API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Feb 4th, 2010
1,605
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 27.20 KB | None | 0 0
raw download clone embed print report
  1. #!/usr/bin/env python
  2. # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
  3. #
  4. # erdr2pml.py
  5. #
  6. # This is a python script. You need a Python interpreter to run it.
  7. # For example, ActiveState Python, which exists for windows.
  8. # Changelog
  9. #
  10. #  Based on ereader2html version 0.08 plus some later small fixes
  11. #
  12. #  0.01 - Initial version
  13. #  0.02 - Support more eReader files. Support bold text and links. Fix PML decoder parsing bug.
  14. #  0.03 - Fix incorrect variable usage at one place.
  15. #  0.03b - enhancement by DeBockle (version 259 support)
  16. # Custom version 0.03 - no change to eReader support, only usability changes
  17. #   - start of pep-8 indentation (spaces not tab), fix trailing blanks
  18. #   - version variable, only one place to change
  19. #   - added main routine, now callable as a library/module,
  20. #     means tools can add optional support for ereader2html
  21. #   - outdir is no longer a mandatory parameter (defaults based on input name if missing)
  22. #   - time taken output to stdout
  23. #   - Psyco support - reduces runtime by a factor of (over) 3!
  24. #     E.g. (~600Kb file) 90 secs down to 24 secs
  25. #       - newstyle classes
  26. #       - changed map call to list comprehension
  27. #         may not work with python 2.3
  28. #         without Psyco this reduces runtime to 90%
  29. #         E.g. 90 secs down to 77 secs
  30. #         Psyco with map calls takes longer, do not run with map in Psyco JIT!
  31. #       - izip calls used instead of zip (if available), further reduction
  32. #         in run time (factor of 4.5).
  33. #         E.g. (~600Kb file) 90 secs down to 20 secs
  34. #   - Python 2.6+ support, avoid DeprecationWarning with sha/sha1
  35. #  0.04 - Footnote support, PML output, correct charset in html, support more PML tags
  36. #   - Feature change, dump out PML file
  37. #   - Added supprt for footnote tags. NOTE footnote ids appear to be bad (not usable)
  38. #       in some pdb files :-( due to the same id being used multiple times
  39. #   - Added correct charset encoding (pml is based on cp1252)
  40. #   - Added logging support.
  41. #  0.05 - Improved type 272 support for sidebars, links, chapters, metainfo, etc
  42. #  0.06 - Merge of 0.04 and 0.05. Improved HTML output
  43. #         Placed images in subfolder, so that it's possible to just
  44. #         drop the book.pml file onto DropBook to make an unencrypted
  45. #         copy of the eReader file.
  46. #         Using that with Calibre works a lot better than the HTML
  47. #         conversion in this code.
  48. #  0.07 - Further Improved type 272 support for sidebars with all earlier fixes
  49. #  0.08 - fixed typos, removed extraneous things
  50. #  0.09 - fixed typos in first_pages to first_page to again support older formats
  51. #  0.10 - minor cleanups
  52. #  0.11 - fixups for using correct xml for footnotes and sidebars for use with Dropbook
  53. #  0.12 - Fix added to prevent lowercasing of image names when the pml code itself uses a different case in the link name.
  54. #  0.13 - change to unbuffered stdout for use with gui front ends
  55.  
  56. __version__='0.13'
  57.  
  58. # Import Psyco if available
  59. try:
  60.     # Dumb speed hack 1
  61.     # http://psyco.sourceforge.net
  62.     import psyco
  63.     psyco.full()
  64.     pass
  65. except ImportError:
  66.     pass
  67. try:
  68.     # Dumb speed hack 2
  69.     # All map() calls converted to list comprehension (some use zip)
  70.     # override zip with izip - saves memory and in rough testing
  71.     # appears to be faster zip() is only used in the converted map() calls
  72.     from itertools import izip as zip
  73. except ImportError:
  74.     pass
  75.  
  76. class Unbuffered:
  77.     def __init__(self, stream):
  78.         self.stream = stream
  79.     def write(self, data):
  80.         self.stream.write(data)
  81.         self.stream.flush()
  82.     def __getattr__(self, attr):
  83.         return getattr(self.stream, attr)
  84.  
  85. import sys
  86. sys.stdout=Unbuffered(sys.stdout)
  87.  
  88. import struct, binascii, zlib, os, os.path, urllib
  89.  
