find_dupes.py

import glob
import sys
import os
import hashlib

root_dir = sys.argv[1]

hash_map = {}

for dirpath, dirs, files in os.walk(root_dir):
    for f in files:
        data = None
        md5 = None
        try:
            file_path = os.path.join(dirpath, f)
            with open(file_path, 'rb') as my_file:
                data = my_file.read()
            md5 = hashlib.md5(data).hexdigest()
            if md5 not in hash_map.keys():
                hash_map[md5] = []
            hash_map[md5].append(file_path)
        except:
            pass

dupes = list(filter(lambda x: len(x) > 1, hash_map.values()))
for d in dupes:
    print(','.join(d))