Duplicate files search. Py3

duplicate_search.py

import os
import hashlib


def check_size(path, files):
    suspects = {}
    for file in files:
        size = os.path.getsize(os.path.join(path, file))
        if size in suspects:
            suspects[size].append(file)
        else:
            suspects[size] = [file]
    return (v for v in suspects.values() if len(v) > 1)


def check_hash(path, suspects, chunk=64*1024):
    for files in suspects:
        duplicated = {}
        for file in files:
            with open(os.path.join(path, file), 'rb') as f:
                hasher = hashlib.md5()
                buf = f.read(chunk)
                while len(buf) > 0:
                    hasher.update(buf)
                    buf = f.read(chunk)
                md5 = hasher.digest()
                duplicate = duplicated.get(md5, None)
                if duplicate:
                    print("Duplicate detected: %s and %s" % (file, duplicate))
                else:
                    duplicated[md5] = file


def find_duplicates(directory):
    files = [f for f in os.listdir(directory) if
             os.path.isfile(os.path.join(directory, f))]
    suspects = check_size(directory, files)
    check_hash(directory, suspects)


if __name__ == '__main__':
    while True:
        directory = input('Please provide directory path: \n')
        if os.path.exists(directory):
            find_duplicates(directory)
            break