-
 #
 # PID generation routines
 #
@@ -222,15 +191,15 @@ def getKindlePid(pidlst, rec209, token, serialnum):
     return pidlst
 
 
-# Parse the EXTH header records and parse the Kindleinfo
-# file to calculate the book pid.
+# parse the Kindleinfo file to calculate the book pid.
+
+keynames = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
 
 def getK4Pids(pidlst, rec209, token, kInfoFile):
-    global kindleDatabase
     global charMap1
     kindleDatabase = None
     try:
-        kindleDatabase = parseKindleInfo(kInfoFile)
+        kindleDatabase = getDBfromFile(kInfoFile)
     except Exception, message:
         print(message)
         kindleDatabase = None
@@ -241,22 +210,22 @@ def getK4Pids(pidlst, rec209, token, kInfoFile):
         
     try:
         # Get the Mazama Random number
-        MazamaRandomNumber = getKindleInfoValueForKey("MazamaRandomNumber")
+        MazamaRandomNumber = kindleDatabase["MazamaRandomNumber"]
 
         # Get the kindle account token
-        kindleAccountToken = getKindleInfoValueForKey("kindle.account.tokens")
+        kindleAccountToken = kindleDatabase["kindle.account.tokens"]
     except KeyError:
         print "Keys not found in " + kInfoFile
         return pidlst
         
-    # Get the HDD serial
-    encodedSystemVolumeSerialNumber = encodeHash(GetVolumeSerialNumber(),charMap1)
+    # Get the ID string used
+    encodedIDString = encodeHash(GetIDString(),charMap1)
 
     # Get the current user name
     encodedUsername = encodeHash(GetUserName(),charMap1)
 
     # concat, hash and encode to calculate the DSN
-    DSN = encode(SHA1(MazamaRandomNumber+encodedSystemVolumeSerialNumber+encodedUsername),charMap1)
+    DSN = encode(SHA1(MazamaRandomNumber+encodedIDString+encodedUsername),charMap1)
        
     # Compute the device PID (for which I can tell, is used for nothing).
     table =  generatePidEncryptionTable()

KindleBooks/lib/mobidedrm.py

@@ -49,10 +49,13 @@
 #  0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
 #  0.28 - slight additional changes to metadata token generation (None -> '')
 #  0.29 - It seems that the ideas about when multibyte trailing characters were
-#         included in the encryption were wrong. They aren't for DOC compressed
-#         files, but they are for HUFF/CDIC compress files!
+#         included in the encryption were wrong. They are for DOC compressed
+#         files, but they are not for HUFF/CDIC compress files!
+#  0.30 - Modified interface slightly to work better with new calibre plugin style
+#  0.31 - The multibyte encrytion info is true for version 7 files too.
+#  0.32 - Added support for "Print Replica" Kindle ebooks
 
-__version__ = '0.29'
+__version__ = '0.32'
 
 import sys
 
@@ -161,8 +164,12 @@ class MobiBook:
         return self.data_file[off:endoff]
 
     def __init__(self, infile):
+        print ('MobiDeDrm v%(__version__)s. '
+           'Copyright 2008-2011 The Dark Reverser et al.' % globals())
+
         # initial sanity check on file
         self.data_file = file(infile, 'rb').read()
+        self.mobi_data = ''
         self.header = self.data_file[0:78]
         if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
             raise DrmException("invalid file format")
@@ -190,14 +197,15 @@ class MobiBook:
             self.meta_array = {}
             return
         self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
+        self.mobi_codepage, = struct.unpack('>L',self.sect[0x1c:0x20])
         self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
         print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
         self.extra_data_flags = 0
         if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
             self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
             print "Extra Data Flags = %d" % self.extra_data_flags
-        if (self.mobi_version < 7) and (self.compression != 17480):
-            # multibyte utf8 data is included in the encryption for mobi_version 6 and below
+        if (self.compression != 17480):
+            # multibyte utf8 data is included in the encryption for PalmDoc compression
             # so clear that byte so that we leave it to be decrypted.
             self.extra_data_flags &= 0xFFFE
 
@@ -227,8 +235,13 @@ class MobiBook:
         except:
             self.meta_array = {}
             pass
+        self.print_replica = False
             
     def getBookTitle(self):
+        codec_map = {
+            1252 : 'windows-1252',
+            65001 : 'utf-8',
+        }
         title = ''
         if 503 in self.meta_array:
             title = self.meta_array[503]
@@ -239,7 +252,10 @@ class MobiBook:
         if title == '':
             title = self.header[:32]
             title = title.split("\0")[0]
-        return title
+        codec = 'windows-1252'
+        if self.mobi_codepage in codec_map.keys():
+            codec = codec_map[self.mobi_codepage]
+        return unicode(title, codec).encode('utf-8')
 
     def getPIDMetaInfo(self):
         rec209 = ''
@@ -301,15 +317,29 @@ class MobiBook:
                         break
         return [found_key,pid]
 
+    def getMobiFile(self, outpath):
+        file(outpath,'wb').write(self.mobi_data)
+        
+    def getPrintReplica(self):
+        return self.print_replica
+
     def processBook(self, pidlist):
         crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
         print 'Crypto Type is: ', crypto_type
         self.crypto_type = crypto_type
         if crypto_type == 0:
             print "This book is not encrypted."
-            return self.data_file
+            # we must still check for Print Replica
+            self.print_replica = (self.loadSection(1)[0:4] == '%MOP')
+            self.mobi_data = self.data_file
+            return
         if crypto_type != 2 and crypto_type != 1:
             raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
+        if 406 in self.meta_array:
+            data406 = self.meta_array[406]
+            val406, = struct.unpack('>Q',data406)
+            if val406 != 0:
+                raise DrmException("Cannot decode library or rented ebooks.")
 
         goodpids = []
         for pid in pidlist:
@@ -353,39 +383,44 @@ class MobiBook:
 
         # decrypt sections
         print "Decrypting. Please wait . . .",
-        new_data = self.data_file[:self.sections[1][0]]
+        self.mobi_data = self.data_file[:self.sections[1][0]]
         for i in xrange(1, self.records+1):
             data = self.loadSection(i)
             extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
             if i%100 == 0:
                 print ".",
             # print "record %d, extra_size %d" %(i,extra_size)
-            new_data += PC1(found_key, data[0:len(data) - extra_size])
+            decoded_data = PC1(found_key, data[0:len(data) - extra_size])
+            if i==1:
+                self.print_replica = (decoded_data[0:4] == '%MOP')
+            self.mobi_data += decoded_data
             if extra_size > 0:
-                new_data += data[-extra_size:]
+                self.mobi_data += data[-extra_size:]
         if self.num_sections > self.records+1:
-            new_data += self.data_file[self.sections[self.records+1][0]:]
-        self.data_file = new_data
+            self.mobi_data += self.data_file[self.sections[self.records+1][0]:]
         print "done"
-        return self.data_file
+        return
 
 def getUnencryptedBook(infile,pid):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook([pid])
+    book.processBook([pid])
+    return book.mobi_data
 
 def getUnencryptedBookWithList(infile,pidlist):
     if not os.path.isfile(infile):
         raise DrmException('Input File Not Found')
     book = MobiBook(infile)
-    return book.processBook(pidlist)
+    book.processBook(pidlist)
+    return book.mobi_data
+
 
 def main(argv=sys.argv):
     print ('MobiDeDrm v%(__version__)s. '
-	   'Copyright 2008-2010 The Dark Reverser.' % globals())
+        'Copyright 2008-2011 The Dark Reverser et al.' % globals())
     if len(argv)<3 or len(argv)>4:
-        print "Removes protection from Mobipocket books"
+        print "Removes protection from Kindle/Mobipocket and Kindle/Print Replica ebooks"
         print "Usage:"
         print "    %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
         return 1
@@ -393,9 +428,9 @@ def main(argv=sys.argv):
         infile = argv[1]
         outfile = argv[2]
         if len(argv) is 4:
-        	pidlist = argv[3].split(',')
+            pidlist = argv[3].split(',')
         else:
-        	pidlist = {}
+            pidlist = {}
         try:
             stripped_file = getUnencryptedBookWithList(infile, pidlist)
             file(outfile, 'wb').write(stripped_file)

KindleBooks/lib/stylexml2css.py

@@ -81,6 +81,14 @@ class DocParser(object):
             pos = foundpos + 1
         return startpos
 
+    # returns a vector of integers for the tagpath
+    def getData(self, tagpath, pos, end):
+        argres=[]
+        (foundat, argt) = self.findinDoc(tagpath, pos, end)
+        if (argt != None) and (len(argt) > 0) :
+            argList = argt.split('|')
+            argres = [ int(strval) for strval in argList]
+        return argres
 
     def process(self):
 
@@ -237,7 +245,11 @@ def convert2CSS(flatxml, fontsize, ph, pw):
 
     # create a document parser
     dp = DocParser(flatxml, fontsize, ph, pw)
-
     csspage = dp.process()
-
     return csspage
+
+
+def getpageIDMap(flatxml):
+    dp = DocParser(flatxml, 0, 0, 0)
+    pageidnumbers = dp.getData('info.original.pid', 0, -1)
+    return pageidnumbers

KindleBooks/lib/topazextract.py

@@ -10,7 +10,12 @@ class Unbuffered:
         return getattr(self.stream, attr)
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
+
+if 'calibre' in sys.modules:
+    inCalibre = True
+else:
+    inCalibre = False
+
 import os, csv, getopt
 import zlib, zipfile, tempfile, shutil
 from struct import pack
@@ -18,10 +23,32 @@ from struct import unpack
 
 class TpzDRMError(Exception):
     pass
+
     
 # local support routines
-import kgenpids
-import genbook
+if inCalibre:
+    from calibre_plugins.k4mobidedrm import kgenpids
+    from calibre_plugins.k4mobidedrm import genbook
+else:
+    import kgenpids
+    import genbook
+
+
+# recursive zip creation support routine
+def zipUpDir(myzip, tdir, localname):
+    currentdir = tdir
+    if localname != "":
+        currentdir = os.path.join(currentdir,localname)
+    list = os.listdir(currentdir)
+    for file in list:
+        afilename = file
+        localfilePath = os.path.join(localname, afilename)
+        realfilePath = os.path.join(currentdir,file)
+        if os.path.isfile(realfilePath):
+            myzip.write(realfilePath, localfilePath)
+        elif os.path.isdir(realfilePath):
+            zipUpDir(myzip, tdir, localfilePath)
+
 #
 # Utility routines
 #
@@ -110,9 +137,10 @@ def decryptDkeyRecords(data,PID):
 
 
 class TopazBook:
-    def __init__(self, filename, outdir):
+    def __init__(self, filename):
         self.fo = file(filename, 'rb')
-        self.outdir = outdir
+        self.outdir = tempfile.mkdtemp()
+        # self.outdir = 'rawdat'
         self.bookPayloadOffset = 0
         self.bookHeaderRecords = {}
         self.bookMetadata = {}
@@ -317,21 +345,34 @@ class TopazBook:
                         file(outputFile, 'wb').write(record)
         print " "
 
