challenge4.py

#!/usr/bin/env python3

# Code By CC Oosting (TheRealProcyon)
# Includes code written by David Buchanan
# This adapted code consists of the byte_frequency variable and the frequency_analysis function

from operator import itemgetter
from operator import xor
from types import *
import re
import string
import os


byte_frequency = [0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.022298, 0.000000, 0.000000, 0.022298, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.166921, 0.002692, 0.000806, 0.000006, 0.000012, 0.000006, 0.000000, 0.017219,
                  0.000454, 0.000454, 0.000525, 0.000000, 0.015315, 0.004441, 0.007198, 0.000143,
                  0.000131, 0.000406, 0.000072, 0.000078, 0.000060, 0.000078, 0.000042, 0.000036,
                  0.000060, 0.000066, 0.001528, 0.001158, 0.000000, 0.000000, 0.000000, 0.001206,
                  0.000012, 0.004309, 0.000746, 0.001116, 0.001444, 0.001868, 0.000800, 0.001152,
                  0.001844, 0.004972, 0.000078, 0.000525, 0.000943, 0.001325, 0.001086, 0.001397,
                  0.001027, 0.000507, 0.001265, 0.001725, 0.003408, 0.000663, 0.000310, 0.001528,
                  0.000036, 0.000848, 0.000006, 0.000024, 0.000000, 0.000024, 0.000000, 0.000024,
                  0.000000, 0.054212, 0.009675, 0.016813, 0.031203, 0.090035, 0.013417, 0.016419,
                  0.045247, 0.046572, 0.001325, 0.007174, 0.030159, 0.013399, 0.046978, 0.055173,
                  0.010719, 0.000806, 0.038198, 0.041666, 0.069420, 0.023080, 0.005437, 0.016091,
                  0.001015, 0.014575, 0.000472, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000,
                  0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000, 0.000000]


def main():

    xoring()
    in_progress()


def xoring():

    with open('4.txt', 'r') as myfile:
        for lines in myfile:
            lines = lines.strip()
            if len(lines) == 60:
                line_length_half = int(len(lines) / 2)

                for hexnumber in range(0xff):
                    hexnumber = hex(hexnumber)
                    hexnumber = hexnumber.replace('0x', '')
                    if len(hexnumber) == 1:
                        hex_number_extended = hexnumber * len(lines)
                    else:
                        hex_number_extended = hexnumber * line_length_half

                    lines_bytearray = bytearray.fromhex(lines)
                    hexnumber_bytearray = bytearray.fromhex(hex_number_extended)

                    xored = bytearray(lines_xor ^ hexnumber_xor for lines_xor, hexnumber_xor
                                      in zip(lines_bytearray, hexnumber_bytearray))
                    text = xored.decode(encoding='utf-8', errors='replace')

                    try:
                        with open('file-complete.txt', 'a+') as file1:
                            if all(characters in string.printable for characters in text):
                                file1.write(text + '\n')
                                file1.close()

                    except FileExistsError:
                        os.remove('file-complete.txt')
                        with open('file-complete.txt', 'a+') as file1:
                            if all(characters in string.printable for characters in text):
                                file1.write(text + '\n')
                                file1.close()


def frequency_analysis(text):

    assert (type(text) is bytes)
    # frequency count
    freqs = [0] * 256
    for char in text:
        freqs[char] += 1
    # normalise
    total = sum(freqs)
    freqs = [f / total for f in freqs]
    # calculate sum of squares of differences
    score = sum((a - b) ** 2 for a, b in zip(freqs, byte_frequency))
    return score


#
# noinspection PyTypeChecker
def in_progress():

    with open('file-complete.txt', 'r') as file2:
        frequency_dict = {}
        for lines in file2:
            lines = lines.strip()

            if not re.match(r'^\s*$', lines):
                analyzed_lines = frequency_analysis(bytes(lines, encoding="utf-8"))
                frequency_dict.update({lines: analyzed_lines})

        frequency_dict = dict(sorted(frequency_dict.items(), key=itemgetter(1)))
        print(list(frequency_dict.keys())[0])


if __name__ == '__main__':
    main()