python_file_dupe.py

python_file_dupe.py

import os
import hashlib
from sets import Set

hash_set = Set([])
for dirpath, dir, files in os.walk("."):
    files

hasher = hashlib.md5()
for file in files:
    with open(file, 'rb') as af:
        hasher.update(af.read())
    filehash = h.hexdigest()
    if (filehash in s):
        print file
    else:
        hash_set.add(filehash)