+    def getHTMLZip(self, zipname):
+        htmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        htmlzip.write(os.path.join(self.outdir,'book.html'),'book.html')
+        htmlzip.write(os.path.join(self.outdir,'book.opf'),'book.opf')
+        if os.path.isfile(os.path.join(self.outdir,'cover.jpg')):
+            htmlzip.write(os.path.join(self.outdir,'cover.jpg'),'cover.jpg')
+        htmlzip.write(os.path.join(self.outdir,'style.css'),'style.css')
+        zipUpDir(htmlzip, self.outdir, 'img')
+        htmlzip.close()
 
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
+    def getSVGZip(self, zipname):
+        svgzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        svgzip.write(os.path.join(self.outdir,'index_svg.xhtml'),'index_svg.xhtml')
+        zipUpDir(svgzip, self.outdir, 'svg')
+        zipUpDir(svgzip, self.outdir, 'img')
+        svgzip.close()
 
+    def getXMLZip(self, zipname):
+        xmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
+        targetdir = os.path.join(self.outdir,'xml')
+        zipUpDir(xmlzip, targetdir, '')
+        zipUpDir(xmlzip, self.outdir, 'img')
+        xmlzip.close()
+
+    def cleanup(self):
+        if os.path.isdir(self.outdir):
+            pass
+            # shutil.rmtree(self.outdir, True)
 
 def usage(progname):
     print "Removes DRM protection from Topaz ebooks and extract the contents"
@@ -383,58 +424,46 @@ def main(argv=sys.argv):
         return 1
 
     bookname = os.path.splitext(os.path.basename(infile))[0]
-    tempdir = tempfile.mkdtemp()
 
-    tb = TopazBook(infile, tempdir)
+    tb = TopazBook(infile)
     title = tb.getBookTitle()
     print "Processing Book: ", title
     keysRecord, keysRecordRecord = tb.getPIDMetaInfo()
     pidlst = kgenpids.getPidList(keysRecord, keysRecordRecord, k4, pids, serials, kInfoFiles) 
 
     try:
+        print "Decrypting Book"
         tb.processBook(pidlst)
+
+        print "   Creating HTML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_nodrm' + '.htmlz')
+        tb.getHTMLZip(zipname)
+
+        print "   Creating SVG ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
+        tb.getSVGZip(zipname)
+
+        print "   Creating XML ZIP Archive"
+        zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
+        tb.getXMLZip(zipname)
+
+        # removing internal temporary directory of pieces
+        tb.cleanup()
+
     except TpzDRMError, e:
         print str(e)
-        print "   Creating DeBug Full Zip Archive of Book"
-        zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-        myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-        zipUpDir(myzip, tempdir, '')
-        myzip.close()
-        shutil.rmtree(tempdir, True)
+        # tb.cleanup()
         return 1
 
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
-
-    print "   Creating SVG ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
-
-    print "   Creating XML ZIP Archive"
-    zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
-
-    shutil.rmtree(tempdir, True)
+    except Exception, e:
+        print str(e)
+        # tb.cleanup
+        return 1
 
     return 0
                 
 
 if __name__ == '__main__':
+    sys.stdout=Unbuffered(sys.stdout)
     sys.exit(main())
 

KindleBooks_Tools/KindleBooks/lib/k4mobidedrm.py

@@ -1,374 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import with_statement
-
-# engine to remove drm from Kindle for Mac and Kindle for PC books
-# for personal use for archiving and converting your ebooks
-
-# PLEASE DO NOT PIRATE EBOOKS! 
-
-# We want all authors and publishers, and eBook stores to live
-# long and prosperous lives but at the same time  we just want to 
-# be able to read OUR books on whatever device we want and to keep 
-# readable for a long, long time
-
-#  This borrows very heavily from works by CMBDTC, IHeartCabbages, skindle, 
-#    unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates 
-#    and many many others
-
-# It can run standalone to convert K4M/K4PC/Mobi files, or it can be installed as a
-# plugin for Calibre (http://calibre-ebook.com/about) so that importing
-# K4 or Mobi with DRM is no londer a multi-step process.
-#
-# ***NOTE*** If you are using this script as a calibre plugin for a K4M or K4PC ebook
-# then calibre must be installed on the same machine and in the same account as K4PC or K4M
-# for the plugin version to function properly.
-#
-# To create a Calibre plugin, rename this file so that the filename
-# ends in '_plugin.py', put it into a ZIP file with all its supporting python routines
-# and import that ZIP into Calibre using its plugin configuration GUI.
-
-
-__version__ = '2.8'
-
-class Unbuffered:
-    def __init__(self, stream):
-        self.stream = stream
-    def write(self, data):
-        self.stream.write(data)
-        self.stream.flush()
-    def __getattr__(self, attr):
-        return getattr(self.stream, attr)
-
-import sys
-import os, csv, getopt
-import string
-import binascii
-import zlib
-import re
-import zlib, zipfile, tempfile, shutil
-from struct import pack, unpack, unpack_from
-
-class DrmException(Exception):
-    pass
-
-if 'calibre' in sys.modules:
-    inCalibre = True
-else:
-    inCalibre = False
-
-def zipUpDir(myzip, tempdir,localname):
-    currentdir = tempdir
-    if localname != "":
-        currentdir = os.path.join(currentdir,localname)
-    list = os.listdir(currentdir)
-    for file in list:
-        afilename = file
-        localfilePath = os.path.join(localname, afilename)
-        realfilePath = os.path.join(currentdir,file)
-        if os.path.isfile(realfilePath):
-            myzip.write(realfilePath, localfilePath)
-        elif os.path.isdir(realfilePath):
-            zipUpDir(myzip, tempdir, localfilePath)
-
-# cleanup bytestring filenames
-# borrowed from calibre from calibre/src/calibre/__init__.py
-# added in removal of non-printing chars
-# and removal of . at start
-# convert spaces to underscores
-def cleanup_name(name):
-    _filename_sanitize = re.compile(r'[\xae\0\\|\?\*<":>\+/]')
-    substitute='_'
-    one = ''.join(char for char in name if char in string.printable)
-    one = _filename_sanitize.sub(substitute, one)
-    one = re.sub(r'\s', ' ', one).strip()
-    one = re.sub(r'^\.+$', '_', one)
-    one = one.replace('..', substitute)
-    # Windows doesn't like path components that end with a period
-    if one.endswith('.'):
-        one = one[:-1]+substitute
-    # Mac and Unix don't like file names that begin with a full stop
-    if len(one) > 0 and one[0] == '.':
-        one = substitute+one[1:]
-    one = one.replace(' ','_')
-    return one
-
-def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
-    import mobidedrm
-    import topazextract
-    import kgenpids
-
-    # handle the obvious cases at the beginning
-    if not os.path.isfile(infile):
-        print "Error: Input file does not exist"
-        return 1
-
-    mobi = True
-    magic3 = file(infile,'rb').read(3)
-    if magic3 == 'TPZ':
-        mobi = False
-
-    bookname = os.path.splitext(os.path.basename(infile))[0]
-
-    if mobi:
-        mb = mobidedrm.MobiBook(infile)
-    else:
-        tempdir = tempfile.mkdtemp()
-        mb = topazextract.TopazBook(infile, tempdir)
-
-    title = mb.getBookTitle()
-    print "Processing Book: ", title
-    filenametitle = cleanup_name(title)
-    outfilename = bookname
-    if len(bookname)>4 and len(filenametitle)>4 and bookname[:4] != filenametitle[:4]:
-        outfilename = outfilename + "_" + filenametitle
-
-    # build pid list
-    md1, md2 = mb.getPIDMetaInfo()
-    pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
-
-    try:
-        if mobi:
-            unlocked_file = mb.processBook(pidlst)
-        else:
-            mb.processBook(pidlst)
-
-    except mobidedrm.DrmException, e:
-        print "Error: " + str(e) + "\nDRM Removal Failed.\n"
-        return 1
-    except Exception, e:
-        if not mobi:
-            print "Error: " + str(e) + "\nDRM Removal Failed.\n"
-            print "   Creating DeBug Full Zip Archive of Book"
-            zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
-            myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-            zipUpDir(myzip, tempdir, '')
-            myzip.close()
-            shutil.rmtree(tempdir, True)
-            return 1
-        pass
-
-    if mobi:
-        outfile = os.path.join(outdir,outfilename + '_nodrm' + '.mobi')
-        file(outfile, 'wb').write(unlocked_file)
-        return 0            
-
-    # topaz:  build up zip archives of results
-    print "   Creating HTML ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_nodrm' + '.zip')
-    myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
-    myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
-    if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-        myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-    myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
-    zipUpDir(myzip1, tempdir, 'img')
-    myzip1.close()
-
-    print "   Creating SVG ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
-    myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
-    zipUpDir(myzip2, tempdir, 'svg')
-    zipUpDir(myzip2, tempdir, 'img')
-    myzip2.close()
-
-    print "   Creating XML ZIP Archive"
-    zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
-    myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
-    targetdir = os.path.join(tempdir,'xml')
-    zipUpDir(myzip3, targetdir, '')
-    zipUpDir(myzip3, tempdir, 'img')
-    myzip3.close()
-
-    shutil.rmtree(tempdir, True)
-    return 0
-
-
-def usage(progname):
-    print "Removes DRM protection from K4PC/M, Kindle, Mobi and Topaz ebooks"
-    print "Usage:"
-    print "    %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir>  " % progname
-
-#
-# Main
-#   
-def main(argv=sys.argv):
-    progname = os.path.basename(argv[0])
-
-    k4 = False
-    kInfoFiles = []
-    serials = []
-    pids = []
-    
-    print ('K4MobiDeDrm v%(__version__)s '
-	   'provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc .' % globals())
-
-    print ' '
-    try:
-        opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
-    except getopt.GetoptError, err:
-        print str(err)
-        usage(progname)
-        sys.exit(2)
-    if len(args)<2:
-        usage(progname)
-        sys.exit(2)
-        
-    for o, a in opts:
-        if o == "-k":
-            if a == None :
-                raise DrmException("Invalid parameter for -k")
-            kInfoFiles.append(a)
-        if o == "-p":
-            if a == None :
-                raise DrmException("Invalid parameter for -p")
-            pids = a.split(',')
-        if o == "-s":
-            if a == None :
-                raise DrmException("Invalid parameter for -s")
-            serials = a.split(',')
-
-    # try with built in Kindle Info files
-    k4 = True
-    if sys.platform.startswith('linux'):
-	k4 = False
-	kInfoFiles = None
-    infile = args[0]
-    outdir = args[1]
-
-    return decryptBook(infile, outdir, k4, kInfoFiles, serials, pids)
-
-
-if __name__ == '__main__':
-    sys.stdout=Unbuffered(sys.stdout)
-    sys.exit(main())
-
-if not __name__ == "__main__" and inCalibre:
-    from calibre.customize import FileTypePlugin
-
-    class K4DeDRM(FileTypePlugin):
-        name                = 'K4PC, K4Mac, Kindle Mobi and Topaz DeDRM' # Name of the plugin
-        description         = 'Removes DRM from K4PC and Mac, Kindle Mobi and Topaz files. \
-                                Provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc.'
-        supported_platforms = ['osx', 'windows', 'linux'] # Platforms this plugin will run on
-        author              = 'DiapDealer, SomeUpdates' # The author of this plugin
-        version             = (0, 2, 8)   # The version number of this plugin
-        file_types          = set(['prc','mobi','azw','azw1','tpz']) # The file types that this plugin will be applied to
-        on_import           = True # Run this plugin during the import
-        priority            = 210  # run this plugin before mobidedrm, k4pcdedrm, k4dedrm
-
-        def run(self, path_to_ebook):
-            from calibre.gui2 import is_ok_to_use_qt
-            from PyQt4.Qt import QMessageBox
-            from calibre.ptempfile import PersistentTemporaryDirectory
-
-            import kgenpids
-            import zlib
-            import zipfile
-            import topazextract
-            import mobidedrm
-
-            k4 = True
-	    if sys.platform.startswith('linux'):
-		k4 = False
-            pids = []
-            serials = []
-            kInfoFiles = []
-
-            # Get supplied list of PIDs to try from plugin customization.
-            customvalues = self.site_customization.split(',')
-            for customvalue in customvalues:
-                customvalue = str(customvalue)
-                customvalue = customvalue.strip()
-            	if len(customvalue) == 10 or len(customvalue) == 8:
-                    pids.append(customvalue)
-            	else :
-                    if len(customvalue) == 16 and customvalue[0] == 'B':
-                        serials.append(customvalue)
-                    else:
-                        print "%s is not a valid Kindle serial number or PID." % str(customvalue)
-            		
-            # Load any kindle info files (*.info) included Calibre's config directory.
-            try:
-                # Find Calibre's configuration directory.
-                confpath = os.path.split(os.path.split(self.plugin_path)[0])[0]
-                print 'K4MobiDeDRM: Calibre configuration directory = %s' % confpath
-                files = os.listdir(confpath)
-                filefilter = re.compile("\.info$", re.IGNORECASE)
-                files = filter(filefilter.search, files)
-    
-                if files:
-                    for filename in files:
-                        fpath = os.path.join(confpath, filename)
-                        kInfoFiles.append(fpath)
-                        print 'K4MobiDeDRM: Kindle info file %s found in config folder.' % filename
-            except IOError:
-                print 'K4MobiDeDRM: Error reading kindle info files from config directory.'
-                pass
-
-
-            mobi = True
-            magic3 = file(path_to_ebook,'rb').read(3)
-            if magic3 == 'TPZ':
-                mobi = False
-
-            bookname = os.path.splitext(os.path.basename(path_to_ebook))[0]
-
-            if mobi:
-                mb = mobidedrm.MobiBook(path_to_ebook)
-            else:
-                tempdir = PersistentTemporaryDirectory()
-                mb = topazextract.TopazBook(path_to_ebook, tempdir)
-
-            title = mb.getBookTitle()
-            md1, md2 = mb.getPIDMetaInfo()
-            pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles) 
-
-            try:
-                if mobi:
-                    unlocked_file = mb.processBook(pidlst)
-                else:
-                    mb.processBook(pidlst)
-
-            except mobidedrm.DrmException:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-            except topazextract.TpzDRMError:
-                #if you reached here then no luck raise and exception
-                if is_ok_to_use_qt():
-                    d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM Plugin", "Error decoding: %s\n" % path_to_ebook)
-                    d.show()
-                    d.raise_()
-                    d.exec_()
-                raise Exception("K4MobiDeDRM plugin could not decode the file")
-                return ""
-
-            print "Success!"
-            if mobi:
-                of = self.temporary_file(bookname+'.mobi')
-                of.write(unlocked_file)
-                of.close()
-                return of.name
-
-            # topaz:  build up zip archives of results
-            print "   Creating HTML ZIP Archive"
-            of = self.temporary_file(bookname + '.zip')
-            myzip = zipfile.ZipFile(of.name,'w',zipfile.ZIP_DEFLATED, False)
-            myzip.write(os.path.join(tempdir,'book.html'),'book.html')
-            myzip.write(os.path.join(tempdir,'book.opf'),'book.opf')
-            if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
-                myzip.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
-            myzip.write(os.path.join(tempdir,'style.css'),'style.css')
-            zipUpDir(myzip, tempdir, 'img')
-            myzip.close()
-            return of.name
-
-        def customization_help(self, gui=False):
-            return 'Enter 10 character PIDs and/or Kindle serial numbers, separated by commas.'