  90. try:
  91.     from hashlib import sha1
  92. except ImportError:
  93.     # older Python release
  94.     import sha
  95.     sha1 = lambda s: sha.new(s)
  96. import cgi
  97. import logging
  98.  
  99. logging.basicConfig()
  100. #logging.basicConfig(level=logging.DEBUG)
  101.  
  102. ECB =   0
  103. CBC =   1
  104. class Des(object):
  105.     __pc1 = [56, 48, 40, 32, 24, 16,  8,  0, 57, 49, 41, 33, 25, 17,
  106.           9,  1, 58, 50, 42, 34, 26, 18, 10,  2, 59, 51, 43, 35,
  107.          62, 54, 46, 38, 30, 22, 14,  6, 61, 53, 45, 37, 29, 21,
  108.          13,  5, 60, 52, 44, 36, 28, 20, 12,  4, 27, 19, 11,  3]
  109.     __left_rotations = [1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1]
  110.     __pc2 = [13, 16, 10, 23,  0,  4,2, 27, 14,  5, 20,  9,
  111.         22, 18, 11,  3, 25,  7, 15,  6, 26, 19, 12,  1,
  112.         40, 51, 30, 36, 46, 54, 29, 39, 50, 44, 32, 47,
  113.         43, 48, 38, 55, 33, 52, 45, 41, 49, 35, 28, 31]
  114.     __ip = [57, 49, 41, 33, 25, 17, 9,  1,  59, 51, 43, 35, 27, 19, 11, 3,
  115.         61, 53, 45, 37, 29, 21, 13, 5,  63, 55, 47, 39, 31, 23, 15, 7,
  116.         56, 48, 40, 32, 24, 16, 8,  0,  58, 50, 42, 34, 26, 18, 10, 2,
  117.         60, 52, 44, 36, 28, 20, 12, 4,  62, 54, 46, 38, 30, 22, 14, 6]
  118.     __expansion_table = [31,  0,  1,  2,  3,  4, 3,  4,  5,  6,  7,  8,
  119.          7,  8,  9, 10, 11, 12,11, 12, 13, 14, 15, 16,
  120.         15, 16, 17, 18, 19, 20,19, 20, 21, 22, 23, 24,
  121.         23, 24, 25, 26, 27, 28,27, 28, 29, 30, 31,  0]
  122.     __sbox = [[14, 4, 13, 1, 2, 15, 11, 8, 3, 10, 6, 12, 5, 9, 0, 7,
  123.          0, 15, 7, 4, 14, 2, 13, 1, 10, 6, 12, 11, 9, 5, 3, 8,
  124.          4, 1, 14, 8, 13, 6, 2, 11, 15, 12, 9, 7, 3, 10, 5, 0,
  125.          15, 12, 8, 2, 4, 9, 1, 7, 5, 11, 3, 14, 10, 0, 6, 13],
  126.         [15, 1, 8, 14, 6, 11, 3, 4, 9, 7, 2, 13, 12, 0, 5, 10,
  127.          3, 13, 4, 7, 15, 2, 8, 14, 12, 0, 1, 10, 6, 9, 11, 5,
  128.          0, 14, 7, 11, 10, 4, 13, 1, 5, 8, 12, 6, 9, 3, 2, 15,
  129.          13, 8, 10, 1, 3, 15, 4, 2, 11, 6, 7, 12, 0, 5, 14, 9],
  130.         [10, 0, 9, 14, 6, 3, 15, 5, 1, 13, 12, 7, 11, 4, 2, 8,
  131.          13, 7, 0, 9, 3, 4, 6, 10, 2, 8, 5, 14, 12, 11, 15, 1,
