play with the linkedin password hash file

lph.py

import hashlib
import shelve

def trim_hash(hash, offset=5):
    """outputs truncated hash
    """
    return '0' * offset + hash[offset:]

def write_word_to_shelf(shelf_fn, wordfile):
    """write hashes of words in wordfile
    to shelf, both 0 prefixed and full
    """
    shelf = shelve.open(shelf_fn)
    with open(wordfile, 'r') as f:
        for line in f:
            l = line.strip()
            ph = hashlib.sha1(l).hexdigest()
            shelf[ph] = l
            shelf[trim_hash(ph)] = l
    shelf.close()


def write_mine(pwd, shelf_fn):
    """adds your password to shelf
    """
    shelf = shelve.open(shelf_fn)
    h = hashlib.sha1(pwd).hexdigest()
    shelf[h] = pwd
    shelf[trim_hash(h)] = pwd
    shelf.close()
    print trim_hash(h), h

def dump(shelf_fn, out_fn, linkedin_hashes='combo_not.txt'):
    """dump 0 prefixed and full sha1 hashes to Python
    shelf. 
    hash is either 0 prefixed or full, so it contains both
    shelf[00000abcd...] = passwd1
    shelf[12345abcd...] = passwd1
    """
    shelf = shelve.open(shelf_fn)
    with open(out_fn, 'w') as w:
        with open(linkedin_hashes, 'r') as f:
            for i, line in enumerate(f):
                l = line.strip()
                try:
                    v = shelf[l]
                    print '%s : %s' % (v, l)
                    w.write('%s : %s\n' % (v, l))
                except KeyError:
                    pass
    shelf.close()

def check(p, linkedin_hashes='combo_not.txt'):
    """check if single password p is in file
    """
    h = hashlib.sha1(p).hexdigest()
    ph = trim_hash(h)

    c = (h, ph)

    with open(linkedin_hashes, 'r') as f:
        for line in f:
            if line.strip() in c:
                print 'bummer'