whitespace and some unicode/bytes

Minor changes.

.gitignore

@@ -0,0 +1 @@
+.DS_Store

DeDRM_plugin/__init__.py

@@ -5,7 +5,7 @@
 # Copyright © 2008-2020 Apprentice Harper et al.
 
 __license__   = 'GPL v3'
-__version__ = '7.0.0'
+__version__ = '7.2.1'
 __docformat__ = 'restructuredtext en'
 
 
@@ -69,15 +69,21 @@ __docformat__ = 'restructuredtext en'
 #   6.6.3 - More cleanup of kindle book names and start of support for .kinf2018
 #   6.7.0 - Handle new library in calibre.
 #   6.8.0 - Full support for .kinf2018 and new KFX encryption (Kindle for PC/Mac 2.5+)
-#   6.8.1 - Kindle key fix for Mac OS X Big Syr
-#   7.0.0 - Switched to Python 3 for calibre 5.0. Thanks to all who comtibuted
+#   6.8.1 - Kindle key fix for Mac OS X Big Sur
+#   7.0.0 - Switched to Python 3 for calibre 5.0. Thanks to all who contributed
+#   7.0.1 - More Python 3 changes. Adobe PDF decryption should now work in some cases
+#   7.0.2 - More Python 3 changes. Adobe PDF decryption should now work on PC too.
+#   7.0.3 - More Python 3 changes. Integer division in ineptpdf.py
+#   7.1.0 - Full release for calibre 5.x
+#   7.2.0 - Update for latest KFX changes, and Python 3 Obok fixes.
+#   7.2.1 - Whitespace!
 
 """
 Decrypt DRMed ebooks.
 """
 
 PLUGIN_NAME = "DeDRM"
-PLUGIN_VERSION_TUPLE = (7, 0, 0)
+PLUGIN_VERSION_TUPLE = tuple([int(x) for x in __version__.split(".")])
 PLUGIN_VERSION = ".".join([str(x)for x in PLUGIN_VERSION_TUPLE])
 # Include an html helpfile in the plugin's zipfile with the following name.
 RESOURCE_NAME = PLUGIN_NAME + '_Help.htm'
@@ -421,7 +427,7 @@ class DeDRM(FileTypePlugin):
         # Attempt to decrypt epub with each encryption key (generated or provided).
         print("{0} v{1}: {2} is a PDF ebook".format(PLUGIN_NAME, PLUGIN_VERSION, os.path.basename(path_to_ebook)))
         for keyname, userkeyhex in dedrmprefs['adeptkeys'].items():
-            userkey = userkeyhex.decode('hex')
+            userkey = codecs.decode(userkeyhex,'hex')
             print("{0} v{1}: Trying Encryption key {2:s}".format(PLUGIN_NAME, PLUGIN_VERSION, keyname))
             of = self.temporary_file(".pdf")
 
@@ -467,7 +473,7 @@ class DeDRM(FileTypePlugin):
 
         newkeys = []
         for keyvalue in defaultkeys:
-            if keyvalue.encode('hex') not in dedrmprefs['adeptkeys'].values():
+            if codecs.encode(keyvalue,'hex') not in dedrmprefs['adeptkeys'].values():
                 newkeys.append(keyvalue)
 
         if len(newkeys) > 0:
@@ -491,7 +497,7 @@ class DeDRM(FileTypePlugin):
                         # Store the new successful key in the defaults
                         print("{0} v{1}: Saving a new default key".format(PLUGIN_NAME, PLUGIN_VERSION))
                         try:
-                            dedrmprefs.addnamedvaluetoprefs('adeptkeys','default_key',keyvalue.encode('hex'))
+                            dedrmprefs.addnamedvaluetoprefs('adeptkeys','default_key',codecs.encode(keyvalue,'hex'))
                             dedrmprefs.writeprefs()
                             print("{0} v{1}: Saved a new default key after {2:.1f} seconds".format(PLUGIN_NAME, PLUGIN_VERSION,time.time()-self.starttime))
                         except:
@@ -596,7 +602,7 @@ class DeDRM(FileTypePlugin):
             of = self.temporary_file(".pmlz")
 
             # Give the userkey, ebook and TemporaryPersistent file to the decryption function.
-            result = erdr2pml.decryptBook(path_to_ebook, of.name, True, userkey.decode('hex'))
+            result = erdr2pml.decryptBook(path_to_ebook, of.name, True, codecs.decode(userkey,'hex'))
 
             of.close()
 

DeDRM_plugin/adobekey.py

@@ -115,7 +115,9 @@ if iswindows:
 
     def _load_crypto_libcrypto():
         from ctypes.util import find_library
-        libcrypto = find_library('libeay32')
+        libcrypto = find_library('libcrypto-1_1')
+        if libcrypto is None:
+            libcrypto = find_library('libeay32')
         if libcrypto is None:
             raise ADEPTError('libcrypto not found')
         libcrypto = CDLL(libcrypto)

DeDRM_plugin/config.py

@@ -175,7 +175,7 @@ class ConfigWidget(QWidget):
     def load_resource(self, name):
         with ZipFile(self.plugin_path, 'r') as zf:
             if name in zf.namelist():
-                return zf.read(name)
+                return zf.read(name).decode('utf-8')
         return ""
 
 

DeDRM_plugin/flatxml2html.py

@@ -559,7 +559,7 @@ class DocParser(object):
                     if (link > 0):
                         linktype = self.link_type[link-1]
                         title = self.link_title[link-1]
-                        title = title.rstrip(b'. ')
+                        title = title.rstrip(b'. ').decode('utf-8')
                         alt_title = parares[lstart:]
                         alt_title = alt_title.strip()
                         # now strip off the actual printed page number
@@ -770,10 +770,10 @@ class DocParser(object):
                             first_para_continued = False
                         (pclass, pdesc) = self.getParaDescription(start,end, regtype)
                         if not pclass:
-                            if orig_regtype.endswith(b'.right')     : pclass = 'cl-right'
-                            elif orig_regtype.endswith(b'.center')  : pclass = 'cl-center'
-                            elif orig_regtype.endswith(b'.left')    : pclass = 'cl-left'
-                            elif orig_regtype.endswith(b'.justify') : pclass = 'cl-justify'
+                            if orig_regtype.endswith(b'.right')     : pclass = b'cl-right'
+                            elif orig_regtype.endswith(b'.center')  : pclass = b'cl-center'
+                            elif orig_regtype.endswith(b'.left')    : pclass = b'cl-left'
+                            elif orig_regtype.endswith(b'.justify') : pclass = b'cl-justify'
                         if pclass and (ptype == 'full') and (len(pclass) >= 6):
                             tag = 'p'
                             if pclass[3:6] == b'h1-' : tag = 'h4'

DeDRM_plugin/ineptepub.py

@@ -353,12 +353,16 @@ class Decryptor(object):
 
     def decompress(self, bytes):
         dc = zlib.decompressobj(-15)
-        bytes = dc.decompress(bytes)
-        ex = dc.decompress(b'Z') + dc.flush()
-        if ex:
-            bytes = bytes + ex
-        return bytes
-
+        try:
+            decompressed_bytes = dc.decompress(bytes)
+            ex = dc.decompress(b'Z') + dc.flush()
+            if ex:
+                decompressed_bytes = decompressed_bytes + ex
+        except:
+            # possibly not compressed by zip - just return bytes
+            return bytes
+        return decompressed_bytes 
+    
     def decrypt(self, path, data):
         if path.encode('utf-8') in self._encrypted:
             data = self._aes.decrypt(data)[16:]
@@ -411,12 +415,12 @@ def decryptBook(userkey, inpath, outpath):
                 return 1
             bookkey = rsa.decrypt(codecs.decode(bookkey.encode('ascii'), 'base64'))
             # Padded as per RSAES-PKCS1-v1_5
-            if len(bookkey) != 16:
-                if bookkey[-17] != '\x00' and bookkey[-17] != 0:
+            if len(bookkey) > 16:
+                if bookkey[-17] == '\x00' or bookkey[-17] == 0:
+                    bookkey = bookkey[-16:]
+                else:
                     print("Could not decrypt {0:s}. Wrong key".format(os.path.basename(inpath)))
                     return 2
-                else:
-                    bookkey = bookkey[-16:]
             encryption = inf.read('META-INF/encryption.xml')
             decryptor = Decryptor(bookkey, encryption)
             kwds = dict(compression=ZIP_DEFLATED, allowZip64=False)

DeDRM_plugin/ineptpdf.py

@@ -54,12 +54,14 @@ Decrypts Adobe ADEPT-encrypted PDF files.
 __license__ = 'GPL v3'
 __version__ = "9.0.0"
 
+import codecs
 import sys
 import os
 import re
 import zlib
 import struct
 import hashlib
+from io import BytesIO
 from decimal import Decimal
 import itertools
 import xml.etree.ElementTree as etree
@@ -258,7 +260,8 @@ def _load_crypto_pycrypto():
     from Crypto.PublicKey import RSA as _RSA
     from Crypto.Cipher import ARC4 as _ARC4
     from Crypto.Cipher import AES as _AES
-
+    from Crypto.Cipher import PKCS1_v1_5 as _PKCS1_v1_5
+    
     # ASN.1 parsing code from tlslite
     class ASN1Error(Exception):
         pass
@@ -372,7 +375,7 @@ def _load_crypto_pycrypto():
 
     class RSA(object):
         def __init__(self, der):
-            key = ASN1Parser([ord(x) for x in der])
+            key = ASN1Parser([x for x in der])
             key = [key.getChild(x).value for x in range(1, 4)]
             key = [self.bytesToNumber(v) for v in key]
             self._rsa = _RSA.construct(key)
@@ -384,7 +387,7 @@ def _load_crypto_pycrypto():
             return total
 
         def decrypt(self, data):
-            return self._rsa.decrypt(data)
+            return _PKCS1_v1_5.new(self._rsa).decrypt(data, 172)
 
     return (ARC4, RSA, AES)
 
@@ -403,7 +406,6 @@ def _load_crypto():
 ARC4, RSA, AES = _load_crypto()
 
 
-from io import BytesIO
 
 
 # Do we generate cross reference streams on output?
@@ -440,7 +442,7 @@ def nunpack(s, default=0):
     elif l == 2:
         return struct.unpack('>H', s)[0]
     elif l == 3:
-        return struct.unpack('>L', '\x00'+s)[0]
+        return struct.unpack('>L', b'\x00'+s)[0]
     elif l == 4:
         return struct.unpack('>L', s)[0]
     else:
@@ -472,16 +474,16 @@ class PSLiteral(PSObject):
     Use PSLiteralTable.intern() instead.
     '''
     def __init__(self, name):
-        self.name = name
+        self.name = name.decode('utf-8')
         return
 
     def __repr__(self):
         name = []
         for char in self.name:
             if not char.isalnum():
-                char = b'#%02x' % ord(char)
+                char = '#%02x' % ord(char)
             name.append(char)
-        return b'/%s' % ''.join(name)
+        return '/%s' % ''.join(name)
 