KindleBooks_Tools/KindleBooks/lib/k4mutils.py

@@ -1,200 +0,0 @@
-# standlone set of Mac OSX specific routines needed for K4DeDRM
-
-from __future__ import with_statement
-import sys
-import os
-import subprocess
-
-
-class DrmException(Exception):
-    pass
-
-
-# interface to needed routines in openssl's libcrypto
-def _load_crypto_libcrypto():
-    from ctypes import CDLL, byref, POINTER, c_void_p, c_char_p, c_int, c_long, \
-        Structure, c_ulong, create_string_buffer, addressof, string_at, cast
-    from ctypes.util import find_library
-
-    libcrypto = find_library('crypto')
-    if libcrypto is None:
-        raise DrmException('libcrypto not found')
-    libcrypto = CDLL(libcrypto)
-
-    AES_MAXNR = 14
-    c_char_pp = POINTER(c_char_p)
-    c_int_p = POINTER(c_int)
-
-    class AES_KEY(Structure):
-        _fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))), ('rounds', c_int)]
-    AES_KEY_p = POINTER(AES_KEY)
-    
-    def F(restype, name, argtypes):
-        func = getattr(libcrypto, name)
-        func.restype = restype
-        func.argtypes = argtypes
-        return func
-    
-    AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,c_int])
-
-    AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',[c_char_p, c_int, AES_KEY_p])
-
-    PKCS5_PBKDF2_HMAC_SHA1 = F(c_int, 'PKCS5_PBKDF2_HMAC_SHA1', 
-                                [c_char_p, c_ulong, c_char_p, c_ulong, c_ulong, c_ulong, c_char_p])
-    
-    class LibCrypto(object):
-        def __init__(self):
-            self._blocksize = 0
-            self._keyctx = None
-            self.iv = 0
-
-        def set_decrypt_key(self, userkey, iv):
-            self._blocksize = len(userkey)
-            if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
-                raise DrmException('AES improper key used')
-                return
-            keyctx = self._keyctx = AES_KEY()
-            self.iv = iv
-            rv = AES_set_decrypt_key(userkey, len(userkey) * 8, keyctx)
-            if rv < 0:
-                raise DrmException('Failed to initialize AES key')
-
-        def decrypt(self, data):
-            out = create_string_buffer(len(data))
-            rv = AES_cbc_encrypt(data, out, len(data), self._keyctx, self.iv, 0)
-            if rv == 0:
-                raise DrmException('AES decryption failed')
-            return out.raw
-
-        def keyivgen(self, passwd):
-            salt = '16743'
-            saltlen = 5
-            passlen = len(passwd)
-            iter = 0x3e8
-            keylen = 80
-            out = create_string_buffer(keylen)
-            rv = PKCS5_PBKDF2_HMAC_SHA1(passwd, passlen, salt, saltlen, iter, keylen, out)
-            return out.raw
-    return LibCrypto
-
-def _load_crypto():
-    LibCrypto = None
-    try:
-        LibCrypto = _load_crypto_libcrypto()
-    except (ImportError, DrmException):
-        pass
-    return LibCrypto
-
-LibCrypto = _load_crypto()
-
-#
-# Utility Routines
-#
-
-
-# Various character maps used to decrypt books. Probably supposed to act as obfuscation
-charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
-charMap2 = "ZB0bYyc1xDdW2wEV3Ff7KkPpL8UuGA4gz-Tme9Nn_tHh5SvXCsIiR6rJjQaqlOoM" 
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
-
-
-
-# uses a sub process to get the Hard Drive Serial Number using ioreg
-# returns with the serial number of drive whose BSD Name is "disk0"
-def GetVolumeSerialNumber():
-    sernum = os.getenv('MYSERIALNUMBER')
-    if sernum != None:
-        return sernum
-    cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
-    cmdline = cmdline.encode(sys.getfilesystemencoding())
-    p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
-    out1, out2 = p.communicate()
-    reslst = out1.split('\n')
-    cnt = len(reslst)
-    bsdname = None
-    sernum = None
-    foundIt = False
-    for j in xrange(cnt):
-        resline = reslst[j]
-        pp = resline.find('"Serial Number" = "')
-        if pp >= 0:
-            sernum = resline[pp+19:-1]
-            sernum = sernum.strip()
-        bb = resline.find('"BSD Name" = "')
-        if bb >= 0:
-            bsdname = resline[bb+14:-1]
-            bsdname = bsdname.strip()
-            if (bsdname == 'disk0') and (sernum != None):
-                foundIt = True
-                break
-    if not foundIt:
-        sernum = '9999999999'
-    return sernum
-
-# uses unix env to get username instead of using sysctlbyname 
-def GetUserName():
-    username = os.getenv('USER')
-    return username
-
-
-def encode(data, map):
-    result = ""
-    for char in data:
-        value = ord(char)
-        Q = (value ^ 0x80) // len(map)
-        R = value % len(map)
-        result += map[Q]
-        result += map[R]
-    return result
-
-import hashlib
-
-def SHA256(message):
-    ctx = hashlib.sha256()
-    ctx.update(message)
-    return ctx.digest()
-
-# implements an Pseudo Mac Version of Windows built-in Crypto routine
-def CryptUnprotectData(encryptedData):
-    sp = GetVolumeSerialNumber() + '!@#' + GetUserName()
-    passwdData = encode(SHA256(sp),charMap1)
-    crp = LibCrypto()
-    key_iv = crp.keyivgen(passwdData)
-    key = key_iv[0:32]
-    iv = key_iv[32:48]
-    crp.set_decrypt_key(key,iv)
-    cleartext = crp.decrypt(encryptedData)
-    return cleartext
-
-
-# Locate the .kindle-info files
-def getKindleInfoFiles(kInfoFiles):
-    home = os.getenv('HOME')
-    cmdline = 'find "' + home + '/Library/Application Support" -name ".kindle-info"'
-    cmdline = cmdline.encode(sys.getfilesystemencoding())
-    p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
-    out1, out2 = p1.communicate()
-    reslst = out1.split('\n')
-    kinfopath = 'NONE'
-    found = False
-    cnt = len(reslst)
-    for resline in reslst:
-        if os.path.isfile(resline):
-            kInfoFiles.append(resline)
-            found = True
-    if not found:
-        print('No .kindle-info files have been found.')
-    return kInfoFiles
-
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
-    DB = {}
-    infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
-    data = infoReader.read()
-    items = data.split('[')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
-    return DB