  132.          13, 6, 4, 9, 8, 15, 3, 0, 11, 1, 2, 12, 5, 10, 14, 7,
  133.          1, 10, 13, 0, 6, 9, 8, 7, 4, 15, 14, 3, 11, 5, 2, 12],
  134.         [7, 13, 14, 3, 0, 6, 9, 10, 1, 2, 8, 5, 11, 12, 4, 15,
  135.          13, 8, 11, 5, 6, 15, 0, 3, 4, 7, 2, 12, 1, 10, 14, 9,
  136.          10, 6, 9, 0, 12, 11, 7, 13, 15, 1, 3, 14, 5, 2, 8, 4,
  137.          3, 15, 0, 6, 10, 1, 13, 8, 9, 4, 5, 11, 12, 7, 2, 14],
  138.         [2, 12, 4, 1, 7, 10, 11, 6, 8, 5, 3, 15, 13, 0, 14, 9,
  139.          14, 11, 2, 12, 4, 7, 13, 1, 5, 0, 15, 10, 3, 9, 8, 6,
  140.          4, 2, 1, 11, 10, 13, 7, 8, 15, 9, 12, 5, 6, 3, 0, 14,
  141.          11, 8, 12, 7, 1, 14, 2, 13, 6, 15, 0, 9, 10, 4, 5, 3],
  142.         [12, 1, 10, 15, 9, 2, 6, 8, 0, 13, 3, 4, 14, 7, 5, 11,
  143.          10, 15, 4, 2, 7, 12, 9, 5, 6, 1, 13, 14, 0, 11, 3, 8,
  144.          9, 14, 15, 5, 2, 8, 12, 3, 7, 0, 4, 10, 1, 13, 11, 6,
  145.          4, 3, 2, 12, 9, 5, 15, 10, 11, 14, 1, 7, 6, 0, 8, 13],
  146.         [4, 11, 2, 14, 15, 0, 8, 13, 3, 12, 9, 7, 5, 10, 6, 1,
  147.          13, 0, 11, 7, 4, 9, 1, 10, 14, 3, 5, 12, 2, 15, 8, 6,
  148.          1, 4, 11, 13, 12, 3, 7, 14, 10, 15, 6, 8, 0, 5, 9, 2,
  149.          6, 11, 13, 8, 1, 4, 10, 7, 9, 5, 0, 15, 14, 2, 3, 12],
  150.         [13, 2, 8, 4, 6, 15, 11, 1, 10, 9, 3, 14, 5, 0, 12, 7,
  151.          1, 15, 13, 8, 10, 3, 7, 4, 12, 5, 6, 11, 0, 14, 9, 2,
  152.          7, 11, 4, 1, 9, 12, 14, 2, 0, 6, 10, 13, 15, 3, 5, 8,
  153.          2, 1, 14, 7, 4, 10, 8, 13, 15, 12, 9, 0, 3, 5, 6, 11],]
  154.     __p = [15, 6, 19, 20, 28, 11,27, 16, 0, 14, 22, 25,
  155.         4, 17, 30, 9, 1, 7,23,13, 31, 26, 2, 8,18, 12, 29, 5, 21, 10,3, 24]
  156.     __fp = [39,  7, 47, 15, 55, 23, 63, 31,38,  6, 46, 14, 54, 22, 62, 30,
  157.         37,  5, 45, 13, 53, 21, 61, 29,36,  4, 44, 12, 52, 20, 60, 28,
  158.         35,  3, 43, 11, 51, 19, 59, 27,34,  2, 42, 10, 50, 18, 58, 26,
  159.         33,  1, 41,  9, 49, 17, 57, 25,32,  0, 40,  8, 48, 16, 56, 24]
  160.     # Type of crypting being done
  161.     ENCRYPT =   0x00
  162.     DECRYPT =   0x01
  163.     def __init__(self, key, mode=ECB, IV=None):
  164.         if len(key) != 8:
  165.             raise ValueError("Invalid DES key size. Key must be exactly 8 bytes long.")