 # PSKeyword
 class PSKeyword(PSObject):
@@ -491,7 +493,7 @@ class PSKeyword(PSObject):
     Use PSKeywordTable.intern() instead.
     '''
     def __init__(self, name):
-        self.name = name
+        self.name = name.decode('utf-8')
         return
 
     def __repr__(self):
@@ -521,12 +523,12 @@ PSLiteralTable = PSSymbolTable(PSLiteral)
 PSKeywordTable = PSSymbolTable(PSKeyword)
 LIT = PSLiteralTable.intern
 KWD = PSKeywordTable.intern
-KEYWORD_BRACE_BEGIN = KWD('{')
-KEYWORD_BRACE_END = KWD('}')
-KEYWORD_ARRAY_BEGIN = KWD('[')
-KEYWORD_ARRAY_END = KWD(']')
-KEYWORD_DICT_BEGIN = KWD('<<')
-KEYWORD_DICT_END = KWD('>>')
+KEYWORD_BRACE_BEGIN = KWD(b'{')
+KEYWORD_BRACE_END = KWD(b'}')
+KEYWORD_ARRAY_BEGIN = KWD(b'[')
+KEYWORD_ARRAY_END = KWD(b']')
+KEYWORD_DICT_BEGIN = KWD(b'<<')
+KEYWORD_DICT_END = KWD(b'>>')
 
 
 def literal_name(x):
@@ -548,18 +550,18 @@ def keyword_name(x):
 
 ##  PSBaseParser
 ##
-EOL = re.compile(r'[\r\n]')
-SPC = re.compile(r'\s')
-NONSPC = re.compile(r'\S')
-HEX = re.compile(r'[0-9a-fA-F]')
-END_LITERAL = re.compile(r'[#/%\[\]()<>{}\s]')
-END_HEX_STRING = re.compile(r'[^\s0-9a-fA-F]')
-HEX_PAIR = re.compile(r'[0-9a-fA-F]{2}|.')
-END_NUMBER = re.compile(r'[^0-9]')
-END_KEYWORD = re.compile(r'[#/%\[\]()<>{}\s]')
-END_STRING = re.compile(r'[()\134]')
-OCT_STRING = re.compile(r'[0-7]')
-ESC_STRING = { 'b':8, 't':9, 'n':10, 'f':12, 'r':13, '(':40, ')':41, '\\':92 }
+EOL = re.compile(rb'[\r\n]')
+SPC = re.compile(rb'\s')
+NONSPC = re.compile(rb'\S')
+HEX = re.compile(rb'[0-9a-fA-F]')
+END_LITERAL = re.compile(rb'[#/%\[\]()<>{}\s]')
+END_HEX_STRING = re.compile(rb'[^\s0-9a-fA-F]')
+HEX_PAIR = re.compile(rb'[0-9a-fA-F]{2}|.')
+END_NUMBER = re.compile(rb'[^0-9]')
+END_KEYWORD = re.compile(rb'[#/%\[\]()<>{}\s]')
+END_STRING = re.compile(rb'[()\\]')
+OCT_STRING = re.compile(rb'[0-7]')
+ESC_STRING = { b'b':8, b't':9, b'n':10, b'f':12, b'r':13, b'(':40, b')':41, b'\\':92 }
 
 class PSBaseParser(object):
 
@@ -591,7 +593,6 @@ class PSBaseParser(object):
         if not pos:
             pos = self.bufpos+self.charpos
         self.fp.seek(pos)
-        ##print >>sys.stderr, 'poll(%d): %r' % (pos, self.fp.read(n))
         self.fp.seek(pos0)
         return
 
@@ -602,7 +603,7 @@ class PSBaseParser(object):
         self.fp.seek(pos)
         # reset the status for nextline()
         self.bufpos = pos
-        self.buf = ''
+        self.buf = b''
         self.charpos = 0
         # reset the status for nexttoken()
         self.parse1 = self.parse_main
@@ -624,32 +625,32 @@ class PSBaseParser(object):
         if not m:
             return (self.parse_main, len(s))
         j = m.start(0)
-        c = s[j]
+        c = bytes([s[j]])
         self.tokenstart = self.bufpos+j
-        if c == '%':
-            self.token = '%'
+        if c == b'%':
+            self.token = c
             return (self.parse_comment, j+1)
-        if c == '/':
-            self.token = ''
+        if c == b'/':
+            self.token = b''
             return (self.parse_literal, j+1)
-        if c in '-+' or c.isdigit():
+        if c in b'-+' or c.isdigit():
             self.token = c
             return (self.parse_number, j+1)
-        if c == '.':
+        if c == b'.':
             self.token = c
             return (self.parse_decimal, j+1)
         if c.isalpha():
             self.token = c
             return (self.parse_keyword, j+1)
-        if c == '(':
-            self.token = ''
+        if c == b'(':
+            self.token = b''
             self.paren = 1
             return (self.parse_string, j+1)
-        if c == '<':
-            self.token = ''
+        if c == b'<':
+            self.token = b''
             return (self.parse_wopen, j+1)
-        if c == '>':
-            self.token = ''
+        if c == b'>':
+            self.token = b''
             return (self.parse_wclose, j+1)
         self.add_token(KWD(c))
         return (self.parse_main, j+1)
@@ -676,20 +677,20 @@ class PSBaseParser(object):
             return (self.parse_literal, len(s))
         j = m.start(0)
         self.token += s[i:j]
-        c = s[j]
-        if c == '#':
-            self.hex = ''
+        c = bytes([s[j]])
+        if c == b'#':
+            self.hex = b''
             return (self.parse_literal_hex, j+1)
         self.add_token(LIT(self.token))
         return (self.parse_main, j)
 
     def parse_literal_hex(self, s, i):
-        c = s[i]
+        c = bytes([s[i]])
         if HEX.match(c) and len(self.hex) < 2:
             self.hex += c
             return (self.parse_literal_hex, i+1)
         if self.hex:
-            self.token += chr(int(self.hex, 16))
+            self.token += bytes([int(self.hex, 16)])
         return (self.parse_literal, i)
 
     def parse_number(self, s, i):
@@ -699,8 +700,8 @@ class PSBaseParser(object):
             return (self.parse_number, len(s))
         j = m.start(0)
         self.token += s[i:j]
-        c = s[j]
-        if c == '.':
+        c = bytes([s[j]])
+        if c == b'.':
             self.token += c
             return (self.parse_decimal, j+1)
         try:
@@ -716,7 +717,7 @@ class PSBaseParser(object):
             return (self.parse_decimal, len(s))
         j = m.start(0)
         self.token += s[i:j]
-        self.add_token(Decimal(self.token))
+        self.add_token(Decimal(self.token.decode('utf-8')))
         return (self.parse_main, j)
 
     def parse_keyword(self, s, i):
@@ -742,58 +743,59 @@ class PSBaseParser(object):
             return (self.parse_string, len(s))
         j = m.start(0)
         self.token += s[i:j]
-        c = s[j]
-        if c == '\\':
+        c = bytes([s[j]])
+        if c == b'\\':
             self.oct = ''
             return (self.parse_string_1, j+1)
-        if c == '(':
+        if c == b'(':
             self.paren += 1
             self.token += c
             return (self.parse_string, j+1)
-        if c == ')':
+        if c == b')':
             self.paren -= 1
             if self.paren:
                 self.token += c
                 return (self.parse_string, j+1)
         self.add_token(self.token)
         return (self.parse_main, j+1)
+
     def parse_string_1(self, s, i):
-        c = s[i]
+        c = bytes([s[i]])
         if OCT_STRING.match(c) and len(self.oct) < 3:
             self.oct += c
             return (self.parse_string_1, i+1)
         if self.oct:
-            self.token += chr(int(self.oct, 8))
+            self.token += bytes([int(self.oct, 8)])
             return (self.parse_string, i)
         if c in ESC_STRING:
-            self.token += chr(ESC_STRING[c])
+            self.token += bytes([ESC_STRING[c]])
         return (self.parse_string, i+1)
 
     def parse_wopen(self, s, i):
-        c = s[i]
+        c = bytes([s[i]])
         if c.isspace() or HEX.match(c):
             return (self.parse_hexstring, i)
-        if c == '<':
+        if c == b'<':
             self.add_token(KEYWORD_DICT_BEGIN)
             i += 1
         return (self.parse_main, i)
 
     def parse_wclose(self, s, i):
-        c = s[i]
-        if c == '>':
+        c = bytes([s[i]])
+        if c == b'>':
             self.add_token(KEYWORD_DICT_END)
             i += 1
         return (self.parse_main, i)
 
     def parse_hexstring(self, s, i):
-        m = END_HEX_STRING.search(s, i)
-        if not m:
+        m1 = END_HEX_STRING.search(s, i)
+        if not m1:
             self.token += s[i:]
             return (self.parse_hexstring, len(s))
-        j = m.start(0)
+        j = m1.start(0)
         self.token += s[i:j]
-        token = HEX_PAIR.sub(lambda m: chr(int(m.group(0), 16)),
-                                                 SPC.sub('', self.token))
+        token = HEX_PAIR.sub(lambda m2: bytes([int(m2.group(0), 16)]),
+                                                 SPC.sub(b'', self.token))
         self.add_token(token)
         return (self.parse_main, j)
 
@@ -808,15 +810,15 @@ class PSBaseParser(object):
         '''
         Fetches a next line that ends either with \\r or \\n.
         '''
-        linebuf = ''
+        linebuf = b''
         linepos = self.bufpos + self.charpos
         eol = False
         while 1:
             self.fillbuf()
             if eol:
-                c = self.buf[self.charpos]
+                c = bytes([self.buf[self.charpos]])
                 # handle '\r\n'
-                if c == '\n':
+                if c == b'\n':
                     linebuf += c
                     self.charpos += 1
                 break
@@ -824,7 +826,7 @@ class PSBaseParser(object):
             if m:
                 linebuf += self.buf[self.charpos:m.end(0)]
                 self.charpos = m.end(0)
-                if linebuf[-1] == '\r':
+                if bytes([linebuf[-1]]) == b'\r':
                     eol = True
                 else:
                     break
@@ -840,7 +842,7 @@ class PSBaseParser(object):
         '''
         self.fp.seek(0, 2)
         pos = self.fp.tell()
-        buf = ''
+        buf = b''
         while 0 < pos:
             prevpos = pos
             pos = max(0, pos-self.BUFSIZ)
@@ -848,13 +850,13 @@ class PSBaseParser(object):
             s = self.fp.read(prevpos-pos)
             if not s: break
             while 1:
-                n = max(s.rfind('\r'), s.rfind('\n'))
+                n = max(s.rfind(b'\r'), s.rfind(b'\n'))
                 if n == -1:
                     buf = s + buf
                     break
                 yield s[n:]+buf
                 s = s[:n]
-                buf = ''
+                buf = b''
         return
 
 
@@ -910,17 +912,17 @@ class PSStackParser(PSBaseParser):
 
     def nextobject(self, direct=False):
         '''
-        Yields a list of objects: keywords, literals, strings,
+        Yields a list of objects: keywords, literals, strings (byte arrays),
         numbers, arrays and dictionaries. Arrays and dictionaries
         are represented as Python sequence and dictionaries.
         '''
         while not self.results:
             (pos, token) = self.nexttoken()
-            ##print (pos,token), (self.curtype, self.curstack)
             if (isinstance(token, int) or
                     isinstance(token, Decimal) or
                     isinstance(token, bool) or
-                    isinstance(token, str) or
+                    isinstance(token, bytearray) or
+                    isinstance(token, bytes) or
                     isinstance(token, PSLiteral)):
                 # normal token
                 self.push((pos, token))
@@ -963,10 +965,10 @@ class PSStackParser(PSBaseParser):
         return obj
 
 
-LITERAL_CRYPT = PSLiteralTable.intern('Crypt')
-LITERALS_FLATE_DECODE = (PSLiteralTable.intern('FlateDecode'), PSLiteralTable.intern('Fl'))
-LITERALS_LZW_DECODE = (PSLiteralTable.intern('LZWDecode'), PSLiteralTable.intern('LZW'))
-LITERALS_ASCII85_DECODE = (PSLiteralTable.intern('ASCII85Decode'), PSLiteralTable.intern('A85'))
+LITERAL_CRYPT = LIT(b'Crypt')
+LITERALS_FLATE_DECODE = (LIT(b'FlateDecode'), LIT(b'Fl'))
+LITERALS_LZW_DECODE = (LIT(b'LZWDecode'), LIT(b'LZW'))
+LITERALS_ASCII85_DECODE = (LIT(b'ASCII85Decode'), LIT(b'A85'))
 