KindleBooks_Tools/KindleBooks/lib/k4pcutils.py

@@ -1,117 +0,0 @@
-# K4PC Windows specific routines
-
-from __future__ import with_statement
-
-import sys, os
-
-from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
-    create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
-    string_at, Structure, c_void_p, cast
-
-import _winreg as winreg
-
-import traceback
-
-MAX_PATH = 255
-
-kernel32 = windll.kernel32
-advapi32 = windll.advapi32
-crypt32 = windll.crypt32
-
-
-# Various character maps used to decrypt books. Probably supposed to act as obfuscation
-charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
-charMap2 = "AaZzB0bYyCc1XxDdW2wEeVv3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_"
-charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
-charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
-
-class DrmException(Exception):
-    pass
-    
-
-class DataBlob(Structure):
-    _fields_ = [('cbData', c_uint),
-                ('pbData', c_void_p)]
-DataBlob_p = POINTER(DataBlob)
-
-
-def GetSystemDirectory():
-    GetSystemDirectoryW = kernel32.GetSystemDirectoryW
-    GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
-    GetSystemDirectoryW.restype = c_uint
-    def GetSystemDirectory():
-        buffer = create_unicode_buffer(MAX_PATH + 1)
-        GetSystemDirectoryW(buffer, len(buffer))
-        return buffer.value
-    return GetSystemDirectory
-GetSystemDirectory = GetSystemDirectory()
-
-def GetVolumeSerialNumber():
-    GetVolumeInformationW = kernel32.GetVolumeInformationW
-    GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
-                                      POINTER(c_uint), POINTER(c_uint),
-                                      POINTER(c_uint), c_wchar_p, c_uint]
-    GetVolumeInformationW.restype = c_uint
-    def GetVolumeSerialNumber(path = GetSystemDirectory().split('\\')[0] + '\\'):
-        vsn = c_uint(0)
-        GetVolumeInformationW(path, None, 0, byref(vsn), None, None, None, 0)
-        return str(vsn.value)
-    return GetVolumeSerialNumber
-GetVolumeSerialNumber = GetVolumeSerialNumber()
-
-
-def GetUserName():
-    GetUserNameW = advapi32.GetUserNameW
-    GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
-    GetUserNameW.restype = c_uint
-    def GetUserName():
-        buffer = create_unicode_buffer(32)
-        size = c_uint(len(buffer))
-        while not GetUserNameW(buffer, byref(size)):
-            buffer = create_unicode_buffer(len(buffer) * 2)
-            size.value = len(buffer)
-        return buffer.value.encode('utf-16-le')[::2]
-    return GetUserName
-GetUserName = GetUserName()
-
-
-def CryptUnprotectData():
-    _CryptUnprotectData = crypt32.CryptUnprotectData
-    _CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
-                                   c_void_p, c_void_p, c_uint, DataBlob_p]
-    _CryptUnprotectData.restype = c_uint
-    def CryptUnprotectData(indata, entropy):
-        indatab = create_string_buffer(indata)
-        indata = DataBlob(len(indata), cast(indatab, c_void_p))
-        entropyb = create_string_buffer(entropy)
-        entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
-        outdata = DataBlob()
-        if not _CryptUnprotectData(byref(indata), None, byref(entropy),
-                                   None, None, 0, byref(outdata)):
-            raise DrmException("Failed to Unprotect Data")
-        return string_at(outdata.pbData, outdata.cbData)
-    return CryptUnprotectData
-CryptUnprotectData = CryptUnprotectData()
-
-# Locate the .kindle-info files
-def getKindleInfoFiles(kInfoFiles):
-    regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders\\")
-    path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
-    kinfopath = path +'\\Amazon\\Kindle For PC\\{AMAwzsaPaaZAzmZzZQzgZCAkZ3AjA_AY}\\kindle.info'
-    if not os.path.isfile(kinfopath):
-        print('The kindle.info files has not been found.')
-    else:
-        kInfoFiles.append(kinfopath)
-    return kInfoFiles
-
-# Parse the Kindle.info file and return the records as a list of key-values
-def parseKindleInfo(kInfoFile):
-    DB = {}
-    infoReader = open(kInfoFile, 'r')
-    infoReader.read(1)
-    data = infoReader.read()
-    items = data.split('{')
-    for item in items:
-        splito = item.split(':')
-        DB[splito[0]] =splito[1]
-    return DB

KindleBooks_Tools/KindleBooks/lib/mobidedrm.py

@@ -1,409 +0,0 @@
-#!/usr/bin/python
-#
-# This is a python script. You need a Python interpreter to run it.
-# For example, ActiveState Python, which exists for windows.
-#
-# Changelog
-#  0.01 - Initial version
-#  0.02 - Huffdic compressed books were not properly decrypted
-#  0.03 - Wasn't checking MOBI header length
-#  0.04 - Wasn't sanity checking size of data record
-#  0.05 - It seems that the extra data flags take two bytes not four
-#  0.06 - And that low bit does mean something after all :-)
-#  0.07 - The extra data flags aren't present in MOBI header < 0xE8 in size
-#  0.08 - ...and also not in Mobi header version < 6
-#  0.09 - ...but they are there with Mobi header version 6, header size 0xE4!
-#  0.10 - Outputs unencrypted files as-is, so that when run as a Calibre
-#         import filter it works when importing unencrypted files.
-#         Also now handles encrypted files that don't need a specific PID.
-#  0.11 - use autoflushed stdout and proper return values
-#  0.12 - Fix for problems with metadata import as Calibre plugin, report errors
-#  0.13 - Formatting fixes: retabbed file, removed trailing whitespace
-#         and extra blank lines, converted CR/LF pairs at ends of each line,
-#         and other cosmetic fixes.
-#  0.14 - Working out when the extra data flags are present has been problematic
-#         Versions 7 through 9 have tried to tweak the conditions, but have been
-#         only partially successful. Closer examination of lots of sample
-#         files reveals that a confusion has arisen because trailing data entries
-#         are not encrypted, but it turns out that the multibyte entries
-#         in utf8 file are encrypted. (Although neither kind gets compressed.)
-#         This knowledge leads to a simplification of the test for the 
-#         trailing data byte flags - version 5 and higher AND header size >= 0xE4. 
-#  0.15 - Now outputs 'heartbeat', and is also quicker for long files.
-#  0.16 - And reverts to 'done' not 'done.' at the end for unswindle compatibility.
-#  0.17 - added modifications to support its use as an imported python module
-#         both inside calibre and also in other places (ie K4DeDRM tools)
-#  0.17a- disabled the standalone plugin feature since a plugin can not import
-#         a plugin
-#  0.18 - It seems that multibyte entries aren't encrypted in a v7 file...
-#         Removed the disabled Calibre plug-in code
-#         Permit use of 8-digit PIDs
-#  0.19 - It seems that multibyte entries aren't encrypted in a v6 file either.
-#  0.20 - Correction: It seems that multibyte entries are encrypted in a v6 file.
-#  0.21 - Added support for multiple pids
-#  0.22 - revised structure to hold MobiBook as a class to allow an extended interface
-#  0.23 - fixed problem with older files with no EXTH section 
-#  0.24 - add support for type 1 encryption and 'TEXtREAd' books as well
-#  0.25 - Fixed support for 'BOOKMOBI' type 1 encryption
-#  0.26 - Now enables Text-To-Speech flag and sets clipping limit to 100%
-#  0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
-#  0.28 - slight additional changes to metadata token generation (None -> '')
-#  0.29 - It seems that the ideas about when multibyte trailing characters were
-#         included in the encryption were wrong. They aren't for DOC compressed
-#         files, but they are for HUFF/CDIC compress files!
-
-__version__ = '0.29'
-
-import sys
-
-class Unbuffered:
-    def __init__(self, stream):
-        self.stream = stream
-    def write(self, data):
-        self.stream.write(data)
-        self.stream.flush()
-    def __getattr__(self, attr):
-        return getattr(self.stream, attr)
-sys.stdout=Unbuffered(sys.stdout)
-
-import os
-import struct
-import binascii
-
-class DrmException(Exception):
-    pass
-
-
-#
-# MobiBook Utility Routines
-#
-
-# Implementation of Pukall Cipher 1
-def PC1(key, src, decryption=True):
-    sum1 = 0;
-    sum2 = 0;
-    keyXorVal = 0;
-    if len(key)!=16:
-        print "Bad key length!"
-        return None
-    wkey = []
-    for i in xrange(8):
-        wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
-    dst = ""
-    for i in xrange(len(src)):
-        temp1 = 0;
-        byteXorVal = 0;
-        for j in xrange(8):
-            temp1 ^= wkey[j]
-            sum2  = (sum2+j)*20021 + sum1
-            sum1  = (temp1*346)&0xFFFF
-            sum2  = (sum2+sum1)&0xFFFF
-            temp1 = (temp1*20021+1)&0xFFFF
-            byteXorVal ^= temp1 ^ sum2
-        curByte = ord(src[i])
-        if not decryption:
-            keyXorVal = curByte * 257;
-        curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
-        if decryption:
-            keyXorVal = curByte * 257;
-        for j in xrange(8):
-            wkey[j] ^= keyXorVal;
-        dst+=chr(curByte)
-    return dst
-
-def checksumPid(s):
-    letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
-    crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
-    crc = crc ^ (crc >> 16)
-    res = s
-    l = len(letters)
-    for i in (0,1):
-        b = crc & 0xff
-        pos = (b // l) ^ (b % l)
-        res += letters[pos%l]
-        crc >>= 8
-    return res
-
-def getSizeOfTrailingDataEntries(ptr, size, flags):
-    def getSizeOfTrailingDataEntry(ptr, size):
-        bitpos, result = 0, 0
-        if size <= 0:
-            return result
-        while True:
-            v = ord(ptr[size-1])
-            result |= (v & 0x7F) << bitpos
-            bitpos += 7
-            size -= 1
-            if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
-                return result
-    num = 0
-    testflags = flags >> 1
-    while testflags:
-        if testflags & 1:
-            num += getSizeOfTrailingDataEntry(ptr, size - num)
-        testflags >>= 1
-    # Check the low bit to see if there's multibyte data present.
-    # if multibyte data is included in the encryped data, we'll
-    # have already cleared this flag.
-    if flags & 1:
-        num += (ord(ptr[size - num - 1]) & 0x3) + 1
-    return num
-
-
-
-class MobiBook:
-    def loadSection(self, section):
-        if (section + 1 == self.num_sections):
-            endoff = len(self.data_file)
-        else:
