在Python中的多个目录中查找相同的文件

import os
import hashlib

def calculate_hash(file_path):
    with open(file_path, 'rb') as f:
        data = f.read()
        file_hash = hashlib.md5(data).hexdigest()
    return file_hash

def find_duplicate_files(directory):
    file_hash_dict = {}
    duplicate_files = []

    for root, dirs, files in os.walk(directory):
        for file in files:
            file_path = os.path.join(root, file)
            file_hash = calculate_hash(file_path)

            if file_hash in file_hash_dict:
                duplicate_files.append((file_path, file_hash))
                duplicate_files.append((file_hash_dict[file_hash], file_hash))
            else:
                file_hash_dict[file_hash] = file_path

    return duplicate_files

directory = '/path/to/directory'
duplicate_files = find_duplicate_files(directory)

if duplicate_files:
    print("找到以下相同的文件：")
    for file_path, file_hash in duplicate_files:
        print("文件路径：", file_path)
        print("文件哈希值：", file_hash)
else:
    print("未找到相同的文件。")