Find duplicate files with pathlib

from collections import defaultdict
from pathlib import Path
from pprint import pprint
from hashlib import md5


def find_files(directory):
    for path in directory.rglob('*'):
        if path.is_file():
            yield path


hashes = defaultdict(list)
for path in find_files(Path.cwd()):
    key = md5(path.read_bytes()).hexdigest()
    hashes[key].append(path)

pprint(hashes)