-            endoff = self.sections[section + 1][0]
-        off = self.sections[section][0]
-        return self.data_file[off:endoff]
-
-    def __init__(self, infile):
-        # initial sanity check on file
-        self.data_file = file(infile, 'rb').read()
-        self.header = self.data_file[0:78]
-        if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
-            raise DrmException("invalid file format")
-        self.magic = self.header[0x3C:0x3C+8]
-        self.crypto_type = -1
-
-        # build up section offset and flag info
-        self.num_sections, = struct.unpack('>H', self.header[76:78])
-        self.sections = []
-        for i in xrange(self.num_sections):
-            offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.data_file[78+i*8:78+i*8+8])
-            flags, val = a1, a2<<16|a3<<8|a4
-            self.sections.append( (offset, flags, val) )
-
-        # parse information from section 0
-        self.sect = self.loadSection(0)
-        self.records, = struct.unpack('>H', self.sect[0x8:0x8+2])
-        self.compression, = struct.unpack('>H', self.sect[0x0:0x0+2])
-
-        if self.magic == 'TEXtREAd':
-            print "Book has format: ", self.magic
-            self.extra_data_flags = 0
-            self.mobi_length = 0
-            self.mobi_version = -1
-            self.meta_array = {}
-            return
-        self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
-        self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
-        print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
-        self.extra_data_flags = 0
-        if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
-            self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
-            print "Extra Data Flags = %d" % self.extra_data_flags
-        if (self.mobi_version < 7) and (self.compression != 17480):
-            # multibyte utf8 data is included in the encryption for mobi_version 6 and below
-            # so clear that byte so that we leave it to be decrypted.
-            self.extra_data_flags &= 0xFFFE
-
-        # if exth region exists parse it for metadata array
-        self.meta_array = {}
-        try:
-            exth_flag, = struct.unpack('>L', self.sect[0x80:0x84])
-            exth = 'NONE'
-            if exth_flag & 0x40:
-                exth = self.sect[16 + self.mobi_length:]
-            if (len(exth) >= 4) and (exth[:4] == 'EXTH'):
-                nitems, = struct.unpack('>I', exth[8:12])
-                pos = 12
-                for i in xrange(nitems):
-                    type, size = struct.unpack('>II', exth[pos: pos + 8])
-                    content = exth[pos + 8: pos + size]
-                    self.meta_array[type] = content
-                    # reset the text to speech flag and clipping limit, if present
-                    if type == 401 and size == 9:
-                        # set clipping limit to 100%
-                        self.patchSection(0, "\144", 16 + self.mobi_length + pos + 8)
-                    elif type == 404 and size == 9:
-                        # make sure text to speech is enabled
-                        self.patchSection(0, "\0", 16 + self.mobi_length + pos + 8)
-                    # print type, size, content, content.encode('hex')
-                    pos += size
-        except:
-            self.meta_array = {}
-            pass
-            
-    def getBookTitle(self):
-        title = ''
-        if 503 in self.meta_array:
-            title = self.meta_array[503]
-        else :
-            toff, tlen = struct.unpack('>II', self.sect[0x54:0x5c])
-            tend = toff + tlen
-            title = self.sect[toff:tend]
-        if title == '':
-            title = self.header[:32]
-            title = title.split("\0")[0]
-        return title
-
-    def getPIDMetaInfo(self):
-        rec209 = ''
-        token = ''
-        if 209 in self.meta_array:
-            rec209 = self.meta_array[209]
-            data = rec209
-            # The 209 data comes in five byte groups. Interpret the last four bytes
-            # of each group as a big endian unsigned integer to get a key value
-            # if that key exists in the meta_array, append its contents to the token
-            for i in xrange(0,len(data),5):
-                val,  = struct.unpack('>I',data[i+1:i+5])
-                sval = self.meta_array.get(val,'')
-                token += sval
-        return rec209, token
-
-    def patch(self, off, new):
-        self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
-
-    def patchSection(self, section, new, in_off = 0):
-        if (section + 1 == self.num_sections):
-            endoff = len(self.data_file)
-        else:
-            endoff = self.sections[section + 1][0]
-        off = self.sections[section][0]
-        assert off + in_off + len(new) <= endoff
-        self.patch(off + in_off, new)
-
-    def parseDRM(self, data, count, pidlist):
-        found_key = None
-        keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
-        for pid in pidlist:
-            bigpid = pid.ljust(16,'\0')
-            temp_key = PC1(keyvec1, bigpid, False)
-            temp_key_sum = sum(map(ord,temp_key)) & 0xff
-            found_key = None
-            for i in xrange(count):
-                verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
-                if cksum == temp_key_sum:
-                    cookie = PC1(temp_key, cookie)
-                    ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
-                    if verification == ver and (flags & 0x1F) == 1:
-                        found_key = finalkey
-                        break
-            if found_key != None:
-                break
-        if not found_key:
-            # Then try the default encoding that doesn't require a PID
-            pid = "00000000"
-            temp_key = keyvec1
-            temp_key_sum = sum(map(ord,temp_key)) & 0xff
-            for i in xrange(count):
-                verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
-                if cksum == temp_key_sum:
-                    cookie = PC1(temp_key, cookie)
-                    ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
-                    if verification == ver:
-                        found_key = finalkey
-                        break
-        return [found_key,pid]
-
-    def processBook(self, pidlist):
-        crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
-        print 'Crypto Type is: ', crypto_type
-        self.crypto_type = crypto_type
-        if crypto_type == 0:
-            print "This book is not encrypted."
-            return self.data_file
-        if crypto_type != 2 and crypto_type != 1:
-            raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
-
-        goodpids = []
-        for pid in pidlist:
-            if len(pid)==10:
-                if checksumPid(pid[0:-2]) != pid:
-                    print "Warning: PID " + pid + " has incorrect checksum, should have been "+checksumPid(pid[0:-2])
-                goodpids.append(pid[0:-2])
-            elif len(pid)==8:
-                goodpids.append(pid)
-
-        if self.crypto_type == 1:
-            t1_keyvec = "QDCVEPMU675RUBSZ"
-            if self.magic == 'TEXtREAd':
-                bookkey_data = self.sect[0x0E:0x0E+16]
-            elif self.mobi_version < 0:
-                bookkey_data = self.sect[0x90:0x90+16] 
-            else:
-                bookkey_data = self.sect[self.mobi_length+16:self.mobi_length+32] 
-            pid = "00000000"
-            found_key = PC1(t1_keyvec, bookkey_data)
-        else :
-            # calculate the keys
-            drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', self.sect[0xA8:0xA8+16])
-            if drm_count == 0:
-                raise DrmException("Not yet initialised with PID. Must be opened with Mobipocket Reader first.")
-            found_key, pid = self.parseDRM(self.sect[drm_ptr:drm_ptr+drm_size], drm_count, goodpids)
-            if not found_key:
-                raise DrmException("No key found. Most likely the correct PID has not been given.")
-            # kill the drm keys
-            self.patchSection(0, "\0" * drm_size, drm_ptr)
-            # kill the drm pointers
-            self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
-            
-        if pid=="00000000":
-            print "File has default encryption, no specific PID."
-        else:
-            print "File is encoded with PID "+checksumPid(pid)+"."
-
-        # clear the crypto type
-        self.patchSection(0, "\0" * 2, 0xC)
-
-        # decrypt sections
-        print "Decrypting. Please wait . . .",
-        new_data = self.data_file[:self.sections[1][0]]
-        for i in xrange(1, self.records+1):
-            data = self.loadSection(i)
-            extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
-            if i%100 == 0:
-                print ".",
-            # print "record %d, extra_size %d" %(i,extra_size)
-            new_data += PC1(found_key, data[0:len(data) - extra_size])
-            if extra_size > 0:
-                new_data += data[-extra_size:]
-        if self.num_sections > self.records+1:
-            new_data += self.data_file[self.sections[self.records+1][0]:]
-        self.data_file = new_data
-        print "done"
-        return self.data_file
-
-def getUnencryptedBook(infile,pid):
-    if not os.path.isfile(infile):
-        raise DrmException('Input File Not Found')
-    book = MobiBook(infile)
-    return book.processBook([pid])
-
-def getUnencryptedBookWithList(infile,pidlist):
-    if not os.path.isfile(infile):
-        raise DrmException('Input File Not Found')
-    book = MobiBook(infile)
-    return book.processBook(pidlist)
-
-def main(argv=sys.argv):
-    print ('MobiDeDrm v%(__version__)s. '
-	   'Copyright 2008-2010 The Dark Reverser.' % globals())
-    if len(argv)<3 or len(argv)>4:
-        print "Removes protection from Mobipocket books"
-        print "Usage:"
-        print "    %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
-        return 1
-    else:
-        infile = argv[1]
-        outfile = argv[2]
-        if len(argv) is 4:
-        	pidlist = argv[3].split(',')
-        else:
-        	pidlist = {}
-        try:
-            stripped_file = getUnencryptedBookWithList(infile, pidlist)
-            file(outfile, 'wb').write(stripped_file)
-        except DrmException, e:
-            print "Error: %s" % e
-            return 1
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