 
 ##  PDF Objects
@@ -1020,7 +1022,7 @@ def resolve_all(x):
     if isinstance(x, list):
         x = [ resolve_all(v) for v in x ]
     elif isinstance(x, dict):
-        for (k,v) in x.iteritems():
+        for (k,v) in iter(x.items()):
             x[k] = resolve_all(v)
     return x
 
@@ -1028,13 +1030,13 @@ def decipher_all(decipher, objid, genno, x):
     '''
     Recursively decipher X.
     '''
-    if isinstance(x, str):
+    if isinstance(x, bytearray) or isinstance(x,bytes):
         return decipher(objid, genno, x)
     decf = lambda v: decipher_all(decipher, objid, genno, v)
     if isinstance(x, list):
         x = [decf(v) for v in x]
     elif isinstance(x, dict):
-        x = dict((k, decf(v)) for (k, v) in x.iteritems())
+        x = dict((k, decf(v)) for (k, v) in iter(x.items()))
     return x
 
 
@@ -1065,7 +1067,7 @@ def num_value(x):
 
 def str_value(x):
     x = resolve1(x)
-    if not isinstance(x, str):
+    if not (isinstance(x, bytearray) or isinstance(x, bytes)):
         if STRICT:
             raise PDFTypeError('String required: %r' % x)
         return ''
@@ -1166,7 +1168,6 @@ class PDFStream(PDFObject):
         if 'Filter' not in self.dic:
             self.data = data
             self.rawdata = None
-            ##print self.dict
             return
         filters = self.dic['Filter']
         if not isinstance(filters, list):
@@ -1176,7 +1177,7 @@ class PDFStream(PDFObject):
                 # will get errors if the document is encrypted.
                 data = zlib.decompress(data)
             elif f in LITERALS_LZW_DECODE:
-                data = ''.join(LZWDecoder(BytesIO(data)).run())
+                data = b''.join(LZWDecoder(BytesIO(data)).run())
             elif f in LITERALS_ASCII85_DECODE:
                 data = ascii85decode(data)
             elif f == LITERAL_CRYPT:
@@ -1204,7 +1205,7 @@ class PDFStream(PDFObject):
                         pred = data[i]
                         ent1 = data[i+1:i+1+columns]
                         if pred == b'\x02':
-                            ent1 = ''.join(bytes([(a+b) & 255]) \
+                            ent1 = b''.join(bytes([(a+b) & 255]) \
                                            for (a,b) in zip(ent0,ent1))
                         buf += ent1
                         ent0 = ent1
@@ -1239,11 +1240,11 @@ class PDFEncryptionError(PDFException): pass
 class PDFPasswordIncorrect(PDFEncryptionError): pass
 
 # some predefined literals and keywords.
-LITERAL_OBJSTM = PSLiteralTable.intern('ObjStm')
-LITERAL_XREF = PSLiteralTable.intern('XRef')
-LITERAL_PAGE = PSLiteralTable.intern('Page')
-LITERAL_PAGES = PSLiteralTable.intern('Pages')
-LITERAL_CATALOG = PSLiteralTable.intern('Catalog')
+LITERAL_OBJSTM = LIT(b'ObjStm')
+LITERAL_XREF = LIT(b'XRef')
+LITERAL_PAGE = LIT(b'Page')
+LITERAL_PAGES = LIT(b'Pages')
+LITERAL_CATALOG = LIT(b'Catalog')
 
 
 ##  XRefs
@@ -1261,7 +1262,7 @@ class PDFXRef(object):
         return '<PDFXRef: objs=%d>' % len(self.offsets)
 
     def objids(self):
-        return self.offsets.iterkeys()
+        return iter(self.offsets.keys())
 
     def load(self, parser):
         self.offsets = {}
@@ -1272,10 +1273,10 @@ class PDFXRef(object):
                 raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
             if not line:
                 raise PDFNoValidXRef('Premature eof: %r' % parser)
-            if line.startswith('trailer'):
+            if line.startswith(b'trailer'):
                 parser.seek(pos)
                 break
-            f = line.strip().split(' ')
+            f = line.strip().split(b' ')
             if len(f) != 2:
                 raise PDFNoValidXRef('Trailer not found: %r: line=%r' % (parser, line))
             try:
@@ -1287,16 +1288,17 @@ class PDFXRef(object):
                     (_, line) = parser.nextline()
                 except PSEOF:
                     raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
-                f = line.strip().split(' ')
+                f = line.strip().split(b' ')
                 if len(f) != 3:
                     raise PDFNoValidXRef('Invalid XRef format: %r, line=%r' % (parser, line))
                 (pos, genno, use) = f
-                if use != 'n': continue
-                self.offsets[objid] = (int(genno), int(pos))
+                if use != b'n':
+                    continue
+                self.offsets[objid] = (int(genno.decode('utf-8')), int(pos.decode('utf-8')))
         self.load_trailer(parser)
         return
 
-    KEYWORD_TRAILER = PSKeywordTable.intern('trailer')
+    KEYWORD_TRAILER = KWD(b'trailer')
     def load_trailer(self, parser):
         try:
             (_,kwd) = parser.nexttoken()
@@ -1401,7 +1403,8 @@ class PDFDocument(object):
     # set_parser(parser)
     #   Associates the document with an (already initialized) parser object.
     def set_parser(self, parser):
-        if self.parser: return
+        if self.parser:
+            return
         self.parser = parser
         # The document is set to be temporarily ready during collecting
         # all the basic information about the document, e.g.
@@ -1423,13 +1426,13 @@ class PDFDocument(object):
                                    dict_value(trailer['Encrypt']))
                 # fix for bad files
                 except:
-                    self.encryption = ('ffffffffffffffffffffffffffffffffffff',
+                    self.encryption = (b'ffffffffffffffffffffffffffffffffffff',
                                        dict_value(trailer['Encrypt']))
             if 'Root' in trailer:
                 self.set_root(dict_value(trailer['Root']))
                 break
-        else:
-            raise PDFSyntaxError('No /Root object! - Is this really a PDF?')
+            else:
+                raise PDFSyntaxError('No /Root object! - Is this really a PDF?')
         # The document is set to be non-ready again, until all the
         # proper initialization (asking the password key and
         # verifying the access permission, so on) is finished.
@@ -1450,7 +1453,7 @@ class PDFDocument(object):
     #   Perform the initialization with a given password.
     #   This step is mandatory even if there's no password associated
     #   with the document.
-    def initialize(self, password=''):
+    def initialize(self, password=b''):
         if not self.encryption:
             self.is_printable = self.is_modifiable = self.is_extractable = True
             self.ready = True
@@ -1477,14 +1480,14 @@ class PDFDocument(object):
     def genkey_adobe_ps(self, param):
         # nice little offline principal keys dictionary
         # global static principal key for German Onleihe / Bibliothek Digital
-        principalkeys = { 'bibliothek-digital.de': 'rRwGv2tbpKov1krvv7PO0ws9S436/lArPlfipz5Pqhw='.decode('base64')}
+        principalkeys = { b'bibliothek-digital.de': codecs.decode(b'rRwGv2tbpKov1krvv7PO0ws9S436/lArPlfipz5Pqhw=','base64')}
         self.is_printable = self.is_modifiable = self.is_extractable = True
-        length = int_value(param.get('Length', 0)) / 8
+        length = int_value(param.get('Length', 0)) // 8
         edcdata = str_value(param.get('EDCData')).decode('base64')
         pdrllic = str_value(param.get('PDRLLic')).decode('base64')
         pdrlpol = str_value(param.get('PDRLPol')).decode('base64')
         edclist = []
-        for pair in edcdata.split('\n'):
+        for pair in edcdata.split(b'\n'):
             edclist.append(pair)
         # principal key request
         for key in principalkeys:
@@ -1493,9 +1496,9 @@ class PDFDocument(object):
             else:
                 raise ADEPTError('Cannot find principal key for this pdf')
         shakey = SHA256(principalkey)
-        ivector = 16 * chr(0)
+        ivector = bytes(16) # 16 zero bytes
         plaintext = AES.new(shakey,AES.MODE_CBC,ivector).decrypt(edclist[9].decode('base64'))
-        if plaintext[-16:] != 16 * chr(16):
+        if plaintext[-16:] != bytearray(b'\0x10')*16:
             raise ADEPTError('Offlinekey cannot be decrypted, aborting ...')
         pdrlpol = AES.new(plaintext[16:32],AES.MODE_CBC,edclist[2].decode('base64')).decrypt(pdrlpol)
         if pdrlpol[-1] < 1 or pdrlpol[-1] > 16:
@@ -1505,8 +1508,8 @@ class PDFDocument(object):
             pdrlpol = pdrlpol[:cutter]
         return plaintext[:16]
 
-    PASSWORD_PADDING = '(\xbfN^Nu\x8aAd\x00NV\xff\xfa\x01\x08..' \
-                       '\x00\xb6\xd0h>\x80/\x0c\xa9\xfedSiz'
+    PASSWORD_PADDING = b'(\xbfN^Nu\x8aAd\x00NV\xff\xfa\x01\x08..' \
+                       b'\x00\xb6\xd0h>\x80/\x0c\xa9\xfedSiz'
     # experimental aes pw support
     def initialize_standard(self, password, docid, param):
         # copy from a global variable
@@ -1523,7 +1526,7 @@ class PDFDocument(object):
         try:
             EncMetadata = str_value(param['EncryptMetadata'])
         except:
-            EncMetadata = 'True'
+            EncMetadata = b'True'
         self.is_printable = bool(P & 4)
         self.is_modifiable = bool(P & 8)
         self.is_extractable = bool(P & 16)
@@ -1540,12 +1543,12 @@ class PDFDocument(object):
         hash.update(docid[0]) # 5
         # aes special handling if metadata isn't encrypted
         if EncMetadata == ('False' or 'false'):
-            hash.update('ffffffff'.decode('hex'))
+            hash.update(codecs.decode(b'ffffffff','hex'))
         if 5 <= R:
             # 8
             for _ in range(50):
-                hash = hashlib.md5(hash.digest()[:length/8])
-        key = hash.digest()[:length/8]
+                hash = hashlib.md5(hash.digest()[:length//8])
+        key = hash.digest()[:length//8]
         if R == 2:
             # Algorithm 3.4
             u1 = ARC4.new(key).decrypt(password)
@@ -1555,7 +1558,7 @@ class PDFDocument(object):
             hash.update(docid[0]) # 3
             x = ARC4.new(key).decrypt(hash.digest()[:16]) # 4
             for i in range(1,19+1):
-                k = ''.join(bytes([c ^ i]) for c in key )
+                k = b''.join(bytes([c ^ i]) for c in key )
                 x = ARC4.new(k).decrypt(x)
             u1 = x+x # 32bytes total
         if R == 2:
@@ -1587,17 +1590,19 @@ class PDFDocument(object):
     def initialize_ebx(self, password, docid, param):
         self.is_printable = self.is_modifiable = self.is_extractable = True
         rsa = RSA(password)
-        length = int_value(param.get('Length', 0)) / 8
-        rights = str_value(param.get('ADEPT_LICENSE')).decode('base64')
+        length = int_value(param.get('Length', 0)) // 8
+        rights = codecs.decode(param.get('ADEPT_LICENSE'), 'base64')
         rights = zlib.decompress(rights, -15)
         rights = etree.fromstring(rights)
         expr = './/{http://ns.adobe.com/adept}encryptedKey'
-        bookkey = ''.join(rights.findtext(expr)).decode('base64')
+        bookkey = codecs.decode(''.join(rights.findtext(expr)).encode('utf-8'),'base64')
         bookkey = rsa.decrypt(bookkey)
-        if bookkey[0] != '\x02':
-            raise ADEPTError('error decrypting book session key')
-        index = bookkey.index('\0') + 1
-        bookkey = bookkey[index:]
+        #if bookkey[0] != 2:
+        #    raise ADEPTError('error decrypting book session key')
+        if len(bookkey) > 16:
+            if bookkey[-17] == '\x00' or bookkey[-17] == 0:
+                bookkey = bookkey[-16:]
+                length = 16
         ebx_V = int_value(param.get('V', 4))
         ebx_type = int_value(param.get('EBX_ENCRYPTIONTYPE', 6))
         # added because of improper booktype / decryption book session key errors
@@ -1643,7 +1648,7 @@ class PDFDocument(object):
         objid = struct.pack('<L', objid ^ 0x3569ac)
         genno = struct.pack('<L', genno ^ 0xca96)
         key = self.decrypt_key
-        key += objid[0] + genno[0] + objid[1] + genno[1] + objid[2] + 'sAlT'
+        key += objid[0] + genno[0] + objid[1] + genno[1] + objid[2] + b'sAlT'
         hash = hashlib.md5(key)
         key = hash.digest()[:min(len(self.decrypt_key) + 5, 16)]
         return key
@@ -1652,7 +1657,7 @@ class PDFDocument(object):
     def genkey_v4(self, objid, genno):
         objid = struct.pack('<L', objid)[:3]
         genno = struct.pack('<L', genno)[:2]
-        key = self.decrypt_key + objid + genno + 'sAlT'
+        key = self.decrypt_key + objid + genno + b'sAlT'
         hash = hashlib.md5(key)
         key = hash.digest()[:min(len(self.decrypt_key) + 5, 16)]
         return key
@@ -1664,7 +1669,6 @@ class PDFDocument(object):
         plaintext = AES.new(key,AES.MODE_CBC,ivector).decrypt(data)
         # remove pkcs#5 aes padding
         cutter = -1 * plaintext[-1]
-        #print cutter
         plaintext = plaintext[:cutter]
         return plaintext
 
