使用不同的索引表解码base64就像字符串一样

Question

My problem is, that I have something encoded (base64 like) with a differnet index table:

0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz+/

instead of

ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/

so when I use base64.b64decode() it gives me a wrong result. Is there a way to set this table durring conversion (as a parameter maybe)?

Or should I "convert" the wrong base64 string, I mean replace 0 to A, 1 to B, etc... and than use base64decode? if so what is the best and fast workaround for this?

update1 : I use this, which works, but looks a bit slow, and unprofessional. :)

def correctbase64(str):
  dicta = [ ['0','A'], ['1','B'], ['2','C'], ['3','D'], ['4','E'], ['5','F'], ['6','G'], ['7','H'], ['8','I'], ['9','J'], ['A','K'], ['B','L'], ['C','M'], ['D','N'], ['E','O'], ['F','P'], ['G','Q'], ['H','R'], ['I','S'], ['J','T'], ['K','U'], ['L','V'], ['M','W'], ['N','X'], ['O','Y'], ['P','Z'], ['Q','a'], ['R','b'], ['S','c'], ['T','d'], ['U','e'], ['V','f'], ['W','g'], ['X','h'], ['Y','i'], ['Z','j'], ['a','k'], ['b','l'], ['c','m'], ['d','n'], ['e','o'], ['f','p'], ['g','q'], ['h','r'], ['i','s'], ['j','t'], ['k','u'], ['l','v'], ['m','w'], ['n','x'], ['o','y'], ['p','z'], ['q','0'], ['r','1'], ['s','2'], ['t','3'], ['u','4'], ['v','5'], ['w','6'], ['x','7'], ['y','8'], ['z','9'] ]
  l = list(str)
  for i in range(len(l)):
    for c in dicta:
      if l[i] == c[0]:
        l[i] = c[1]
        break
  return "".join(l)

Answer 1

Something like this should work (WARNING: untested code; may be full of mistakes):

import string

my_base64chars  = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz+/"
std_base64chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"

s = s.translate(string.maketrans(my_base64chars, std_base64chars))
data = base64.b64decode(s)

It isn't possible to make the standard base64 functions (or the lower-level ones in binascii that they call) use a custom table.

Answer 2

You can use translate() and maketrans() :

from string import maketrans

base64fixTable = maketrans("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz+/", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/");
def correctbase64(str):
    return str.translate(base64fixTable)

Answer 3

this will handle error TypeError: Incorrect padding

from string import maketrans
import base64
STANDARD_ALPHABET = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/'
CUSTOM_ALPHABET = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz+/'

def correctbase64(input):
    DECODE_TRANS = maketrans(CUSTOM_ALPHABET, STANDARD_ALPHABET)
    newStr =  input.translate(DECODE_TRANS)
    # Add '=' char at the end of the string
    newStr += '='
    return base64.b64decode(newStr)

print custom_base64decode('x/Tcw/g') # hello

Answer 4

print "Hello Reverse Engineering!\n"

import string
import base64


my_base64chars  = "WXYZlabcd3fghijko12e456789ABCDEFGHIJKL+/MNOPQRSTUVmn0pqrstuvwxyz"
std_base64chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"

s = 'whatever encoded message you have that used my_base64chars index'

c = s.translate(string.maketrans(my_base64chars, std_base64chars))
data = base64.b64decode(c)
print (data)

Answer 5

Use maketrans to build a translation table and then translate from the first alphabet to the second. Then base64 decode.

import string
import base64
def decode(str):
    #make a translation table.
    table = string.maketrans(
      #your alphabet
      string.digits + string.uppercase + string.lowercase + "+/",
      #the original alphabet
      string.uppercase + string.lowercase + string.digits + "+/"
    )
    #translate
    str.translate(s, table)

    #finally decode
    return base64.b64decode(str)