KindleBooks_Tools/Kindle_4_Mac_Unswindle/K4Munswindle.pyw

@@ -1,299 +0,0 @@
-#!/usr/bin/env python
-# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-
-import sys
-sys.path.append('lib')
-import os, os.path, urllib
-import subprocess
-from subprocess import Popen, PIPE, STDOUT
-import subasyncio
-from subasyncio import Process
-import Tkinter
-import Tkconstants
-import tkFileDialog
-import tkMessageBox
-from scrolltextwidget import ScrolledText
-import binascii
-import hashlib
-
-
-#
-# Returns the SHA1 digest of "message"
-#
-def SHA1(message):
-    ctx = hashlib.sha1()
-    ctx.update(message)
-    return ctx.hexdigest()
-
-
-class MainDialog(Tkinter.Frame):
-    def __init__(self, root):
-        Tkinter.Frame.__init__(self, root, border=5)
-        self.root = root
-        self.interval = 2000
-        self.p2 = None
-        self.status = Tkinter.Label(self, text='Remove Encryption from Kindle for Mac Mobi eBook')
-        self.status.pack(fill=Tkconstants.X, expand=1)
-        body = Tkinter.Frame(self)
-        body.pack(fill=Tkconstants.X, expand=1)
-        sticky = Tkconstants.E + Tkconstants.W
-        body.grid_columnconfigure(1, weight=2)
-
-        Tkinter.Label(body, text='Locate your Kindle Applications').grid(row=0, sticky=Tkconstants.E)
-        self.k4mpath = Tkinter.Entry(body, width=50)
-        self.k4mpath.grid(row=0, column=1, sticky=sticky)
-        self.appname = '/Applications/Kindle for Mac.app'
-        if not os.path.exists(self.appname):
-            self.appname = '/Applications/Kindle.app'
-        cwd = self.appname
-        cwd = cwd.encode('utf-8')
-        self.k4mpath.insert(0, cwd)
-        button = Tkinter.Button(body, text="...", command=self.get_k4mpath)
-        button.grid(row=0, column=2)
-
-        Tkinter.Label(body, text='Directory for Unencrypted Output File').grid(row=1, sticky=Tkconstants.E)
-        self.outpath = Tkinter.Entry(body, width=50)
-        self.outpath.grid(row=1, column=1, sticky=sticky)
-        desktoppath = os.getenv('HOME') + '/Desktop/'
-        desktoppath = desktoppath.encode('utf-8')
-        self.outpath.insert(0, desktoppath)
-        button = Tkinter.Button(body, text="...", command=self.get_outpath)
-        button.grid(row=1, column=2)
-
-        msg1 = 'Conversion Log \n\n'
-        self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
-        self.stext.grid(row=3, column=0, columnspan=2,sticky=sticky)
-        self.stext.insert(Tkconstants.END,msg1)
-
-        buttons = Tkinter.Frame(self)
-        buttons.pack()
-        self.sbotton = Tkinter.Button(
-            buttons, text="Start", width=10, command=self.convertit)
-        self.sbotton.pack(side=Tkconstants.LEFT)
-
-        Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
-        self.qbutton = Tkinter.Button(
-            buttons, text="Quit", width=10, command=self.quitting)
-        self.qbutton.pack(side=Tkconstants.RIGHT)
-
-    # read from subprocess pipe without blocking
-    # invoked every interval via the widget "after"
-    # option being used, so need to reset it for the next time
-    def processPipe(self):
-        poll = self.p2.wait('nowait')
-        if poll != None: 
-            text = self.p2.readerr()
-            text += self.p2.read()
-            msg = text + '\n\n' + 'Encryption successfully removed\n'
-            if poll != 0:
-                msg = text + '\n\n' + 'Error: Encryption Removal Failed\n'
-            self.showCmdOutput(msg)
-            self.p2 = None
-            self.sbotton.configure(state='normal')
-            return
-        text = self.p2.readerr()
-        text += self.p2.read()
-        self.showCmdOutput(text)
-        # make sure we get invoked again by event loop after interval 
-        self.stext.after(self.interval,self.processPipe)
-        return
-
-    # post output from subprocess in scrolled text widget
-    def showCmdOutput(self, msg):
-        if msg and msg !='':
-            msg = msg.encode('utf-8')
-            self.stext.insert(Tkconstants.END,msg)
-            self.stext.yview_pickplace(Tkconstants.END)
-        return
-
-    # run as a subprocess via pipes and collect stdout
-    def mobirdr(self, infile, outfile, pidnum):
-        cmdline = 'python ./lib/mobidedrm.py "' + infile + '" "' + outfile + '" "' + pidnum + '"'
-        cmdline = cmdline.encode(sys.getfilesystemencoding())
-        p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
-        return p2
-
-    def get_k4mpath(self):
-        k4mpath = tkFileDialog.askopenfilename(
-            parent=None, title='Select Your Kindle Application',
-            defaultextension='.app', filetypes=[('Kindle for Mac Application', '.app')])
-
-        if k4mpath:
-            k4mpath = os.path.normpath(k4mpath)
-            self.k4mpath.delete(0, Tkconstants.END)
-            self.k4mpath.insert(0, k4mpath)
-        return
-
-    def get_outpath(self):
-        cwd = os.getcwdu()
-        cwd = cwd.encode('utf-8')
-        outpath = tkFileDialog.askdirectory(
-            parent=None, title='Directory to Put Non-DRM eBook into',
-            initialdir=cwd, initialfile=None)
-        if outpath:
-            outpath = os.path.normpath(outpath)
-            self.outpath.delete(0, Tkconstants.END)
-            self.outpath.insert(0, outpath)
-        return
-
-    def quitting(self):
-        # kill any still running subprocess
-        if self.p2 != None:
-            if (self.p2.wait('nowait') == None):
-                self.p2.terminate()
-        self.root.destroy()
-
-    # run as a gdb subprocess via pipes and collect stdout
-    def gdbrdr(self, k4mappfile, gdbcmds):
-        cmdline = '/usr/bin/gdb -q -silent -readnow -batch -x ' +  gdbcmds + ' "' + k4mappfile + '"'
-        cmdline = cmdline.encode(sys.getfilesystemencoding())
-        p3 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
-        poll = p3.wait('wait')
-        results = p3.read()
-        pidnum = 'NOTAPID+'
-        topazbook = 0
-        bookpath = 'book not found'
-        # parse the gdb results to get the last pid and the last azw/prc file name in the gdb listing
-        reslst = results.split('\n')
-        cnt = len(reslst)
-        for j in xrange(cnt):
-            resline = reslst[j]
-            pp = resline.find('PID is ')
-            if pp == 0:
-                pidnum = resline[7:]
-                topazbook = 0
-            if pp > 0:
-                pidnum = resline[13:]
-                topazbook = 1
-            fp = resline.find('File is ')
-            if fp >= 0:
-                tp1 = resline.find('.azw')
-                tp2 = resline.find('.prc')
-                tp3 = resline.find('.mbp')
-                if tp1 >= 0 or tp2 >= 0:
-                    bookpath = resline[8:]
-                if tp3 >= 0 and topazbook == 1:
-                    bookpath = resline[8:-3]
-                    bookpath += 'azw'
-        # put code here to get pid and file name
-        return pidnum, bookpath, topazbook
-
-    # convert from 8 digit PID to proper 10 digit PID
-    def checksumPid(self, s):
-        letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
-        crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
-        crc = crc ^ (crc >> 16)
-        res = s
-        l = len(letters)
-        for i in (0,1):
-            b = crc & 0xff
-            pos = (b // l) ^ (b % l)
-            res += letters[pos%l]
-            crc >>= 8
-        return res
-
-    # start the process
-    def convertit(self):
-        # dictionary of all known Kindle for Mac Binaries
-        sha1_app_digests = {
-            'e197ed2171ceb44a35c24bd30263b7253331694f' : 'gdb_kindle_cmds_r1.txt',
-            '4f702436171f84acc13bdf9f94fae91525aecef5' : 'gdb_kindle_cmds_r2.txt',
-            '4981b7eb37ccf0b8f63f56e8024b5ab593e8a97c' : 'gdb_kindle_cmds_r3.txt',
-            '82909f0545688f09343e2c8fd8521eeee37d2de6' : 'gdb_kindle_cmds_r4.txt',
-            'e260e3515cd525cd085c70baa6e42e08079edbcd' : 'gdb_kindle_cmds_r4.txt',
-            'no_sha1_digest_key_here_________________' : 'no_gdb_kindle_cmds.txt',
-        }
-        # now disable the button to prevent multiple launches
-        self.sbotton.configure(state='disabled')
-
-        k4mpath = self.k4mpath.get()
-        outpath = self.outpath.get()
-
-        # basic error checking
-        if not k4mpath or not os.path.exists(k4mpath):
-            self.status['text'] = 'Error: Specified Kindle for Mac Application does not exist'
-            self.sbotton.configure(state='normal')
-            return
-        if not outpath:
-            self.status['text'] = 'Error: No output directory specified'
-            self.sbotton.configure(state='normal')
-            return
-        if not os.path.isdir(outpath):
-            self.status['text'] = 'Error specified outputdirectory does not exist'
-            self.sbotton.configure(state='normal')
-            return
-        if not os.path.isfile('/usr/bin/gdb'):
-            self.status['text'] = 'Error: gdb does not exist, install the XCode Develoepr Tools'
-            self.sbotton.configure(state='normal')
-            return
-
-
-        # now check if the K4M app binary is known and if so which gdbcmds to use
-        binary_app_file = k4mpath + '/Contents/MacOS/Kindle for Mac'
-        if not os.path.exists(binary_app_file):
-            binary_app_file = k4mpath + '/Contents/MacOS/Kindle'
-
-        k4mpath = binary_app_file
-
-        digest = SHA1(file(binary_app_file, 'rb').read())
-
-        # print digest
-        gdbcmds = None
-        if digest in sha1_app_digests:
-            gdbcmds = sha1_app_digests[digest]
-        else :
-            self.status['text'] = 'Error: Kindle Application does not match any known version, sha1sum is ' + digest
-            self.sbotton.configure(state='normal')
-            return
-
-        # run Kindle for Mac in gdb to get what we need
-        (pidnum, bookpath, topazbook) = self.gdbrdr(k4mpath, gdbcmds)
-
-        if topazbook == 1:
-            log = 'Warning: ' + bookpath + ' is a Topaz book\n'
-            log += '\n\n'
-            log += 'To convert this book please use the Topaz Tools\n'
-            log += 'With the 8 digit PID: "' + pidnum + '"\n'
-            log += '\n\n'
-            log = log.encode('utf-8')
-            self.stext.insert(Tkconstants.END,log)
-            self.sbotton.configure(state='normal')
-            return
-
-        pidnum = self.checksumPid(pidnum)
-
-        # default output file name to be input file name + '_nodrm.mobi'
-        initname = os.path.splitext(os.path.basename(bookpath))[0]
-        initname += '_nodrm.mobi' 
-        outpath += '/' + initname
-
-        log = 'Command = "python mobidedrm.py"\n'
-        log += 'Mobi Path = "'+ bookpath + '"\n'
-        log += 'Output file = "' + outpath + '"\n'
-        log += 'PID = "' + pidnum + '"\n'
-        log += '\n\n'
-        log += 'Please Wait ...\n\n'
-        log = log.encode('utf-8')
-        self.stext.insert(Tkconstants.END,log)
-        self.p2 = self.mobirdr(bookpath, outpath, pidnum)
-
-        # python does not seem to allow you to create
-        # your own eventloop which every other gui does - strange 
-        # so need to use the widget "after" command to force
-        # event loop to run non-gui events every interval
-        self.stext.after(self.interval,self.processPipe)
-        return
-
-
-def main(argv=None):
-    root = Tkinter.Tk()
-    root.title('Kindle for Mac eBook Encryption Removal')
-    root.resizable(True, False)
-    root.minsize(300, 0)
-    MainDialog(root).pack(fill=Tkconstants.X, expand=1)
-    root.mainloop()
-    return 0
-    
-
-if __name__ == "__main__":
-    sys.exit(main())

KindleBooks_Tools/Kindle_4_Mac_Unswindle/README_K4Munswindle.txt

@@ -1,61 +0,0 @@
-K4Munswindle
-
-Prerequisites:
-
-   - Kindle for Mac.app Version 1.0.0 Beta 1 (27214)
-	or
-     Kindle.app Version 1.2.0 (30689)
-        or
-     Kindle.app Version 1.2.1 (30781)
-     	or
-     Kindle.app Version 1.2.2 (30814)
-     (this is now the current version)
-
-   - A **recent** version of the XCode Developer Tools **must** be Installed 
-    (see your latest Mac OS X Install Disk for the installer, and then use Apple System Updates)
-
-***PLEASE REMEMBER to UNCHECK the "auto updates" in the Kindle.app Preferences!
-***otherwise it will always update and K4MUnswindle will stop working
-
-
-The directions for use are:
-
-1. double-click on K4Munswindle.pyw
-
-In the window that opens:
-
-– hit the first '...' button to locate your Kindle Application 
-     if it is not in /Applications
-
-– hit the second '...' button to select an output directory 
-      (defaults to your Desktop)
-
-– hit the 'Start' button
-
-After a short delay, your Kindle application should open up automagically
-
-2. In Kindle for Mac:
-
- - hit the  “Home” button to go home. 
-
- - double-click on ONE of your books.
-   This should open the book.
-
-3. Once the book you want is open
-
--  hit the “Home” button and then exit the Kindle for Mac application
-
-4. Once you have exited the Kindle for Mac application you should see one of the following:
-
-  - If the book you selected was a Topaz Book:
-
-      A Warning message will appear in the Conversion Log indicating 
-      that the book you opened was Topaz, along with the 8 digit PID 
-      needed to convert it using Topaz_Tools
-
-  - If the book you selected was a Mobi book:
-
-      MobiDeDRM will be automagically started in the Conversion Log 
-      window and if successful you should find your decoded book in 
-      the output directory.
-

KindleBooks_Tools/Kindle_4_Mac_Unswindle/gdb_kindle_cmds_r1.txt

@@ -1,13 +0,0 @@
-set verbose 0
-break * 0x00b2a56a
-commands 1
-printf "PID is %s\n", $edx
-continue
-end
-break * 0x014ca2af
-commands 2
-printf "File is %s\n", $eax
-continue
-end
-condition 2 $eax != 0
-run

KindleBooks_Tools/Kindle_4_Mac_Unswindle/gdb_kindle_cmds_r2.txt

@@ -1,18 +0,0 @@
-set verbose 0
-break * 0x00e37be4
-commands 1
-printf "PID is %s\n", $eax
-continue
-end
-break * 0x0142cd94
-commands 2
-printf "File is %s\n", $eax
-continue
-end
-condition 2 $eax != 0
-break * 0x01009c88
-commands 3
-printf "TOPAZ PID is %s\n", *(long*)($esp+12)
-continue
-end
-run

KindleBooks_Tools/Kindle_4_Mac_Unswindle/gdb_kindle_cmds_r3.txt

@@ -1,18 +0,0 @@
-set verbose 0
-break * 0x00d3dac4
-commands 1
-printf "PID is %s\n", $eax
-continue
-end
-break * 0x0130a384
-commands 2
-printf "File is %s\n", $eax
-continue
-end
-condition 2 $eax != 0
-break * 0x00f0f306
-commands 3
-printf "TOPAZ PID is %s\n", *(long*)($esp+12)
-continue
-end
-run