@@ -1675,7 +1679,6 @@ class PDFDocument(object):
         plaintext = AES.new(key,AES.MODE_CBC,ivector).decrypt(data)
         # remove pkcs#5 aes padding
         cutter = -1 * plaintext[-1]
-        #print cutter
         plaintext = plaintext[:cutter]
         return plaintext
 
@@ -1684,7 +1687,7 @@ class PDFDocument(object):
         return ARC4.new(key).decrypt(data)
 
 
-    KEYWORD_OBJ = PSKeywordTable.intern('obj')
+    KEYWORD_OBJ = KWD(b'obj')
 
     def getobj(self, objid):
         if not self.ready:
@@ -1791,11 +1794,11 @@ class PDFParser(PSStackParser):
     def __repr__(self):
         return '<PDFParser>'
 
-    KEYWORD_R = PSKeywordTable.intern('R')
-    KEYWORD_ENDOBJ = PSKeywordTable.intern('endobj')
-    KEYWORD_STREAM = PSKeywordTable.intern('stream')
-    KEYWORD_XREF = PSKeywordTable.intern('xref')
-    KEYWORD_STARTXREF = PSKeywordTable.intern('startxref')
+    KEYWORD_R = KWD(b'R')
+    KEYWORD_ENDOBJ = KWD(b'endobj')
+    KEYWORD_STREAM = KWD(b'stream')
+    KEYWORD_XREF = KWD(b'xref')
+    KEYWORD_STARTXREF = KWD(b'startxref')
     def do_keyword(self, pos, token):
         if token in (self.KEYWORD_XREF, self.KEYWORD_STARTXREF):
             self.add_results(*self.pop(1))
@@ -1843,8 +1846,8 @@ class PDFParser(PSStackParser):
                     if STRICT:
                         raise PDFSyntaxError('Unexpected EOF')
                     break
-                if 'endstream' in line:
-                    i = line.index('endstream')
+                if b'endstream' in line:
+                    i = line.index(b'endstream')
                     objlen += i
                     data += line[:i]
                     break
@@ -1864,7 +1867,7 @@ class PDFParser(PSStackParser):
         prev = None
         for line in self.revreadlines():
             line = line.strip()
-            if line == 'startxref': break
+            if line == b'startxref': break
             if line:
                 prev = line
         else:
@@ -1916,7 +1919,7 @@ class PDFParser(PSStackParser):
         except PDFNoValidXRef:
             # fallback
             self.seek(0)
-            pat = re.compile(r'^(\d+)\s+(\d+)\s+obj\b')
+            pat = re.compile(rb'^(\d+)\s+(\d+)\s+obj\b')
             offsets = {}
             xref = PDFXRef()
             while 1:
@@ -1924,7 +1927,7 @@ class PDFParser(PSStackParser):
                     (pos, line) = self.nextline()
                 except PSEOF:
                     break
-                if line.startswith('trailer'):
+                if line.startswith(b'trailer'):
                     trailerpos = pos # remember last trailer
                 m = pat.match(line)
                 if not m: continue
@@ -1951,7 +1954,7 @@ class PDFObjStrmParser(PDFParser):
         self.add_results(*self.popall())
         return
 
-    KEYWORD_R = KWD('R')
+    KEYWORD_R = KWD(b'R')
     def do_keyword(self, pos, token):
         if token is self.KEYWORD_R:
             # reference to indirect object
@@ -1994,7 +1997,7 @@ class PDFSerializer(object):
     def dump(self, outf):
         self.outf = outf
         self.write(self.version)
-        self.write('\n%\xe2\xe3\xcf\xd3\n')
+        self.write(b'\n%\xe2\xe3\xcf\xd3\n')
         doc = self.doc
         objids = self.objids
         xrefs = {}
@@ -2016,18 +2019,18 @@ class PDFSerializer(object):
         startxref = self.tell()
 
         if not gen_xref_stm:
-            self.write('xref\n')
-            self.write('0 %d\n' % (maxobj + 1,))
+            self.write(b'xref\n')
+            self.write(b'0 %d\n' % (maxobj + 1,))
             for objid in range(0, maxobj + 1):
                 if objid in xrefs:
                     # force the genno to be 0
-                    self.write("%010d 00000 n \n" % xrefs[objid][0])
+                    self.write(b"%010d 00000 n \n" % xrefs[objid][0])
                 else:
-                    self.write("%010d %05d f \n" % (0, 65535))
+                    self.write(b"%010d %05d f \n" % (0, 65535))
 
-            self.write('trailer\n')
+            self.write(b'trailer\n')
             self.serialize_object(trailer)
-            self.write('\nstartxref\n%d\n%%%%EOF' % startxref)
+            self.write(b'\nstartxref\n%d\n%%%%EOF' % startxref)
 
         else: # Generate crossref stream.
 
@@ -2076,7 +2079,7 @@ class PDFSerializer(object):
                 data.append(struct.pack('>L', f2)[-fl2:])
                 data.append(struct.pack('>L', f3)[-fl3:])
             index.extend((first, prev - first + 1))
-            data = zlib.compress(''.join(data))
+            data = zlib.compress(b''.join(data))
             dic = {'Type': LITERAL_XREF, 'Size': prev + 1, 'Index': index,
                    'W': [1, fl2, fl3], 'Length': len(data),
                    'Filter': LITERALS_FLATE_DECODE[0],
@@ -2085,7 +2088,7 @@ class PDFSerializer(object):
                 dic['Info'] = trailer['Info']
             xrefstm = PDFStream(dic, data)
             self.serialize_indirect(maxobj, xrefstm)
-            self.write('startxref\n%d\n%%%%EOF' % startxref)
+            self.write(b'startxref\n%d\n%%%%EOF' % startxref)
     def write(self, data):
         self.outf.write(data)
         self.last = data[-1:]
@@ -2094,13 +2097,10 @@ class PDFSerializer(object):
         return self.outf.tell()
 
     def escape_string(self, string):
-        string = string.replace('\\', '\\\\')
-        string = string.replace('\n', r'\n')
-        string = string.replace('(', r'\(')
-        string = string.replace(')', r'\)')
-         # get rid of ciando id
-        regularexp = re.compile(r'http://www.ciando.com/index.cfm/intRefererID/\d{5}')
-        if regularexp.match(string): return ('http://www.ciando.com')
+        string = string.replace(b'\\', b'\\\\')
+        string = string.replace(b'\n', rb'\n')
+        string = string.replace(b'(', rb'\(')
+        string = string.replace(b')', rb'\)')
         return string
 
     def serialize_object(self, obj):
@@ -2111,34 +2111,38 @@ class PDFSerializer(object):
                 obj['Subtype'] = obj['Type']
                 del obj['Type']
             # end - hope this doesn't have bad effects
-            self.write('<<')
+            self.write(b'<<')
             for key, val in obj.items():
-                self.write('/%s' % key)
+                self.write(str(LIT(key.encode('utf-8'))).encode('utf-8'))
                 self.serialize_object(val)
-            self.write('>>')
+            self.write(b'>>')
         elif isinstance(obj, list):
-            self.write('[')
+            self.write(b'[')
             for val in obj:
                 self.serialize_object(val)
-            self.write(']')
+            self.write(b']')
+        elif isinstance(obj, bytearray):
+            self.write(b'(%s)' % self.escape_string(obj))
+        elif isinstance(obj, bytes):
+            self.write(b'(%s)' % self.escape_string(obj))
         elif isinstance(obj, str):
-            self.write('(%s)' % self.escape_string(obj))
+            self.write(b'(%s)' % self.escape_string(obj.encode('utf-8')))
         elif isinstance(obj, bool):
             if self.last.isalnum():
-                self.write(' ')
-            self.write(str(obj).lower())
+                self.write(b' ')
+            self.write(str(obj).lower().encode('utf-8'))
         elif isinstance(obj, int):
             if self.last.isalnum():
-                self.write(' ')
-            self.write(str(obj))
+                self.write(b' ')
+            self.write(str(obj).encode('utf-8'))
         elif isinstance(obj, Decimal):
             if self.last.isalnum():
-                self.write(' ')
-            self.write(str(obj))
+                self.write(b' ')
+            self.write(str(obj).encode('utf-8'))
         elif isinstance(obj, PDFObjRef):
             if self.last.isalnum():
-                self.write(' ')
-            self.write('%d %d R' % (obj.objid, 0))
+                self.write(b' ')
+            self.write(b'%d %d R' % (obj.objid, 0))
         elif isinstance(obj, PDFStream):
             ### If we don't generate cross ref streams the object streams
             ### are no longer useful, as we have extracted all objects from
@@ -2148,41 +2152,36 @@ class PDFSerializer(object):
             else:
                 data = obj.get_decdata()
                 self.serialize_object(obj.dic)
-                self.write('stream\n')
+                self.write(b'stream\n')
                 self.write(data)
-                self.write('\nendstream')
+                self.write(b'\nendstream')
         else:
-            data = str(obj)
-            if data[0].isalnum() and self.last.isalnum():
-                self.write(' ')
+            data = str(obj).encode('utf-8')
+            if bytes([data[0]]).isalnum() and self.last.isalnum():
+                self.write(b' ')
             self.write(data)
 
     def serialize_indirect(self, objid, obj):
-        self.write('%d 0 obj' % (objid,))
+        self.write(b'%d 0 obj' % (objid,))
         self.serialize_object(obj)
         if self.last.isalnum():
-            self.write('\n')
-        self.write('endobj\n')
+            self.write(b'\n')
+        self.write(b'endobj\n')
 
