Solution to PyPool 11/11/13 Problem: You have intercepted a coded message. (Also available in plain text.) Your objective is to identify the source of the material. You can see from the character encoding of the HTML document that the encoded message is in Unicode. You have also received intelligence that the original message is in English and t…

brutus

import string
from urllib.request import urlopen
from collections import Counter

def getCipherText():
    cipherreq = urlopen("http://pypool.daihuws.me.uk/crypto/encrypted.txt")
    cipherstr = cipherreq.read().decode("utf-8")
    cipherreq.close()
    return cipherstr

freqdict = Counter(getCipherText().translate(string.punctuation).split(sep=" "))

# Assume that the most common word is "the"
the = freqdict.most_common()[0]

the_offsets = [ord(c)-ord(t) for c,t in zip(the[0],"the")]

if all(x==the_offsets[0] for x in the_offsets):
    print("All Offsets equivalent for \"The\", going ahead with transposition\n\n")
    the_offset = the_offsets[0]
    clear_text=""
    awkward_bastards = []
    for c in getCipherText():
        if c in string.punctuation or c in string.whitespace:
            clear_line+=(c)
        else:
            try:
                clear_line+=(chr(ord(c)-the_offset))
            except ValueError:
                clear_line+=(c)
                awkward_bastards.append(c)
    
    print(clear_line)
    
    if awkward_bastards:
        print("\n\nThese characters failed translation and were left as-is: %s"%str(awkward_bastards))
else:
    print("This probably isn't a caeser cipher, give up: %s"%(str(the_offsets)))