KindleBooks_Tools/Kindle_4_Mac_Unswindle/gdb_kindle_cmds_r4.txt

@@ -1,18 +0,0 @@
-set verbose 0
-break * 0x00d8f72a
-commands 1
-printf "PID is %s\n", *(long*)($esp+4)
-continue
-end
-break * 0x0127498c
-commands 2
-printf "File is %s\n", $eax
-continue
-end
-condition 2 $eax != 0
-break * 0x00e9aec0
-commands 3
-printf "TOPAZ PID is %s\n", **(long**)($esp+8)
-continue
-end
-run

KindleBooks_Tools/Kindle_4_Mac_Unswindle/lib/mobidedrm.py

@@ -1,409 +0,0 @@
-#!/usr/bin/python
-#
-# This is a python script. You need a Python interpreter to run it.
-# For example, ActiveState Python, which exists for windows.
-#
-# Changelog
-#  0.01 - Initial version
-#  0.02 - Huffdic compressed books were not properly decrypted
-#  0.03 - Wasn't checking MOBI header length
-#  0.04 - Wasn't sanity checking size of data record
-#  0.05 - It seems that the extra data flags take two bytes not four
-#  0.06 - And that low bit does mean something after all :-)
-#  0.07 - The extra data flags aren't present in MOBI header < 0xE8 in size
-#  0.08 - ...and also not in Mobi header version < 6
-#  0.09 - ...but they are there with Mobi header version 6, header size 0xE4!
-#  0.10 - Outputs unencrypted files as-is, so that when run as a Calibre
-#         import filter it works when importing unencrypted files.
-#         Also now handles encrypted files that don't need a specific PID.
-#  0.11 - use autoflushed stdout and proper return values
-#  0.12 - Fix for problems with metadata import as Calibre plugin, report errors
-#  0.13 - Formatting fixes: retabbed file, removed trailing whitespace
-#         and extra blank lines, converted CR/LF pairs at ends of each line,
-#         and other cosmetic fixes.
-#  0.14 - Working out when the extra data flags are present has been problematic
-#         Versions 7 through 9 have tried to tweak the conditions, but have been
-#         only partially successful. Closer examination of lots of sample
-#         files reveals that a confusion has arisen because trailing data entries
-#         are not encrypted, but it turns out that the multibyte entries
-#         in utf8 file are encrypted. (Although neither kind gets compressed.)
-#         This knowledge leads to a simplification of the test for the 
-#         trailing data byte flags - version 5 and higher AND header size >= 0xE4. 
-#  0.15 - Now outputs 'heartbeat', and is also quicker for long files.
-#  0.16 - And reverts to 'done' not 'done.' at the end for unswindle compatibility.
-#  0.17 - added modifications to support its use as an imported python module
-#         both inside calibre and also in other places (ie K4DeDRM tools)
-#  0.17a- disabled the standalone plugin feature since a plugin can not import
-#         a plugin
-#  0.18 - It seems that multibyte entries aren't encrypted in a v7 file...
-#         Removed the disabled Calibre plug-in code
-#         Permit use of 8-digit PIDs
-#  0.19 - It seems that multibyte entries aren't encrypted in a v6 file either.
-#  0.20 - Correction: It seems that multibyte entries are encrypted in a v6 file.
-#  0.21 - Added support for multiple pids
-#  0.22 - revised structure to hold MobiBook as a class to allow an extended interface
-#  0.23 - fixed problem with older files with no EXTH section 
-#  0.24 - add support for type 1 encryption and 'TEXtREAd' books as well
-#  0.25 - Fixed support for 'BOOKMOBI' type 1 encryption
-#  0.26 - Now enables Text-To-Speech flag and sets clipping limit to 100%
-#  0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
-#  0.28 - slight additional changes to metadata token generation (None -> '')
-#  0.29 - It seems that the ideas about when multibyte trailing characters were
-#         included in the encryption were wrong. They aren't for DOC compressed
-#         files, but they are for HUFF/CDIC compress files!
-
-__version__ = '0.29'
-
-import sys
-
-class Unbuffered:
-    def __init__(self, stream):
-        self.stream = stream
-    def write(self, data):
-        self.stream.write(data)
-        self.stream.flush()
-    def __getattr__(self, attr):
-        return getattr(self.stream, attr)
-sys.stdout=Unbuffered(sys.stdout)
-
-import os
-import struct
-import binascii
-
-class DrmException(Exception):
-    pass
-
-
-#
-# MobiBook Utility Routines
-#
-
-# Implementation of Pukall Cipher 1
-def PC1(key, src, decryption=True):
-    sum1 = 0;
-    sum2 = 0;
-    keyXorVal = 0;
-    if len(key)!=16:
-        print "Bad key length!"
-        return None
-    wkey = []
-    for i in xrange(8):
-        wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
-    dst = ""
-    for i in xrange(len(src)):
-        temp1 = 0;
-        byteXorVal = 0;
-        for j in xrange(8):
-            temp1 ^= wkey[j]
-            sum2  = (sum2+j)*20021 + sum1
-            sum1  = (temp1*346)&0xFFFF
-            sum2  = (sum2+sum1)&0xFFFF
-            temp1 = (temp1*20021+1)&0xFFFF
-            byteXorVal ^= temp1 ^ sum2
-        curByte = ord(src[i])
-        if not decryption:
-            keyXorVal = curByte * 257;
-        curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
-        if decryption:
-            keyXorVal = curByte * 257;
-        for j in xrange(8):
-            wkey[j] ^= keyXorVal;
-        dst+=chr(curByte)
-    return dst
-
-def checksumPid(s):
-    letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
-    crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
-    crc = crc ^ (crc >> 16)
-    res = s
-    l = len(letters)
-    for i in (0,1):
-        b = crc & 0xff
-        pos = (b // l) ^ (b % l)
-        res += letters[pos%l]
-        crc >>= 8
-    return res
-
-def getSizeOfTrailingDataEntries(ptr, size, flags):
-    def getSizeOfTrailingDataEntry(ptr, size):
-        bitpos, result = 0, 0
-        if size <= 0:
-            return result
-        while True:
-            v = ord(ptr[size-1])
-            result |= (v & 0x7F) << bitpos
-            bitpos += 7
-            size -= 1
-            if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
-                return result
-    num = 0
-    testflags = flags >> 1
-    while testflags:
-        if testflags & 1:
-            num += getSizeOfTrailingDataEntry(ptr, size - num)
-        testflags >>= 1
-    # Check the low bit to see if there's multibyte data present.
-    # if multibyte data is included in the encryped data, we'll
-    # have already cleared this flag.
-    if flags & 1:
-        num += (ord(ptr[size - num - 1]) & 0x3) + 1
-    return num
-
-
-
-class MobiBook:
-    def loadSection(self, section):
-        if (section + 1 == self.num_sections):
-            endoff = len(self.data_file)
-        else:
-            endoff = self.sections[section + 1][0]
-        off = self.sections[section][0]
-        return self.data_file[off:endoff]
-
-    def __init__(self, infile):
-        # initial sanity check on file
-        self.data_file = file(infile, 'rb').read()
-        self.header = self.data_file[0:78]
-        if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
-            raise DrmException("invalid file format")
-        self.magic = self.header[0x3C:0x3C+8]
-        self.crypto_type = -1
-
-        # build up section offset and flag info
-        self.num_sections, = struct.unpack('>H', self.header[76:78])
-        self.sections = []
-        for i in xrange(self.num_sections):
-            offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.data_file[78+i*8:78+i*8+8])
-            flags, val = a1, a2<<16|a3<<8|a4
-            self.sections.append( (offset, flags, val) )
-
-        # parse information from section 0
-        self.sect = self.loadSection(0)
-        self.records, = struct.unpack('>H', self.sect[0x8:0x8+2])
-        self.compression, = struct.unpack('>H', self.sect[0x0:0x0+2])
-
-        if self.magic == 'TEXtREAd':
-            print "Book has format: ", self.magic
-            self.extra_data_flags = 0
-            self.mobi_length = 0
-            self.mobi_version = -1
-            self.meta_array = {}
-            return
-        self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
-        self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
-        print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
-        self.extra_data_flags = 0
-        if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
-            self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
-            print "Extra Data Flags = %d" % self.extra_data_flags
-        if (self.mobi_version < 7) and (self.compression != 17480):
-            # multibyte utf8 data is included in the encryption for mobi_version 6 and below
-            # so clear that byte so that we leave it to be decrypted.
-            self.extra_data_flags &= 0xFFFE
-
-        # if exth region exists parse it for metadata array
-        self.meta_array = {}
-        try:
-            exth_flag, = struct.unpack('>L', self.sect[0x80:0x84])
-            exth = 'NONE'
-            if exth_flag & 0x40:
-                exth = self.sect[16 + self.mobi_length:]
-            if (len(exth) >= 4) and (exth[:4] == 'EXTH'):
-                nitems, = struct.unpack('>I', exth[8:12])
-                pos = 12
-                for i in xrange(nitems):
-                    type, size = struct.unpack('>II', exth[pos: pos + 8])
-                    content = exth[pos + 8: pos + size]
-                    self.meta_array[type] = content
-                    # reset the text to speech flag and clipping limit, if present
-                    if type == 401 and size == 9:
-                        # set clipping limit to 100%
-                        self.patchSection(0, "\144", 16 + self.mobi_length + pos + 8)
-                    elif type == 404 and size == 9:
-                        # make sure text to speech is enabled
-                        self.patchSection(0, "\0", 16 + self.mobi_length + pos + 8)
-                    # print type, size, content, content.encode('hex')
-                    pos += size
-        except:
-            self.meta_array = {}
-            pass
-            
-    def getBookTitle(self):
-        title = ''
-        if 503 in self.meta_array:
-            title = self.meta_array[503]
-        else :
-            toff, tlen = struct.unpack('>II', self.sect[0x54:0x5c])
-            tend = toff + tlen
-            title = self.sect[toff:tend]
-        if title == '':
-            title = self.header[:32]
-            title = title.split("\0")[0]
-        return title
-
-    def getPIDMetaInfo(self):
-        rec209 = ''
-        token = ''
-        if 209 in self.meta_array:
-            rec209 = self.meta_array[209]
-            data = rec209
-            # The 209 data comes in five byte groups. Interpret the last four bytes
-            # of each group as a big endian unsigned integer to get a key value
-            # if that key exists in the meta_array, append its contents to the token
-            for i in xrange(0,len(data),5):
-                val,  = struct.unpack('>I',data[i+1:i+5])
-                sval = self.meta_array.get(val,'')
-                token += sval
-        return rec209, token
-
-    def patch(self, off, new):
-        self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
-
-    def patchSection(self, section, new, in_off = 0):
-        if (section + 1 == self.num_sections):
-            endoff = len(self.data_file)
-        else:
-            endoff = self.sections[section + 1][0]
-        off = self.sections[section][0]
-        assert off + in_off + len(new) <= endoff
-        self.patch(off + in_off, new)
-
-    def parseDRM(self, data, count, pidlist):
-        found_key = None
-        keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
-        for pid in pidlist:
-            bigpid = pid.ljust(16,'\0')
-            temp_key = PC1(keyvec1, bigpid, False)
-            temp_key_sum = sum(map(ord,temp_key)) & 0xff
-            found_key = None
-            for i in xrange(count):
-                verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
-                if cksum == temp_key_sum:
-                    cookie = PC1(temp_key, cookie)
-                    ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
-                    if verification == ver and (flags & 0x1F) == 1:
-                        found_key = finalkey
-                        break
-            if found_key != None:
-                break
-        if not found_key:
-            # Then try the default encoding that doesn't require a PID
-            pid = "00000000"
-            temp_key = keyvec1
-            temp_key_sum = sum(map(ord,temp_key)) & 0xff
-            for i in xrange(count):
-                verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
-                if cksum == temp_key_sum:
-                    cookie = PC1(temp_key, cookie)
-                    ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
-                    if verification == ver:
-                        found_key = finalkey
-                        break
-        return [found_key,pid]
-
-    def processBook(self, pidlist):
-        crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
-        print 'Crypto Type is: ', crypto_type
-        self.crypto_type = crypto_type
-        if crypto_type == 0:
-            print "This book is not encrypted."
-            return self.data_file
-        if crypto_type != 2 and crypto_type != 1:
-            raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
-
-        goodpids = []
-        for pid in pidlist:
-            if len(pid)==10:
-                if checksumPid(pid[0:-2]) != pid:
-                    print "Warning: PID " + pid + " has incorrect checksum, should have been "+checksumPid(pid[0:-2])
-                goodpids.append(pid[0:-2])
-            elif len(pid)==8:
-                goodpids.append(pid)
-
-        if self.crypto_type == 1:
-            t1_keyvec = "QDCVEPMU675RUBSZ"
-            if self.magic == 'TEXtREAd':
-                bookkey_data = self.sect[0x0E:0x0E+16]
-            elif self.mobi_version < 0:
-                bookkey_data = self.sect[0x90:0x90+16] 
-            else:
-                bookkey_data = self.sect[self.mobi_length+16:self.mobi_length+32] 
-            pid = "00000000"
-            found_key = PC1(t1_keyvec, bookkey_data)
-        else :
-            # calculate the keys
-            drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', self.sect[0xA8:0xA8+16])
-            if drm_count == 0:
-                raise DrmException("Not yet initialised with PID. Must be opened with Mobipocket Reader first.")
-            found_key, pid = self.parseDRM(self.sect[drm_ptr:drm_ptr+drm_size], drm_count, goodpids)
-            if not found_key:
-                raise DrmException("No key found. Most likely the correct PID has not been given.")
-            # kill the drm keys
-            self.patchSection(0, "\0" * drm_size, drm_ptr)
-            # kill the drm pointers
-            self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
-            
-        if pid=="00000000":
-            print "File has default encryption, no specific PID."
-        else:
-            print "File is encoded with PID "+checksumPid(pid)+"."
-
-        # clear the crypto type
-        self.patchSection(0, "\0" * 2, 0xC)
-
-        # decrypt sections
-        print "Decrypting. Please wait . . .",
-        new_data = self.data_file[:self.sections[1][0]]
-        for i in xrange(1, self.records+1):
-            data = self.loadSection(i)
-            extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
-            if i%100 == 0:
-                print ".",
-            # print "record %d, extra_size %d" %(i,extra_size)
-            new_data += PC1(found_key, data[0:len(data) - extra_size])
-            if extra_size > 0:
-                new_data += data[-extra_size:]
-        if self.num_sections > self.records+1:
-            new_data += self.data_file[self.sections[self.records+1][0]:]
-        self.data_file = new_data
-        print "done"
-        return self.data_file
-
-def getUnencryptedBook(infile,pid):
-    if not os.path.isfile(infile):
-        raise DrmException('Input File Not Found')
-    book = MobiBook(infile)
-    return book.processBook([pid])
-
-def getUnencryptedBookWithList(infile,pidlist):
-    if not os.path.isfile(infile):
-        raise DrmException('Input File Not Found')
-    book = MobiBook(infile)
-    return book.processBook(pidlist)
-
-def main(argv=sys.argv):
-    print ('MobiDeDrm v%(__version__)s. '
-	   'Copyright 2008-2010 The Dark Reverser.' % globals())
-    if len(argv)<3 or len(argv)>4:
-        print "Removes protection from Mobipocket books"
-        print "Usage:"
-        print "    %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
-        return 1
-    else:
-        infile = argv[1]
-        outfile = argv[2]
-        if len(argv) is 4:
-        	pidlist = argv[3].split(',')
-        else:
-        	pidlist = {}
-        try:
-            stripped_file = getUnencryptedBookWithList(infile, pidlist)
-            file(outfile, 'wb').write(stripped_file)
-        except DrmException, e:
-            print "Error: %s" % e
-            return 1
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