 
 
 
 def decryptBook(userkey, inpath, outpath):
     if RSA is None:
-        raise ADEPTError("PyCrypto or OpenSSL must be installed.")
+        raise ADEPTError("PyCryptodome or OpenSSL must be installed.")
     with open(inpath, 'rb') as inf:
-        #try:
         serializer = PDFSerializer(inf, userkey)
-        #except:
-        #    print "Error serializing pdf {0}. Probably wrong key.".format(os.path.basename(inpath))
-        #    return 2
-        # hope this will fix the 'bad file descriptor' problem
         with open(outpath, 'wb') as outf:
             # help construct to make sure the method runs to the end
             try:
                 serializer.dump(outf)
             except Exception as e:
-                print("error writing pdf: {0}".format(e.args[0]))
+                print("error writing pdf: {0}".format(e))
                 return 2
     return 0
 

DeDRM_plugin/ion.py

@@ -512,6 +512,8 @@ class BinaryIonParser(object):
 
         if table is not None:
             self.symbols.import_(table, min(maxid, len(table.symnames)))
+            if len(table.symnames) < maxid:
+                self.symbols.importunknown(name + "-unknown", maxid - len(table.symnames))
         else:
             self.symbols.importunknown(name, maxid)
 
@@ -733,7 +735,10 @@ SYM_NAMES = [ 'com.amazon.drm.Envelope@1.0',
               'com.amazon.drm.EncryptedPage@2.0',
               'com.amazon.drm.PlainText@2.0', 'compression_algorithm',
               'com.amazon.drm.Compressed@1.0', 'page_index_table',
-              'com.amazon.drm.VoucherEnvelope@2.0', 'com.amazon.drm.VoucherEnvelope@3.0' ]
+              ] + ['com.amazon.drm.VoucherEnvelope@%d.0' % n
+                   for n in list(range(2, 29)) + [
+                                   9708, 1031, 2069, 9041, 3646,
+                                   6052, 9479, 9888, 4648, 5683]]
 
 def addprottable(ion):
     ion.addtocatalog("ProtectedData", 1, SYM_NAMES)
@@ -757,9 +762,45 @@ def pkcs7unpad(msg, blocklen):
 
 
 # every VoucherEnvelope version has a corresponding "word" and magic number, used in obfuscating the shared secret
-VOUCHER_VERSION_INFOS = {
-    2: [b'Antidisestablishmentarianism', 5],
-    3: [b'Floccinaucinihilipilification', 8]
+OBFUSCATION_TABLE = {
+    "V1":    (0x00, None),
+    "V2":    (0x05, b'Antidisestablishmentarianism'),
+    "V3":    (0x08, b'Floccinaucinihilipilification'),
+    "V4":    (0x07, b'>\x14\x0c\x12\x10-\x13&\x18U\x1d\x05Rlt\x03!\x19\x1b\x13\x04]Y\x19,\t\x1b'),
+    "V5":    (0x06, b'~\x18~\x16J\\\x18\x10\x05\x0b\x07\t\x0cZ\r|\x1c\x15\x1d\x11>,\x1b\x0e\x03"4\x1b\x01'),
+    "V6":    (0x09, b'3h\x055\x03[^>\x19\x1c\x08\x1b\rtm4\x02Rp\x0c\x16B\n'),
+    "V7":    (0x05, b'\x10\x1bJ\x18\nh!\x10"\x03>Z\'\r\x01]W\x06\x1c\x1e?\x0f\x13'),
+    "V8":    (0x09, b"K\x0c6\x1d\x1a\x17pO}Rk\x1d'w1^\x1f$\x1c{C\x02Q\x06\x1d`"),
+    "V9":    (0x05, b'X.\x0eW\x1c*K\x12\x12\t\n\n\x17Wx\x01\x02Yf\x0f\x18\x1bVXPi\x01'),
+    "V10":   (0x07, b'z3\n\x039\x12\x13`\x06=v,\x02MTK\x1e%}L\x1c\x1f\x15\x0c\x11\x02\x0c\n8\x17p'),
+    "V11":   (0x05, b'L=\nhVm\x07go\n6\x14\x06\x16L\r\x02\x0b\x0c\x1b\x04#p\t'),
+    "V12":   (0x06, b',n\x1d\rl\x13\x1c\x13\x16p\x14\x07U\x0c\x1f\x19w\x16\x16\x1d5T'),
+    "V13":   (0x07, b'I\x05\t\x08\x03r)\x01$N\x0fr3n\x0b062D\x0f\x13'),
+    "V14":   (0x05, b"\x03\x02\x1c9\x19\x15\x15q\x1057\x08\x16\x0cF\x1b.Fw\x01\x12\x03\x13\x02\x17S'hk6"),
+    "V15":   (0x0A, b'&,4B\x1dcI\x0bU\x03I\x07\x04\x1c\t\x05c\x07%ws\x0cj\t\x1a\x08\x0f'),
+    "V16":   (0x0A, b'\x06\x18`h,b><\x06PqR\x02Zc\x034\n\x16\x1e\x18\x06#e'),
+    "V17":   (0x07, b'y\r\x12\x08fw.[\x02\t\n\x13\x11\x0c\x11b\x1e8L\x10(\x13<Jx6c\x0f'),
+    "V18":   (0x07, b'I\x0b\x0e,\x19\x1aIa\x10s\x19g\\\x1b\x11!\x18yf\x0f\t\x1d7[bSp\x03'),
+    "V19":   (0x05, b'\n6>)N\x02\x188\x016s\x13\x14\x1b\x16jeN\n\x146\x04\x18\x1c\x0c\x19\x1f,\x02]'),
+    "V20":   (0x08, b'_\r\x01\x12]\\\x14*\x17i\x14\r\t!\x1e,~hZ\x12jK\x17\x1e*1'),
+    "V21":   (0x07, b'e\x1d\x19|\ty\x1di|N\x13\x0e\x04\x1bj<h\x13\x15k\x12\x08=\x1f\x16~\x13l'),
+    "V22":   (0x08, b'?\x17yi$k7Pc\tEo\x0c\x07\x07\t\x1f,*i\x12\x0cI0\x10I\x1a?2\x04'),
+    "V23":   (0x08, b'\x16+db\x13\x04\x18\rc%\x14\x17\x0f\x13F\x0c[\t9\x1ay\x01\x1eH'),
+    "V24":   (0x06, b'|6\\\x1a\r\x10\nP\x07\x0fu\x1f\t,\rr`uv\\~55\x11]N'),
+    "V25":   (0x09, b'\x07\x14w\x1e,^y\x01:\x08\x07\x1fr\tU#j\x16\x12\x1eB\x04\x16=\x06fZ\x07\x02\x06'),
+    "V26":   (0x06, b'\x03IL\x1e"K\x1f\x0f\x1fp0\x01`X\x02z0`\x03\x0eN\x07'),
+    "V27":   (0x07, b'Xk\x10y\x02\x18\x10\x17\x1d,\x0e\x05e\x10\x15"e\x0fh(\x06s\x1c\x08I\x0c\x1b\x0e'),
+    "V28":   (0x0A, b'6P\x1bs\x0f\x06V.\x1cM\x14\x02\n\x1b\x07{P0:\x18zaU\x05'),
+    "V9708": (0x05, b'\x1diIm\x08a\x17\x1e!am\x1d\x1aQ.\x16!\x06*\}x04\x11\t\x06\x04?'),
+    "V1031": (0x08, b'Antidisestablishmentarianism'),
+    "V2069": (0x07, b'Floccinaucinihilipilification'),
+    "V9041": (0x06, b'>\x14\x0c\x12\x10-\x13&\x18U\x1d\x05Rlt\x03!\x19\x1b\x13\x04]Y\x19,\t\x1b'),
+    "V3646": (0x09, b'~\x18~\x16J\\\x18\x10\x05\x0b\x07\t\x0cZ\r|\x1c\x15\x1d\x11>,\x1b\x0e\x03"4\x1b\x01'),
+    "V6052": (0x05, b'3h\x055\x03[^>\x19\x1c\x08\x1b\rtm4\x02Rp\x0c\x16B\n'),
+    "V9479": (0x09, b'\x10\x1bJ\x18\nh!\x10"\x03>Z\'\r\x01]W\x06\x1c\x1e?\x0f\x13'),
+    "V9888": (0x05, b"K\x0c6\x1d\x1a\x17pO}Rk\x1d'w1^\x1f$\x1c{C\x02Q\x06\x1d`"),
+    "V4648": (0x07, b'X.\x0eW\x1c*K\x12\x12\t\n\n\x17Wx\x01\x02Yf\x0f\x18\x1bVXPi\x01'),
+    "V5683": (0x05, b'z3\n\x039\x12\x13`\x06=v,\x02MTK\x1e%}L\x1c\x1f\x15\x0c\x11\x02\x0c\n8\x17p'),
 }
 
 
@@ -768,9 +809,7 @@ def obfuscate(secret, version):
     if version == 1:  # v1 does not use obfuscation
         return secret
 
-    params = VOUCHER_VERSION_INFOS[version]
-    word = params[0]
-    magic = params[1]
+    magic, word = OBFUSCATION_TABLE["V%d" % version]
 
     # extend secret so that its length is divisible by the magic number
     if len(secret) % magic != 0:
@@ -809,24 +848,30 @@ class DrmIonVoucher(object):
     def __init__(self, voucherenv, dsn, secret):
         self.dsn, self.secret = dsn, secret
 
+        if isinstance(dsn, str):
+            self.dsn = dsn.encode('ASCII')
+
+        if isinstance(secret, str):
+            self.secret = secret.encode('ASCII')
+
         self.lockparams = []
 
         self.envelope = BinaryIonParser(voucherenv)
         addprottable(self.envelope)
 
     def decryptvoucher(self):
-        shared = "PIDv3" + self.encalgorithm + self.enctransformation + self.hashalgorithm
+        shared = ("PIDv3" + self.encalgorithm + self.enctransformation + self.hashalgorithm).encode('ASCII')
 
         self.lockparams.sort()
         for param in self.lockparams:
             if param == "ACCOUNT_SECRET":
-                shared += param + self.secret
+                shared += param.encode('ASCII') + self.secret
             elif param == "CLIENT_ID":
-                shared += param + self.dsn
+                shared += param.encode('ASCII') + self.dsn
             else:
                 _assert(False, "Unknown lock parameter: %s" % param)
 
-        sharedsecret = obfuscate(shared.encode('ASCII'), self.version)
+        sharedsecret = obfuscate(shared, self.version)
 
         key = hmac.new(sharedsecret, b"PIDv3", digestmod=hashlib.sha256).digest()
         aes = AES.new(key[:32], AES.MODE_CBC, self.cipheriv[:16])
@@ -993,6 +1038,7 @@ class DrmIon(object):
 
                 elif self.ion.gettypename() in ["com.amazon.drm.EncryptedPage@1.0", "com.amazon.drm.EncryptedPage@2.0"]:
                     decompress = False
+                    decrypt = True
                     ct = None
                     civ = None
                     self.ion.stepin()
@@ -1006,7 +1052,23 @@ class DrmIon(object):
                             civ = self.ion.lobvalue()
 
                     if ct is not None and civ is not None:
-                        self.processpage(ct, civ, outpages, decompress)
+                        self.processpage(ct, civ, outpages, decompress, decrypt)
+                    self.ion.stepout()
+
+                elif self.ion.gettypename() in ["com.amazon.drm.PlainText@1.0", "com.amazon.drm.PlainText@2.0"]:
+                    decompress = False
+                    decrypt = False
+                    plaintext = None
+                    self.ion.stepin()
+                    while self.ion.hasnext():
+                        self.ion.next()
+                        if self.ion.gettypename() == "com.amazon.drm.Compressed@1.0":
+                            decompress = True
+                        if self.ion.getfieldname() == "data":
+                            plaintext = self.ion.lobvalue()
+
+                    if plaintext is not None:
+                        self.processpage(plaintext, None, outpages, decompress, decrypt)
                     self.ion.stepout()
 
             self.ion.stepout()
@@ -1017,9 +1079,12 @@ class DrmIon(object):
     def print_(self, lst):
         self.ion.print_(lst)
 
