python 按文件大小查找重复项

Posted 2021-05-09

import os

from collections import defaultdict


def find_duplicates_by_size(files):
    """
    Description:
        Find duplicate files based solely on the size per file
    """
    file_sizes = defaultdict(list)
    for path in list(files):
        file_sizes[os.path.getsize(path)].append(path)

    duplicates = [x for x in file_sizes.values() if len(x) > 1]
    return [x for x in file_sizes if x.value in duplicates]