KindleBooks_Tools/Kindle_4_Mac_Unswindle/lib/scrolltextwidget.py

@@ -1,27 +0,0 @@
-#!/usr/bin/env python
-# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-
-import Tkinter
-import Tkconstants
-
-# basic scrolled text widget
-class ScrolledText(Tkinter.Text):
-    def __init__(self, master=None, **kw):
-        self.frame = Tkinter.Frame(master)
-        self.vbar = Tkinter.Scrollbar(self.frame)
-        self.vbar.pack(side=Tkconstants.RIGHT, fill=Tkconstants.Y)
-        kw.update({'yscrollcommand': self.vbar.set})
-        Tkinter.Text.__init__(self, self.frame, **kw)
-        self.pack(side=Tkconstants.LEFT, fill=Tkconstants.BOTH, expand=True)
-        self.vbar['command'] = self.yview
-        # Copy geometry methods of self.frame without overriding Text
-        # methods = hack!
-        text_meths = vars(Tkinter.Text).keys()
-        methods = vars(Tkinter.Pack).keys() + vars(Tkinter.Grid).keys() + vars(Tkinter.Place).keys()
-        methods = set(methods).difference(text_meths)
-        for m in methods:
-            if m[0] != '_' and m != 'config' and m != 'configure':
-                setattr(self, m, getattr(self.frame, m))
-
-    def __str__(self):
-        return str(self.frame)

KindleBooks_Tools/Kindle_4_Mac_Unswindle/lib/subasyncio.py

@@ -1,149 +0,0 @@
-#!/usr/bin/env python
-# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-
-import os, sys
-import signal
-import threading
-import subprocess
-from subprocess import Popen, PIPE, STDOUT
-
-# **heavily** chopped up and modfied version of asyncproc.py
-# to make it actually work on Windows as well as Mac/Linux
-# For the original see:
-# "http://www.lysator.liu.se/~bellman/download/"
-# author is  "Thomas Bellman <bellman@lysator.liu.se>"
-# available under GPL version 3 or Later
-
-# create an asynchronous subprocess whose output can be collected in
-# a non-blocking manner
-
-# What a mess!  Have to use threads just to get non-blocking io
-# in a cross-platform manner
-
-# luckily all thread use is hidden within this class
-
-class Process(object):
-    def __init__(self, *params, **kwparams):
-        if len(params) <= 3:
-            kwparams.setdefault('stdin', subprocess.PIPE)
-        if len(params) <= 4:
-            kwparams.setdefault('stdout', subprocess.PIPE)
-        if len(params) <= 5:
-            kwparams.setdefault('stderr', subprocess.PIPE)
-        self.__pending_input = []
-        self.__collected_outdata = []
-        self.__collected_errdata = []
-        self.__exitstatus = None
-        self.__lock = threading.Lock()
-        self.__inputsem = threading.Semaphore(0)
-        self.__quit = False
-
-        self.__process = subprocess.Popen(*params, **kwparams)
-
-        if self.__process.stdin:
-            self.__stdin_thread = threading.Thread(
-                name="stdin-thread",
-                target=self.__feeder, args=(self.__pending_input,
-                                            self.__process.stdin))
-            self.__stdin_thread.setDaemon(True)
-            self.__stdin_thread.start()
-
-        if self.__process.stdout:
-            self.__stdout_thread = threading.Thread(
-                name="stdout-thread",
-                target=self.__reader, args=(self.__collected_outdata,
-					    self.__process.stdout))
-            self.__stdout_thread.setDaemon(True)
-            self.__stdout_thread.start()
-
-        if self.__process.stderr:
-            self.__stderr_thread = threading.Thread(
-                name="stderr-thread",
-                target=self.__reader, args=(self.__collected_errdata,
-					    self.__process.stderr))
-            self.__stderr_thread.setDaemon(True)
-            self.__stderr_thread.start()
-
-    def pid(self):
-        return self.__process.pid
-
-    def kill(self, signal):
-        self.__process.send_signal(signal)
-
-    # check on subprocess (pass in 'nowait') to act like poll
-    def wait(self, flag):
-        if flag.lower() == 'nowait':
-            rc = self.__process.poll()
-        else:
-            rc = self.__process.wait()
-        if rc != None:
-            if self.__process.stdin:
-                self.closeinput()
-            if self.__process.stdout:
-                self.__stdout_thread.join()
-            if self.__process.stderr:
-                self.__stderr_thread.join()
-        return self.__process.returncode
-
-    def terminate(self):
-        if self.__process.stdin:
-            self.closeinput()
-        self.__process.terminate()
-
-    # thread gets data from subprocess stdout
-    def __reader(self, collector, source):
-        while True:
-            data = os.read(source.fileno(), 65536)
-            self.__lock.acquire()
-            collector.append(data)
-            self.__lock.release()
-            if data == "":
-                source.close()
-                break
-        return
-
-    # thread feeds data to subprocess stdin
-    def __feeder(self, pending, drain):
-        while True:
-            self.__inputsem.acquire()
-            self.__lock.acquire()
-            if not pending  and self.__quit:
-                drain.close()
-                self.__lock.release()
-                break
-            data = pending.pop(0)
-            self.__lock.release()
-            drain.write(data)
-
-    # non-blocking read of data from subprocess stdout
-    def read(self):
-        self.__lock.acquire()
-        outdata = "".join(self.__collected_outdata)
-        del self.__collected_outdata[:]
-        self.__lock.release()
-        return outdata
-
-    # non-blocking read of data from subprocess stderr
-    def readerr(self):
-        self.__lock.acquire()
-        errdata = "".join(self.__collected_errdata)
-        del self.__collected_errdata[:]
-        self.__lock.release()
-        return errdata
-
-    # non-blocking write to stdin of subprocess
-    def write(self, data):
-        if self.__process.stdin is None:
-            raise ValueError("Writing to process with stdin not a pipe")
-        self.__lock.acquire()
-        self.__pending_input.append(data)
-        self.__inputsem.release()
-        self.__lock.release()
-
-    # close stdinput of subprocess
-    def closeinput(self):
-        self.__lock.acquire()
-        self.__quit = True
-        self.__inputsem.release()
-        self.__lock.release()
-

KindleBooks_Tools/Kindle_4_PC_Unswindle/README-unswindlev7.txt

@@ -1,5 +0,0 @@
-README
-
-unswindle can be used to find the book specific PID but it needs to be updated for each version of Kindle4PC that Amazon releases (and therefore is also useful for Linux users who have Wine). This program “patches” the Kindle4PC executable and therefore is very release specific.
-
-Unfortunately unswindle v7 the latest, has not been updated to work with the latest version of Kindle for PC.  You will need to find one of the older versions of Kindle4PC and prevent later updates in order to use this tool.