-    def processpage(self, ct, civ, outpages, decompress):
-        aes = AES.new(self.key[:16], AES.MODE_CBC, civ[:16])
-        msg = pkcs7unpad(aes.decrypt(ct), 16)
+    def processpage(self, ct, civ, outpages, decompress, decrypt):
+        if decrypt:
+            aes = AES.new(self.key[:16], AES.MODE_CBC, civ[:16])
+            msg = pkcs7unpad(aes.decrypt(ct), 16)
+        else:
+            msg = ct
 
         if not decompress:
             outpages.write(msg)

DeDRM_plugin/k4mobidedrm.py

@@ -191,7 +191,7 @@ def unescape(text):
         else:
             # named entity
             try:
-                text = chr(htmlentitydefs.name2codepoint[text[1:-1]])
+                text = chr(html.entities.name2codepoint[text[1:-1]])
             except KeyError:
                 pass
         return text # leave as is

DeDRM_plugin/kfxdedrm.py

@@ -4,10 +4,13 @@
 # Engine to remove drm from Kindle KFX ebooks
 
 #  2.0   - Python 3 for calibre 5.0
+#  2.1   - Some fixes for debugging
+#  2.1.1 - Whitespace!
 
 
 import os
 import shutil
+import traceback
 import zipfile
 
 from io import BytesIO
@@ -65,6 +68,9 @@ class KFXZipBook:
         print("Decrypting KFX DRM voucher: {0}".format(info.filename))
 
         for pid in [''] + totalpids:
+            # Belt and braces. PIDs should be unicode strings, but just in case...
+            if isinstance(pid, bytes):
+                pid = pid.decode('ascii')
             for dsn_len,secret_len in [(0,0), (16,0), (16,40), (32,40), (40,0), (40,40)]:
                 if len(pid) == dsn_len + secret_len:
                     break       # split pid into DSN and account secret
@@ -77,6 +83,7 @@ class KFXZipBook:
                 voucher.decryptvoucher()
                 break
             except:
+                traceback.print_exc()
                 pass
         else:
             raise Exception("Failed to decrypt KFX DRM voucher with any key")

DeDRM_plugin/kgenpids.py

@@ -174,14 +174,14 @@ def pidFromSerial(s, l):
 
 # Parse the EXTH header records and use the Kindle serial number to calculate the book pid.
 def getKindlePids(rec209, token, serialnum):
+    if isinstance(serialnum,str):
+        serialnum = serialnum.encode('utf-8')
+
     if rec209 is None:
         return [serialnum]
 
     pids=[]
 
-    if isinstance(serialnum,str):
-        serialnum = serialnum.encode('utf-8')
-
     # Compute book PID
     pidHash = SHA1(serialnum+rec209+token)
     bookPID = encodePID(pidHash)
@@ -209,7 +209,7 @@ def getK4Pids(rec209, token, kindleDatabase):
         kindleAccountToken = bytearray.fromhex((kindleDatabase[1])['kindle.account.tokens'])
 
     except KeyError:
-        kindleAccountToken=""
+        kindleAccountToken = b''
         pass
 
     try:
@@ -296,14 +296,14 @@ def getPidList(md1, md2, serials=[], kDatabases=[]):
 
     for kDatabase in kDatabases:
         try:
-            pidlst.extend(getK4Pids(md1, md2, kDatabase))
+            pidlst.extend(map(bytes,getK4Pids(md1, md2, kDatabase)))
         except Exception as e:
             print("Error getting PIDs from database {0}: {1}".format(kDatabase[0],e.args[0]))
             traceback.print_exc()
 
     for serialnum in serials:
         try:
-            pidlst.extend(getKindlePids(md1, md2, serialnum))
+            pidlst.extend(map(bytes,getKindlePids(md1, md2, serialnum)))
         except Exception as e:
             print("Error getting PIDs from serial number {0}: {1}".format(serialnum ,e.args[0]))
             traceback.print_exc()

DeDRM_plugin/mobidedrm.py

@@ -191,19 +191,21 @@ def PC1(key, src, decryption=True):
         dst+=bytes([curByte])
     return dst
 
+# accepts unicode returns unicode
 def checksumPid(s):
     letters = 'ABCDEFGHIJKLMNPQRSTUVWXYZ123456789'
-    crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
+    crc = (~binascii.crc32(s.encode('utf-8'),-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].encode('ascii')
+        res += letters[pos%l]
         crc >>= 8
     return res
 
+# expects bytearray
 def getSizeOfTrailingDataEntries(ptr, size, flags):
     def getSizeOfTrailingDataEntry(ptr, size):
         bitpos, result = 0, 0
@@ -282,7 +284,7 @@ class MobiBook:
         self.mobi_codepage = 1252
         self.mobi_version = -1
 
-        if self.magic == 'TEXtREAd':
+        if self.magic == b'TEXtREAd':
             print("PalmDoc format book detected.")
             return
 
@@ -301,7 +303,7 @@ class MobiBook:
         # if exth region exists parse it for metadata array
         try:
             exth_flag, = struct.unpack('>L', self.sect[0x80:0x84])
-            exth = ''
+            exth = b''
             if exth_flag & 0x40:
                 exth = self.sect[16 + self.mobi_length:]
             if (len(exth) >= 12) and (exth[:4] == b'EXTH'):
@@ -323,12 +325,13 @@ class MobiBook:
         except Exception as e:
             print("Cannot set meta_array: Error: {:s}".format(e.args[0]))
 
+    #returns unicode
     def getBookTitle(self):
         codec_map = {
             1252 : 'windows-1252',
             65001 : 'utf-8',
         }
-        title = ''
+        title = b''
         codec = 'windows-1252'
         if self.magic == b'BOOKMOBI':
             if 503 in self.meta_array:
@@ -339,7 +342,7 @@ class MobiBook:
                 title = self.sect[toff:tend]
             if self.mobi_codepage in codec_map.keys():
                 codec = codec_map[self.mobi_codepage]
-        if title == '':
+        if title == b'':
             title = self.header[:32]
             title = title.split(b'\0')[0]
         return title.decode(codec)
@@ -355,13 +358,15 @@ class MobiBook:
             # if that key exists in the meta_array, append its contents to the token
             for i in range(0,len(data),5):
                 val,  = struct.unpack('>I',data[i+1:i+5])
-                sval = self.meta_array.get(val,'')
+                sval = self.meta_array.get(val,b'')
                 token += sval
         return rec209, token
 
+    # new must be byte array
     def patch(self, off, new):
         self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
 
+    # new must be byte array
     def patchSection(self, section, new, in_off = 0):
         if (section + 1 == self.num_sections):
             endoff = len(self.data_file)
@@ -371,12 +376,12 @@ class MobiBook:
         assert off + in_off + len(new) <= endoff
         self.patch(off + in_off, new)
 
+    # pids in pidlist must be unicode, returned key is byte array, pid is unicode
     def parseDRM(self, data, count, pidlist):
         found_key = None
         keyvec1 = b'\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96'
         for pid in pidlist:
-            bigpid = pid.ljust(16,b'\0')
-            bigpid = bigpid
+            bigpid = pid.encode('utf-8').ljust(16,b'\0')
             temp_key = PC1(keyvec1, bigpid, False)
             temp_key_sum = sum(temp_key) & 0xff
             found_key = None
@@ -424,6 +429,7 @@ class MobiBook:
             return ".azw3"
         return ".mobi"
 
+    # pids in pidlist may be unicode or bytearrays or bytes
     def processBook(self, pidlist):
         crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
         print("Crypto Type is: {0:d}".format(crypto_type))
@@ -445,6 +451,8 @@ class MobiBook:
         goodpids = []
         # print("DEBUG ==== pidlist = ", pidlist)
         for pid in pidlist:
+            if isinstance(pid,(bytearray,bytes)):
+                pid = pid.decode('utf-8')
             if len(pid)==10:
                 if checksumPid(pid[0:-2]) != pid:
                     print("Warning: PID {0} has incorrect checksum, should have been {1}".format(pid,checksumPid(pid[0:-2])))
@@ -457,8 +465,8 @@ class MobiBook:
         # print("======= DEBUG good pids = ", goodpids)
 
         if self.crypto_type == 1:
-            t1_keyvec = 'QDCVEPMU675RUBSZ'
-            if self.magic == 'TEXtREAd':
+            t1_keyvec = b'QDCVEPMU675RUBSZ'
+            if self.magic == b'TEXtREAd':
                 bookkey_data = self.sect[0x0E:0x0E+16]
             elif self.mobi_version < 0:
                 bookkey_data = self.sect[0x90:0x90+16]
@@ -473,7 +481,7 @@ class MobiBook:
                 raise DrmException("Encryption not initialised. 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 in {0:d} keys tried.".format(len(goodpids)))
+                raise DrmException("No key found in {0:d} PIDs tried.".format(len(goodpids)))
             # kill the drm keys
             self.patchSection(0, b'\0' * drm_size, drm_ptr)
             # kill the drm pointers
@@ -509,6 +517,7 @@ class MobiBook:
         print("done")
         return
 
+# pids in pidlist must be unicode
 def getUnencryptedBook(infile,pidlist):
     if not os.path.isfile(infile):
         raise DrmException("Input File Not Found.")
@@ -530,8 +539,7 @@ def cli_main():
         infile = argv[1]
         outfile = argv[2]
         if len(argv) == 4:
-            # convert from unicode to bytearray before splitting.
-            pidlist = argv[3].encode('utf-8').split(b',')
+            pidlist = argv[3].split(',')
         else:
             pidlist = []
         try:

DeDRM_plugin/zipfix.py

@@ -66,21 +66,21 @@ class fixZip:
 
     def uncompress(self, cmpdata):
         dc = zlib.decompressobj(-15)
-        data = ''
+        data = b''
         while len(cmpdata) > 0:
             if len(cmpdata) > _MAX_SIZE :
                 newdata = cmpdata[0:_MAX_SIZE]
                 cmpdata = cmpdata[_MAX_SIZE:]
             else:
                 newdata = cmpdata
-                cmpdata = ''
+                cmpdata = b''
             newdata = dc.decompress(newdata)
             unprocessed = dc.unconsumed_tail
             if len(unprocessed) == 0:
                 newdata += dc.flush()
             data += newdata
             cmpdata += unprocessed
-            unprocessed = ''
+            unprocessed = b''
         return data
 
     def getfiledata(self, zi):
@@ -123,7 +123,7 @@ class fixZip:
             mimeinfo.internal_attr = 1 # text file
             try:
                 # if the mimetype is present, get its info, including time-stamp
-                oldmimeinfo = self.inzip.getinfo('mimetype')
+                oldmimeinfo = self.inzip.getinfo(b'mimetype')
                 # copy across useful fields
                 mimeinfo.date_time = oldmimeinfo.date_time
                 mimeinfo.comment = oldmimeinfo.comment
@@ -137,7 +137,7 @@ class fixZip:
 