  166.         self.block_size = 8
  167.         self.key_size = 8
  168.         self.__padding = ''
  169.         self.setMode(mode)
  170.         if IV:
  171.             self.setIV(IV)
  172.         self.L = []
  173.         self.R = []
  174.         self.Kn = [ [0] * 48 ] * 16 # 16 48-bit keys (K1 - K16)
  175.         self.final = []
  176.         self.setKey(key)
  177.     def getKey(self):
  178.         return self.__key
  179.     def setKey(self, key):
  180.         self.__key = key
  181.         self.__create_sub_keys()
  182.     def getMode(self):
  183.         return self.__mode
  184.     def setMode(self, mode):
  185.         self.__mode = mode
  186.     def getIV(self):
  187.         return self.__iv
  188.     def setIV(self, IV):
  189.         if not IV or len(IV) != self.block_size:
  190.             raise ValueError("Invalid Initial Value (IV), must be a multiple of " + str(self.block_size) + " bytes")
  191.         self.__iv = IV
  192.     def getPadding(self):
  193.         return self.__padding
  194.     def __String_to_BitList(self, data):
  195.         l = len(data) * 8
  196.         result = [0] * l
  197.         pos = 0
  198.         for c in data:
  199.             i = 7
  200.             ch = ord(c)
  201.             while i >= 0:
  202.                 if ch & (1 << i) != 0:
  203.                     result[pos] = 1
  204.                 else:
  205.                     result[pos] = 0
  206.                 pos += 1
  207.                 i -= 1
  208.         return result
  209.     def __BitList_to_String(self, data):
  210.         result = ''
  211.         pos = 0
  212.         c = 0
  213.         while pos < len(data):
  214.             c += data[pos] << (7 - (pos % 8))
  215.             if (pos % 8) == 7:
  216.                 result += chr(c)
  217.                 c = 0
  218.             pos += 1
  219.         return result
  220.     def __permutate(self, table, block):
  221.         return [block[x] for x in table]
  222.     def __create_sub_keys(self):
  223.         key = self.__permutate(Des.__pc1, self.__String_to_BitList(self.getKey()))
  224.         i = 0
  225.         self.L = key[:28]
  226.         self.R = key[28:]
  227.         while i < 16:
  228.             j = 0
  229.             while j < Des.__left_rotations[i]:
  230.                 self.L.append(self.L[0])
  231.                 del self.L[0]
  232.                 self.R.append(self.R[0])
  233.                 del self.R[0]
  234.                 j += 1
  235.             self.Kn[i] = self.__permutate(Des.__pc2, self.L + self.R)
  236.             i += 1
  237.     def __des_crypt(self, block, crypt_type):
  238.         block = self.__permutate(Des.__ip, block)
  239.         self.L = block[:32]
  240.         self.R = block[32:]
  241.         if crypt_type == Des.ENCRYPT:
  242.             iteration = 0
  243.             iteration_adjustment = 1
  244.         else:
  245.             iteration = 15
  246.             iteration_adjustment = -1
  247.         i = 0
  248.         while i < 16:
  249.             tempR = self.R[:]
  250.             self.R = self.__permutate(Des.__expansion_table, self.R)
  251.             self.R = [x ^ y for x,y in zip(self.R, self.Kn[iteration])]
  252.             B = [self.R[:6], self.R[6:12], self.R[12:18], self.R[18:24], self.R[24:30], self.R[30:36], self.R[36:42], self.R[42:]]
  253.             j = 0
  254.             Bn = [0] * 32
  255.             pos = 0
  256.             while j < 8:
  257.                 m = (B[j][0] << 1) + B[j][5]
  258.                 n = (B[j][1] << 3) + (B[j][2] << 2) + (B[j][3] << 1) + B[j][4]
  259.                 v = Des.__sbox[j][(m << 4) + n]
  260.                 Bn[pos] = (v & 8) >> 3
  261.                 Bn[pos + 1] = (v & 4) >> 2
  262.                 Bn[pos + 2] = (v & 2) >> 1
  263.                 Bn[pos + 3] = v & 1
  264.                 pos += 4
  265.                 j += 1
  266.             self.R = self.__permutate(Des.__p, Bn)
  267.             self.R = [x ^ y for x, y in zip(self.R, self.L)]
  268.             self.L = tempR
  269.             i += 1
  270.             iteration += iteration_adjustment
  271.         self.final = self.__permutate(Des.__fp, self.R + self.L)
  272.         return self.final
  273.     def crypt(self, data, crypt_type):
  274.         if not data:
  275.             return ''
  276.         if len(data) % self.block_size != 0:
  277.             if crypt_type == Des.DECRYPT: # Decryption must work on 8 byte blocks
  278.                 raise ValueError("Invalid data length, data must be a multiple of " + str(self.block_size) + " bytes\n.")
