PYTHON查找和删除重复文件

# coding=gbk
# -*- coding: utf-8 -*- 
import os
import hashlib
from collections import defaultdict

def file_hash(file_path, block_size=65536):
    # 计算文件的MD5哈希值
    hasher = hashlib.md5()
    with open(file_path, 'rb') as f:
        for block in iter(lambda: f.read(block_size), b''):
            hasher.update(block)
    return hasher.hexdigest()

def find_duplicates(directory):
    file_sizes = defaultdict(list)
    duplicates = []

    # 遍历目录及其子目录，查找相同大小的文件
    for root, dirs, files in os.walk(directory):
        for filename in files:
            file_path = os.path.join(root, filename)
            size = os.path.getsize(file_path)
            file_sizes[size].append(file_path)

    # 对相同大小的文件进行进一步检查，使用MD5哈希值
    for size, paths in file_sizes.items():
        if len(paths) > 1:
            hash_dict = defaultdict(list)

            for file_path in paths:
                file_hash_val