         # write the rest of the files
         for zinfo in self.inzip.infolist():
-            if zinfo.filename != "mimetype" or self.ztype != 'epub':
+            if zinfo.filename != b"mimetype" or self.ztype != 'epub':
                 data = None
                 try:
                     data = self.inzip.read(zinfo.filename)
@@ -153,6 +153,7 @@ class fixZip:
                 nzinfo.internal_attr=zinfo.internal_attr
                 nzinfo.external_attr=zinfo.external_attr
                 nzinfo.create_system=zinfo.create_system
+                nzinfo.flag_bits = zinfo.flag_bits & 0x800  # preserve UTF-8 flag
                 self.outzip.writestr(nzinfo,data)
 
         self.bzf.close()

FAQs.md

@@ -27,12 +27,12 @@ Verify the one of the following cryptographic hash values, using software of you
 #### Kindle for PC `KindleForPC-installer-1.17.44170.exe`:
 * MD-5: 53F793B562F4823721AA47D7DE099869
 * SHA-1: 73C404D719F0DD8D4AE1C2C96612B095D6C86255
-* SHA-256: 14E0F0053F1276C0C7C446892DC170344F707FBFE99B695176 2C120144163200
+* SHA-256: 14E0F0053F1276C0C7C446892DC170344F707FBFE99B6951762C120144163200
 
 #### Kindle for Mac `KindleForMac-44182.dmg`:
 * MD-5: E7E36D5369E1F3CF1D28E5D9115DF15F
 * SHA-1: 7AB9A86B954CB23D622BD79E3257F8E2182D791C
-* SHA-256: 28DC21246A9C7CDEDD2D6F0F4082E6BF7EF9DB9CE9D485548E 8A9E1D19EAE2AC. 
+* SHA-256: 28DC21246A9C7CDEDD2D6F0F4082E6BF7EF9DB9CE9D485548E8A9E1D19EAE2AC
 
 You will need to go to the preferences and uncheck the auto update checkbox. Then download and install 1.17 over the top of the newer installation. You'll also need to delete the KFX folders from your My Kindle Content folder. You may also need to take further action to prevent an auto update. The simplest wayis to find the 'updates' folder and replace it with a file. See [this thread] (http://www.mobileread.com/forums/showthread.php?t=283371) at MobileRead for a Script to do this on a PC. On a Mac you can find the folder at ~/Library/Application Support/Kindle/ just delete the folder 'updates' and save a blank text file called 'updates' in its place.
 
@@ -51,7 +51,9 @@ Mac Note: If the chmod command fails with a permission error try again using `su
 After restarting the Kindle program any books previously downloaded in KFX format will no longer open. You will need to remove them from your device and re-download them. All future downloads will use the older Kindle formats instead of KFX although they will continue to be placed in one individual subdirectory per book. Note that books soudl be downoad by right-click and 'Download', not by just opening the book. Recent (1.25+) versions of Kindle for Mac/PC may convert KF8 files to a new format that is not supported by these tools when the book is opened for reading.
 
 #### Decrypting KFX
-Thanks to work by several people, the tools can now decrypt KFX format ebooks from Kindle for Mac/PC version 1.26 or earlier (version later than 1.26 use a new encryption scheme for KFX files). In addition to the DeDRM plugin, calibre users will also need to install jhowell's KFX Input plugin which is available through the standard plugin menu in calibre, or directly from [his plugin thread](https://www.mobileread.com/forums/showthread.php?t=291290) on Mobileread. 
+Thanks to work by several people, the tools can now decrypt KFX format ebooks from Kindle for Mac/PC. In addition to the DeDRM plugin, calibre users will also need to install jhowell's KFX Input plugin which is available through the standard plugin menu in calibre, or directly from [his plugin thread](https://www.mobileread.com/forums/showthread.php?t=291290) on Mobileread. 
+
+It's quite possible that Amazon will update their KFX DeDRM to prevent DRM removal from KFX books again. So Remove DRM as soon as possible!
 
 #### Thanks
 Thanks to jhowell for his investigations into KFX format and the KFX Input plugin. Some of these instructions are from [his thread on the subject](https://www.mobileread.com/forums/showthread.php?t=283371) at MobileRead.

Obok_plugin/__init__.py

@@ -3,7 +3,7 @@ from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__version__ = '6.7.0'
+__version__ = '7.2.1'
 __docformat__ = 'restructuredtext en'
 
 #####################################################################
@@ -20,7 +20,7 @@ except NameError:
 PLUGIN_NAME = 'Obok DeDRM'
 PLUGIN_SAFE_NAME = PLUGIN_NAME.strip().lower().replace(' ', '_')
 PLUGIN_DESCRIPTION = _('Removes DRM from Kobo kepubs and adds them to the library.')
-PLUGIN_VERSION_TUPLE = (6, 7, 0)
+PLUGIN_VERSION_TUPLE = (7, 2, 1)
 PLUGIN_VERSION = '.'.join([str(x) for x in PLUGIN_VERSION_TUPLE])
 HELPFILE_NAME = PLUGIN_SAFE_NAME + '_Help.htm'
 PLUGIN_AUTHORS = 'Anon'

Obok_plugin/action.py

@@ -197,7 +197,7 @@ class InterfacePluginAction(InterfaceAction):
             # We will write the help file out every time, in case the user upgrades the plugin zip
             # and there is a newer help file contained within it.
             file_path = os.path.join(config_dir, 'plugins', HELPFILE_NAME)
-            file_data = self.load_resources(HELPFILE_NAME)[HELPFILE_NAME]
+            file_data = self.load_resources(HELPFILE_NAME)[HELPFILE_NAME].decode('utf-8')
             with open(file_path,'w') as f:
                 f.write(file_data)
             return file_path

Obok_plugin/obok/obok.py

@@ -1,6 +1,9 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
+# Version 4.1.0 February 2021
+# Add detection for Kobo directory location on Linux
+
 # Version 4.0.0 September 2020
 # Python 3.0
 #
@@ -365,9 +368,33 @@ class KoboLibrary(object):
                     self.kobodir = os.path.join(self.kobodir, "Kobo", "Kobo Desktop Edition")
                 elif sys.platform.startswith('darwin'):
                     self.kobodir = os.path.join(os.environ['HOME'], "Library", "Application Support", "Kobo", "Kobo Desktop Edition")
-            #elif linux_path != None:
-                # Probably Linux, let's get the wine prefix and path to Kobo.
-            #   self.kobodir = os.path.join(linux_path, "Local Settings", "Application Data", "Kobo", "Kobo Desktop Edition")
+                elif sys.platform.startswith('linux'):
+
+                    #sets ~/.config/calibre as the location to store the kobodir location info file and creates this directory if necessary
+                    kobodir_cache_dir = os.path.join(os.environ['HOME'], ".config", "calibre")
+                    if not os.path.isdir(kobodir_cache_dir):
+                        os.mkdir(kobodir_cache_dir)
+                    
+                    #appends the name of the file we're storing the kobodir location info to the above path
+                    kobodir_cache_file = str(kobodir_cache_dir) + "/" + "kobo location"
+                    
+                    """if the above file does not exist, recursively searches from the root
+                    of the filesystem until kobodir is found and stores the location of kobodir
+                    in that file so this loop can be skipped in the future"""
+                    original_stdout = sys.stdout
+                    if not os.path.isfile(kobodir_cache_file):
+                        for root, dirs, files in os.walk('/'):
+                            for file in files:
+                                if file == 'Kobo.sqlite':
+                                    kobo_linux_path = str(root)
+                                    with open(kobodir_cache_file, 'w') as f:
+                                        sys.stdout = f
+                                        print(kobo_linux_path, end='')
+                                        sys.stdout = original_stdout
+
+                    f = open(kobodir_cache_file, 'r' )
+                    self.kobodir = f.read()
+
             # desktop versions use Kobo.sqlite
             kobodb = os.path.join(self.kobodir, "Kobo.sqlite")
             # check for existence of file
@@ -443,15 +470,15 @@ class KoboLibrary(object):
         """The list of all MAC addresses on this machine."""
         macaddrs = []
         if sys.platform.startswith('win'):
-            c = re.compile('\s(' + '[0-9a-f]{2}-' * 5 + '[0-9a-f]{2})(\s|$)', re.IGNORECASE)
-            output = subprocess.Popen('ipconfig /all', shell=True, stdout=subprocess.PIPE, text=True).stdout
+            c = re.compile('\s?(' + '[0-9a-f]{2}[:\-]' * 5 + '[0-9a-f]{2})(\s|$)', re.IGNORECASE)
+            output = subprocess.Popen('wmic nic where PhysicalAdapter=True get MACAddress', shell=True, stdout=subprocess.PIPE, text=True).stdout
             for line in output:
                 m = c.search(line)
                 if m:
                     macaddrs.append(re.sub("-", ":", m.group(1)).upper())
         elif sys.platform.startswith('darwin'):
             c = re.compile('\s(' + '[0-9a-f]{2}:' * 5 + '[0-9a-f]{2})(\s|$)', re.IGNORECASE)
-            output = subprocess.check_output('/sbin/ifconfig -a', shell=True)
+            output = subprocess.check_output('/sbin/ifconfig -a', shell=True, encoding='utf-8')
             matches = c.findall(output)
             for m in matches:
                 # print "m:{0}".format(m[0])