  279.             if not self.getPadding():
  280.                 raise ValueError("Invalid data length, data must be a multiple of " + str(self.block_size) + " bytes\n. Try setting the optional padding character")
  281.             else:
  282.                 data += (self.block_size - (len(data) % self.block_size)) * self.getPadding()
  283.         if self.getMode() == CBC:
  284.             if self.getIV():
  285.                 iv = self.__String_to_BitList(self.getIV())
  286.             else:
  287.                 raise ValueError("For CBC mode, you must supply the Initial Value (IV) for ciphering")
  288.         i = 0
  289.         dict = {}
  290.         result = []
  291.         while i < len(data):
  292.             block = self.__String_to_BitList(data[i:i+8])
  293.             if self.getMode() == CBC:
  294.                 if crypt_type == Des.ENCRYPT:
  295.                     block = [x ^ y for x, y in zip(block, iv)]
  296.                 processed_block = self.__des_crypt(block, crypt_type)
  297.                 if crypt_type == Des.DECRYPT:
  298.                     processed_block = [x ^ y for x, y in zip(processed_block, iv)]
  299.                     iv = block
  300.                 else:
  301.                     iv = processed_block
  302.             else:
  303.                 processed_block = self.__des_crypt(block, crypt_type)
  304.             result.append(self.__BitList_to_String(processed_block))
  305.             i += 8
  306.         if crypt_type == Des.DECRYPT and self.getPadding():
  307.             s = result[-1]
  308.             while s[-1] == self.getPadding():
  309.                 s = s[:-1]
  310.             result[-1] = s
  311.         return ''.join(result)
  312.     def encrypt(self, data, pad=''):
  313.         self.__padding = pad
  314.         return self.crypt(data, Des.ENCRYPT)
  315.     def decrypt(self, data, pad=''):
  316.         self.__padding = pad
  317.         return self.crypt(data, Des.DECRYPT)
  318.  
  319. class Sectionizer(object):
  320.     def __init__(self, filename, ident):
  321.         self.contents = file(filename, 'rb').read()
  322.         self.header = self.contents[0:72]
  323.         self.num_sections, = struct.unpack('>H', self.contents[76:78])
  324.         if self.header[0x3C:0x3C+8] != ident:
  325.             raise ValueError('Invalid file format')
  326.         self.sections = []
  327.         for i in xrange(self.num_sections):
  328.             offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.contents[78+i*8:78+i*8+8])
  329.             flags, val = a1, a2<<16|a3<<8|a4
  330.             self.sections.append( (offset, flags, val) )
  331.     def loadSection(self, section):
  332.         if section + 1 == self.num_sections:
  333.             end_off = len(self.contents)
  334.         else:
  335.             end_off = self.sections[section + 1][0]
  336.         off = self.sections[section][0]
  337.         return self.contents[off:end_off]
  338.  
  339. def sanitizeFileName(s):
  340.     r = ''
  341.     for c in s:
  342.         if c in "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-":
  343.             r += c
  344.     return r
  345.  
  346. def fixKey(key):
  347.     def fixByte(b):
  348.         return b ^ ((b ^ (b<<1) ^ (b<<2) ^ (b<<3) ^ (b<<4) ^ (b<<5) ^ (b<<6) ^ (b<<7) ^ 0x80) & 0x80)
  349.     return  "".join([chr(fixByte(ord(a))) for a in key])
  350.  
  351. def deXOR(text, sp, table):
  352.     r=''
  353.     j = sp
  354.     for i in xrange(len(text)):
  355.         r += chr(ord(table[j]) ^ ord(text[i]))
  356.         j = j + 1
  357.         if j == len(table):
  358.             j = 0
  359.     return r
  360.  
  361. class EreaderProcessor(object):
  362.     def __init__(self, section_reader, username, creditcard):
  363.         self.section_reader = section_reader
  364.         data = section_reader(0)
  365.         version,  = struct.unpack('>H', data[0:2])
  366.         self.version = version
  367.         logging.info('eReader file format version %s', version)
  368.         if version != 272 and version != 260 and version != 259:
  369.             raise ValueError('incorrect eReader version %d (error 1)' % version)
  370.         data = section_reader(1)
  371.         self.data = data
  372.         des = Des(fixKey(data[0:8]))
  373.         cookie_shuf, cookie_size = struct.unpack('>LL', des.decrypt(data[-8:]))
  374.         if cookie_shuf < 3 or cookie_shuf > 0x14 or cookie_size < 0xf0 or cookie_size > 0x200:
  375.             raise ValueError('incorrect eReader version (error 2)')
  376.         input = des.decrypt(data[-cookie_size:])
  377.         def unshuff(data, shuf):
  378.             r = [''] * len(data)
  379.             j = 0
  380.             for i in xrange(len(data)):
  381.                 j = (j + shuf) % len(data)
  382.                 r[j] = data[i]
  383.             assert  len("".join(r)) == len(data)
  384.             return "".join(r)
  385.         r = unshuff(input[0:-8], cookie_shuf)
  386.  
