python list_dupes.py

Posted 2021-05-09

import hashlib, os
unique = dict()
for filename in os.listdir('.'):
    if os.path.isfile(filename):
        filehash = hashlib.md5(open(filename, 'rb').read()).hexdigest()

        if filehash not in unique: 
            unique[filehash] = filename
        else:
            print (filename + ' is a duplicate of ' + unique[filehash])