Obok_plugin/translations/sv.po

@@ -8,7 +8,7 @@ msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2014-11-17 12:51+0100\n"
-"PO-Revision-Date: 2020-02-02 09:18+0100\n"
+"PO-Revision-Date: 2021-01-19 12:20+0100\n"
 "Language: sv\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
@@ -16,14 +16,14 @@ msgstr ""
 "Plural-Forms: nplurals=2; plural=(n != 1);\n"
 "Last-Translator: \n"
 "Language-Team: \n"
-"X-Generator: Poedit 2.2.4\n"
+"X-Generator: Poedit 2.4.2\n"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:80
 msgid ""
 "<p>No books found in Kobo Library\n"
 "Are you sure it's installed\\configured\\synchronized?"
 msgstr ""
-"<p>Inga böcker finns i Kobo-bibliotek\n"
+"<p>Inga böcker hittades i Kobo-bibliotek\n"
 "Är du säker på att den är installerad\\konfigurerad\\synkroniserad?"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:87
@@ -36,7 +36,7 @@ msgstr "Problem med att hämta nycklar med nyare obok-metod."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:97
 msgid "Found {0} possible keys to try."
-msgstr "Hittade {0} möjliga nycklar att pröva med."
+msgstr "Hittade {0} möjliga nycklar att försöka med."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:99
 msgid "<p>No userkeys found to decrypt books with. No point in proceeding."
@@ -46,7 +46,7 @@ msgstr ""
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:115
 msgid "{} - Decryption canceled by user."
-msgstr "{} - Dekryptering avbryts av användaren."
+msgstr "{} - Dekryptering avbröts av användaren."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:135
 msgid "{} - \"Add books\" canceled by user."
@@ -87,14 +87,14 @@ msgstr "dubblett upptäcktes"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:233
 msgid "{0} - Successfully added EPUB format to existing {1}"
-msgstr "{0} - Lade till EPUB-format till befintliga {1}"
+msgstr "{0} - EPUB-formatet har lagts till i befintliga {1}"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:236
 msgid ""
 "{0} - Error adding EPUB format to existing {1}. This really shouldn't happen."
 msgstr ""
-"{0} - Fel vid tillägg av EPUB-format till befintligt {1}. Det här borde inte "
-"hända."
+"{0} - Fel vid tilläggning av EPUB-formatet till befintliga {1}. Detta borde "
+"verkligen inte hända."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:259
 msgid "{} - \"Insert formats\" canceled by user."
@@ -103,44 +103,44 @@ msgstr "{} - \"Infoga format\" avbröts av användaren."
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:291
 msgid ""
 "<p><b>{0}</b> EPUB{2} successfully added to library.<br /><br /><b>{1}</b> "
-msgstr "<p><b>{0}</b> EPUB{2} lades till bibliotek.<br /><br /><b>{1}</b> "
+msgstr "<p><b>{0}</b> EPUB{2} har lagts till i bibliotek.<br /><br /><b>{1}</b> "
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:292
 msgid ""
 "not added because books with the same title/author were detected.<br /><br /"
 ">Would you like to try and add the EPUB format{0}"
 msgstr ""
-"inte tillagd eftersom böcker med samma titel/författare upptäcktes.<br/><br /"
-">Vill du försöka lägga till EPUB-formatet{0}"
+"lades inte till eftersom böcker med samma titel/författare upptäcktes.<br/"
+"><br />Vill du försöka lägga till EPUB-formatet{0}"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:293
 msgid ""
 " to those existing entries?<br /><br />NOTE: no pre-existing EPUBs will be "
 "overwritten."
 msgstr ""
-" till dessa befintliga poster?<br /><br />OBS: inga befintliga EPUB:er "
-"kommer att skrivas över."
+" till dessa befintliga poster?<br /><br />OBS: inga befintliga EPUB:er kommer "
+"att skrivas över."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:295
 msgid ""
 "{0} -- not added because of {1} in your library.\n"
 "\n"
 msgstr ""
-"{0} -- inte tillagd på grund av {1} i ditt bibliotek.\n"
+"{0} -- lades inte till på grund av {1} i ditt bibliotek.\n"
 "\n"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:297
 msgid "<p><b>{0}</b> -- not added because of {1} in your library.<br /><br />"
 msgstr ""
-"<p><b>{0}</b> -- inte tillagd på grund av {1} i ditt bibliotek.<br /><br />"
+"<p><b>{0}</b> -- lades inte till på grund av {1} i ditt bibliotek.<br /><br />"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:298
 msgid ""
 "Would you like to try and add the EPUB format to an available calibre "
 "duplicate?<br /><br />"
 msgstr ""
-"Vill du försöka lägga till EPUB-formatet till en tillgänglig calibre-"
-"dubblett?<br /><br />"
+"Vill du försöka lägga till EPUB-formatet till en tillgänglig calibre-dubblett?"
+"<br /><br />"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:299
 msgid "NOTE: no pre-existing EPUB will be overwritten."
@@ -148,23 +148,23 @@ msgstr "OBS: ingen befintlig EPUB kommer att skrivas över."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:346
 msgid "Trying key: "
-msgstr "Prövar nyckel: "
+msgstr "Försöker med nyckel: "
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:378
 msgid "Decryption failed, trying next key."
-msgstr "Det gick inte att dekryptera, prövar nästa nyckel."
+msgstr "Dekryptering misslyckades, försöker med nästa nyckel."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:382
 msgid "Unknown Error decrypting, trying next key.."
-msgstr "Okänt fel dekryptering, prövar nästa nyckel.."
+msgstr "Okänt fel vid dekryptering, försöker med nästa nyckel.."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:395
 msgid ""
 "<p>All selected Kobo books added as new calibre books or inserted into "
 "existing calibre ebooks.<br /><br />No issues."
 msgstr ""
-"<p>Alla valda Kobo-böcker läggs till som nya calibre-böcker eller infogas i "
-"befintliga calibre-e-böcker.<br /><br />Inga problem."
+"<p>Alla valda Kobo-böcker har lagts till som nya calibre-böcker eller infogats "
+"i befintliga calibre-e-böcker.<br /><br />Inga problem."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:399
 msgid "<p>{0} successfully added."
@@ -192,15 +192,14 @@ msgstr "<p><b>Nya böcker skapade:</b> {}</p>\n"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:418
 msgid "<p><b>Duplicates that weren't added:</b> {}</p>\n"
-msgstr "<p><b>Dubbletter som inte tillsattes:</b> {}</p>\n"
+msgstr "<p><b>Dubbletter som inte har lagts till:</b> {}</p>\n"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:426
 msgid "<p><b>Book imports cancelled by user:</b> {}</p>\n"
 msgstr "<p><b>Bokimport avbröts av användaren:</b> {}</p>\n"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:428
-msgid ""
-"<p><b>New EPUB formats inserted in existing calibre books:</b> {0}</p>\n"
+msgid "<p><b>New EPUB formats inserted in existing calibre books:</b> {0}</p>\n"
 msgstr ""
 "<p><b>Nya EPUB-format infogade i befintliga calibre-böcker:</b> {0}</p>\n"
 
@@ -208,8 +207,7 @@ msgstr ""
 msgid ""
 "<p><b>EPUB formats NOT inserted into existing calibre books:</b> {}<br />\n"
 msgstr ""
-"<p><b>EPUB-format som INTE infogats i befintliga calibre-böcker:</b> {}<br /"
-">\n"
+"<p><b>EPUB-format som INTE infogats i befintliga calibre-böcker:</b> {}<br />\n"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:435
 msgid ""
@@ -221,7 +219,7 @@ msgstr ""
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:444
 msgid "<p><b>Format imports cancelled by user:</b> {}</p>\n"
-msgstr "<p><b>Format-import avbröts av användaren:</b> {}</p>\n"
+msgstr "<p><b>Format-importen avbröts av användaren:</b> {}</p>\n"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:458
 msgid "Unknown Book Title"
@@ -233,11 +231,11 @@ msgstr "den kunde inte dekrypteras."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:462
 msgid ""
-"user CHOSE not to insert the new EPUB format, or all existing calibre "
-"entries HAD an EPUB format already."
+"user CHOSE not to insert the new EPUB format, or all existing calibre entries "
+"HAD an EPUB format already."
 msgstr ""
-"användaren VALDE att inte infoga det nya EPUB-formatet, eller alla "
-"befintliga calibre-poster hade redan ett EPUB-format."
+"användaren VALDE att inte infoga det nya EPUB-formatet, eller alla befintliga "
+"calibre-poster hade redan ett EPUB-format."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:464
 msgid "of unknown reasons. Gosh I'm embarrassed!"
@@ -245,7 +243,7 @@ msgstr "av okända skäl. Jag skäms!"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\action.py:465
 msgid "<p>{0} not added because {1}"
-msgstr "<p>{0} inte tillagd eftersom {1}"
+msgstr "<p>{0} lades inte till på grund av {1}"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\common_utils.py:226
 msgid "Help"
@@ -254,31 +252,31 @@ msgstr "Hjälp"
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\common_utils.py:235
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\utilities.py:214
 msgid "Restart required"
-msgstr "Omstart krävs"
+msgstr "Kräver omstart"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\common_utils.py:236
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\utilities.py:215
 msgid ""
 "Title image not found - you must restart Calibre before using this plugin!"
 msgstr ""
-"Titelbild hittades inte - du måste starta calibre innan du använder denna "
+"Titelbild hittades inte - du måste starta om calibre innan du använder denna "
 "insticksmodul!"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\common_utils.py:322
 msgid "Undefined"
-msgstr "Obestämd"
+msgstr "Odefinierad"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\config.py:30
 msgid "When should Obok try to insert EPUBs into existing calibre entries?"
-msgstr "När ska Obok försöka infoga EPUB:er i befintliga calibre-böcker?"
+msgstr "När ska Obok försöka infoga EPUB:er i befintliga calibre-poster?"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\config.py:33
 msgid ""
 "<p>Default behavior when duplicates are detected. None of the choices will "
 "cause calibre ebooks to be overwritten"
 msgstr ""
-"<p>Standardbeteende när dubbletter upptäcks. Inget av alternativen kommer "
-"att orsaka calibre-e-böcker att skrivas över"
+"<p>Standardbeteende när dubbletter upptäcks. Inget av alternativen kommer att "
+"orsaka att calibre-e-böcker skrivs över"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\config.py:35
 msgid "Ask"
@@ -323,7 +321,7 @@ msgstr "Välj alla böcker med DRM."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\dialogs.py:95
 msgid "All DRM free"
-msgstr "Alla DRM fria"
+msgstr "Alla utan DRM"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\dialogs.py:96
 msgid "Select all books without DRM."
@@ -355,12 +353,12 @@ msgstr "Tar bort DRM från Kobo-kepubs och lägger till dem i biblioteket."
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\obok\obok.py:162
 msgid "AES improper key used"
-msgstr "AES felaktig nyckel används"
+msgstr "Felaktig AES-nyckel används"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\obok\obok.py:167
 msgid "Failed to initialize AES key"
-msgstr "Det gick inte att initiera AES-nyckel"
+msgstr "Misslyckades med att initiera AES-nyckel"
 
 #: I:\Herramientas\PoeditPortable\App\Poedit\bin\obok_plugin-3.1.0_trad\obok\obok.py:175
 msgid "AES decryption failed"
-msgstr "AES dekryptering misslyckades"
+msgstr "AES-dekryptering misslyckades"

Other_Tools/Tetrachroma_FileOpen_ineptpdf/ineptpdf_8.4.51.pyw

@@ -2290,10 +2290,13 @@ class PDFDocument(object):
             import win32api
             import win32security
             import win32file
-            import winreg
         except:
             raise ADEPTError('PyWin Extension (Win32API module) needed.\n'+\
                              'Download from http://sourceforge.net/projects/pywin32/files/ ')
+        try:
+            import winreg
+        except ImportError:
+            import _winreg as winreg
         try:
             v0 = win32api.GetVolumeInformation('C:\\')
             v1 = win32api.GetSystemInfo()[6]

README.md

@@ -10,14 +10,12 @@ The individual scripts are now released as two plugins for calibre: DeDRM and Ob
 The DeDRM plugin handles books that use Amazon DRM, Adobe Digital Editions DRM (version 1), Barnes & Noble DRM, and some historical formats.
 The Obok plugin handles Kobo DRM.
 
-Users with calibre 5.x or later should use release 7.0.0b2 or later of the tools.
-Users with calibe 4.x or earlier should use release 6.8.0 of the tools.
-
-Developers might be interested in forking the repository, as it contains unzipped versions of those tools that are zipped to make the changes over time easier to follow.
+Users with calibre 5.x or later should use release 7.2.0 or later of the tools.
+Users with calibe 4.x or earlier should use release 6.8.x of the tools.
 
 For the latest Amazon KFX format, users of the calibre plugin should also install the KFX Input plugin from the standard calibre plugin menu. It's also available from the MobileRead thread here: https://www.mobileread.com/forums/showthread.php?t=291290
 
-Note that DRM can only be removed from KFX format files downloaded with Kindle for PC/Mac 1.26 or earlier. Amazon changes the DRM for KFX files in Kindle for PC/Mac 1.27 and later.
+Note that Amazon changes the DRM for KFX files frequently. What works for KFX today might not work tomorrow.
 
 I welcome contributions from others to improve these tools, from expanding the range of books handled, improving key retrieval,  to just general bug fixes, speed improvements and UI enhancements.
 

ReadMe_Overview.txt

@@ -26,7 +26,7 @@ The tools are provided in the form of plugins for calibre. Calibre is an open so
 
 DeDRM plugin for calibre (Mac OS X, Windows)
 -------------------------------------------------------
-calibe 5.x and later are now written in Python 3, and plugins must also use Python 3. If you have calibre 5, you must use version 7.x or later of the plugins. For calibre 4.x and earlier, use version 6.8.0 of the plugins.
+calibe 5.x and later are now written in Python 3, and plugins must also use Python 3. If you have calibre 5, you must use version 7.x or later of the plugins. For calibre 4.x and earlier, use version 6.8.x of the plugins.
 
 The DeDRM plugin for calibre removes DRM from your Kindle and Adobe DRM ebooks when they are imported to calibre. Just install the DeDRM plugin (DeDRM_plugin.zip), following the instructions and configuration directions provided in the ReadMe file and the help links in the plugin's configuration dialogs.