  387.         def fixUsername(s):
  388.             r = ''
  389.             for c in s.lower():
  390.                 if (c >= 'a' and c <= 'z' or c >= '0' and c <= '9'):
  391.                     r += c
  392.             return r
  393.  
  394.         user_key = struct.pack('>LL', binascii.crc32(fixUsername(username)) & 0xffffffff, binascii.crc32(creditcard[-8:])& 0xffffffff)
  395.         drm_sub_version = struct.unpack('>H', r[0:2])[0]
  396.         self.num_text_pages = struct.unpack('>H', r[2:4])[0] - 1
  397.         self.num_image_pages = struct.unpack('>H', r[26:26+2])[0]
  398.         self.first_image_page = struct.unpack('>H', r[24:24+2])[0]
  399.         if self.version == 272:
  400.             self.num_footnote_pages = struct.unpack('>H', r[46:46+2])[0]
  401.             self.first_footnote_page = struct.unpack('>H', r[44:44+2])[0]
  402.             self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
  403.             self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
  404.             # self.num_bookinfo_pages = struct.unpack('>H', r[34:34+2])[0]
  405.             # self.first_bookinfo_page = struct.unpack('>H', r[32:32+2])[0]
  406.             # self.num_chapter_pages = struct.unpack('>H', r[22:22+2])[0]
  407.             # self.first_chapter_page = struct.unpack('>H', r[20:20+2])[0]
  408.             # self.num_link_pages = struct.unpack('>H', r[30:30+2])[0]
  409.             # self.first_link_page = struct.unpack('>H', r[28:28+2])[0]
  410.             # self.num_xtextsize_pages = struct.unpack('>H', r[54:54+2])[0]
  411.             # self.first_xtextsize_page = struct.unpack('>H', r[52:52+2])[0]
  412.  
  413.             # **before** data record 1 was decrypted and unshuffled, it contained data
  414.             # to create an XOR table and which is used to fix footnote record 0, link records, chapter records, etc
  415.             self.xortable_offset  = struct.unpack('>H', r[40:40+2])[0]
  416.             self.xortable_size = struct.unpack('>H', r[42:42+2])[0]
  417.             self.xortable = self.data[self.xortable_offset:self.xortable_offset + self.xortable_size]
  418.         else:
  419.             self.num_footnote_pages = 0
  420.             self.num_sidebar_pages = 0
  421.             self.first_footnote_page = -1
  422.             self.first_sidebar_page = -1
  423.             # self.num_bookinfo_pages = 0
  424.             # self.num_chapter_pages = 0
  425.             # self.num_link_pages = 0
  426.             # self.num_xtextsize_pages = 0
  427.             # self.first_bookinfo_page = -1
  428.             # self.first_chapter_page = -1
  429.             # self.first_link_page = -1
  430.             # self.first_xtextsize_page = -1
  431.  
  432.         logging.debug('self.num_text_pages %d', self.num_text_pages)
  433.         logging.debug('self.num_footnote_pages %d, self.first_footnote_page %d', self.num_footnote_pages , self.first_footnote_page)
  434.         logging.debug('self.num_sidebar_pages %d, self.first_sidebar_page %d', self.num_sidebar_pages , self.first_sidebar_page)
  435.         self.flags = struct.unpack('>L', r[4:8])[0]
  436.         reqd_flags = (1<<9) | (1<<7) | (1<<10)
  437.         if (self.flags & reqd_flags) != reqd_flags:
  438.             print "Flags: 0x%X" % self.flags
  439.             raise ValueError('incompatible eReader file')
  440.         des = Des(fixKey(user_key))
  441.         if version == 259:
  442.             if drm_sub_version != 7:
  443.                 raise ValueError('incorrect eReader version %d (error 3)' % drm_sub_version)
  444.             encrypted_key_sha = r[44:44+20]
  445.             encrypted_key = r[64:64+8]
  446.         elif version == 260:
  447.             if drm_sub_version != 13:
  448.                 raise ValueError('incorrect eReader version %d (error 3)' % drm_sub_version)
  449.             encrypted_key = r[44:44+8]
  450.             encrypted_key_sha = r[52:52+20]
  451.         elif version == 272:
  452.             encrypted_key = r[172:172+8]
  453.             encrypted_key_sha = r[56:56+20]
  454.         self.content_key = des.decrypt(encrypted_key)
  455.         if sha1(self.content_key).digest() != encrypted_key_sha:
  456.             raise ValueError('Incorrect Name and/or Credit Card')
  457.  
  458.     def getNumImages(self):
  459.         return self.num_image_pages
  460.  
  461.     def getImage(self, i):
  462.         sect = self.section_reader(self.first_image_page + i)
  463.         name = sect[4:4+32].strip('\0')
  464.         data = sect[62:]
  465.         return sanitizeFileName(name), data
  466.  
  467.     def cleanPML(self,pml):
  468.         # Update old \b font tag with correct \B bold font tag
  469.         pml2 = pml.replace('\\b', '\\B')
  470.         # Convert special characters to proper PML code.  High ASCII start at (\x82, \a130) and go up to (\xff, \a255)
  471.         for k in xrange(130,256):
  472.             # a2b_hex takes in a hexidecimal as a string and converts it
  473.             # to a binary ascii code that we search and replace for
  474.             badChar=binascii.a2b_hex('%02x' % k)
  475.             pml2 = pml2.replace(badChar, '\\a%03d' % k)
  476.             #end for k
  477.         return pml2
  478.  
  479.     # def getChapterNamePMLOffsetData(self):
  480.     #     cv = ''
  481.     #     if self.num_chapter_pages > 0:
  482.     #         for i in xrange(self.num_chapter_pages):
  483.     #             chaps = self.section_reader(self.first_chapter_page + i)
  484.     #             j = i % self.xortable_size
  485.     #             offname = deXOR(chaps, j, self.xortable)
  486.     #             offset = struct.unpack('>L', offname[0:4])[0]
  487.     #             name = offname[4:].strip('\0')
  488.     #             cv += '%d|%s\n' % (offset, name)
  489.     #     return cv
  490.  
  491.     # def getLinkNamePMLOffsetData(self):
  492.     #     lv = ''
  493.     #     if self.num_link_pages > 0:
  494.     #         for i in xrange(self.num_link_pages):
  495.     #             links = self.section_reader(self.first_link_page + i)
  496.     #             j = i % self.xortable_size
  497.     #             offname = deXOR(links, j, self.xortable)
  498.     #             offset = struct.unpack('>L', offname[0:4])[0]
  499.     #             name = offname[4:].strip('\0')
  500.     #             lv += '%d|%s\n' % (offset, name)
  501.     #     return lv
  502.  
  503.     # def getExpandedTextSizesData(self):
  504.     #      ts = ''
  505.     #      if self.num_xtextsize_pages > 0:
  506.     #          tsize = deXOR(self.section_reader(self.first_xtextsize_page), 0, self.xortable)
  507.     #          for i in xrange(self.num_text_pages):
  508.     #              xsize = struct.unpack('>H', tsize[0:2])[0]
  509.     #              ts += "%d\n" % xsize
  510.     #              tsize = tsize[2:]
  511.     #      return ts
  512.  
  513.     # def getBookInfo(self):
  514.     #     bkinfo = ''
  515.     #     if self.num_bookinfo_pages > 0:
  516.     #         info = self.section_reader(self.first_bookinfo_page)
  517.     #         bkinfo = deXOR(info, 0, self.xortable)
  518.     #         bkinfo = bkinfo.replace('\0','|')
  519.     #         bkinfo += '\n'
  520.     #     return bkinfo
  521.  
  522.     def getText(self):
  523.         des = Des(fixKey(self.content_key))
  524.         r = ''
  525.         for i in xrange(self.num_text_pages):
  526.             logging.debug('get page %d', i)
  527.             r += zlib.decompress(des.decrypt(self.section_reader(1 + i)))
  528.              
  529.         # now handle footnotes pages
  530.         if self.num_footnote_pages > 0:
  531.             r += '\n'
  532.             # the record 0 of the footnote section must pass through the Xor Table to make it useful
  533.             sect = self.section_reader(self.first_footnote_page)
  534.             fnote_ids = deXOR(sect, 0, self.xortable)
  535.             # the remaining records of the footnote sections need to be decoded with the content_key and zlib inflated
  536.             des = Des(fixKey(self.content_key))
  537.             for i in xrange(1,self.num_footnote_pages):
  538.                 logging.debug('get footnotepage %d', i)
  539.                 id_len = ord(fnote_ids[2])
  540.                 id = fnote_ids[3:3+id_len]
  541.                 fmarker = '<footnote id="%s">\n' % id
  542.                 fmarker += zlib.decompress(des.decrypt(self.section_reader(self.first_footnote_page + i)))
  543.                 fmarker += '\n</footnote>\n'
  544.                 r += fmarker
  545.                 fnote_ids = fnote_ids[id_len+4:]
  546.  
  547.         # now handle sidebar pages
  548.         if self.num_sidebar_pages > 0:
  549.             r += '\n'
  550.             # the record 0 of the sidebar section must pass through the Xor Table to make it useful
  551.             sect = self.section_reader(self.first_sidebar_page)
  552.             sbar_ids = deXOR(sect, 0, self.xortable)
  553.             # the remaining records of the sidebar sections need to be decoded with the content_key and zlib inflated
  554.             des = Des(fixKey(self.content_key))
  555.             for i in xrange(1,self.num_sidebar_pages):
  556.                 id_len = ord(sbar_ids[2])
  557.                 id = sbar_ids[3:3+id_len]
  558.                 smarker = '<sidebar id="%s">\n' % id
  559.                 smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_footnote_page + i)))
  560.                 smarker += '\n</sidebar>\n'
  561.                 r += smarker
  562.                 sbar_ids = sbar_ids[id_len+4:]
  563.  
  564.         return r
  565.  
  566. def convertEreaderToPml(infile, name, cc, outdir):
  567.     if not os.path.exists(outdir):
  568.         os.makedirs(outdir)
  569.  
  570.     print "   Decoding File"
  571.     sect = Sectionizer(infile, 'PNRdPPrs')
  572.     er = EreaderProcessor(sect.loadSection, name, cc)
  573.  
  574.     if er.getNumImages() > 0:
  575.         print "   Extracting images"
  576.         imagedir = bookname + '_img/'
  577.         imagedirpath = os.path.join(outdir,imagedir)
  578.         if not os.path.exists(imagedirpath):
  579.             os.makedirs(imagedirpath)
  580.         for i in xrange(er.getNumImages()):
  581.             name, contents = er.getImage(i)
  582.             file(os.path.join(imagedirpath, name), 'wb').write(contents)
  583.  
  584.     print "   Extracting pml"
  585.     pml_string = er.getText()
  586.     pmlfilename = bookname + ".pml"
  587.     file(os.path.join(outdir, pmlfilename),'wb').write(pml_string)
  588.  
  589.     # bkinfo = er.getBookInfo()
  590.     # if bkinfo != '':
  591.     #     print "   Extracting book meta information"
  592.     #     file(os.path.join(outdir, 'bookinfo.txt'),'wb').write(bkinfo)
  593.  
  594.  
  595. def main(argv=None):
  596.     global bookname
  597.     if argv is None:
  598.         argv = sys.argv
  599.    
  600.     print "eRdr2Pml v%s. Copyright (c) 2009 The Dark Reverser" % __version__
  601.  
  602.     if len(argv)!=4 and len(argv)!=5:
  603.         print "Converts DRMed eReader books to PML Source"
  604.         print "Usage:"
  605.         print "  erdr2pml infile.pdb [outdir] \"your name\" credit_card_number "
  606.         print "Note:"
  607.         print "  if ommitted, outdir defaults based on 'infile.pdb'"
  608.         print "  It's enough to enter the last 8 digits of the credit card number"
  609.         return 1
  610.     else:
  611.         if len(argv)==4:
  612.             infile, name, cc = argv[1], argv[2], argv[3]
  613.             outdir = infile[:-4] + '_Source'
  614.         elif len(argv)==5:
  615.             infile, outdir, name, cc = argv[1], argv[2], argv[3], argv[4]
  616.         bookname = os.path.splitext(os.path.basename(infile))[0]
  617.  
  618.         try:
  619.             print "Processing..."
  620.             import time
  621.             start_time = time.time()
  622.             convertEreaderToPml(infile, name, cc, outdir)
  623.             end_time = time.time()
  624.             search_time = end_time - start_time
  625.             print 'elapsed time: %.2f seconds' % (search_time, )
  626.             print 'output in %s' % outdir
  627.             print "done"
  628.         except ValueError, e:
  629.             print "Error: %s" % e
  630.             return 1
  631.     return 0
  632.  
  633. if __name__ == "__main__":
  634.     #import cProfile
  635.     #command = """sys.exit(main())"""
  636.     #cProfile.runctx( command, globals(), locals(), filename="cprofile.profile" )
  637.    
  638.     sys.exit(main())
  639.  
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!