Python写去重脚本根据MD5哈希值扫描重复图片并删除

import osimport hashlibfrom collections import defaultdict

def get_file_md5(file_path):    """计算文件的MD5值"""    with open(file_path, 'rb') as f:        file_hash = hashlib.md5()        while chunk := f.read(8192):            file_hash.update(chunk)    return file_hash.hexdigest()

def hacker_progress_bar(iteration, total, prefix='', suffix='', decimals=1, length=100, fill='█'):    """    进度条特效函数    :param iteration: 当前迭代次数    :param total: 总进度    :param prefix: 进度条前缀    :param suffix: 进度条后缀    :param decimals: 进度小数位数    :param length: 进度条长度    :param fill: 进度条填充字符    """    if total == 0:        return    percent = ("{0:." + str(decimals) + "f}").format(100 * (iteration / float(total)))    filled_length = int(length * iteration // total)    bar = fill * filled_length + '-' * (length - filled_length)    print(f'r{prefix} |{bar}| {percent}% {suffix}', end='r')    if iteration == total:        print()

def remove_duplicate_images(directory):    """删除目录中重复的图像文件"""    image_files = []    for root, _, files in os.walk(directory):        for filename in files:            if filename.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.bmp')):                file_path = os.path.join(root, filename)                image_files.append(file_path)

    total_files = len(image_files)    if total_files == 0:        print("去重复图片脚本---微信公众号:蓝胖子之家")        print("")        print("")        print(f"目录 {directory} 中没有图像文件。")        input("按下回车键退出...")        return        print("去重复图片脚本---微信公众号:蓝胖子之家")    print("")    print("")    print(f"正在扫描目录 {directory} 中的图像文件...")    hacker_progress_bar(0, total_files, prefix='Progress:', suffix='Scanning', length=50)

    image_md5s = defaultdict(list)    for i, file_path in enumerate(image_files):        md5 = get_file_md5(file_path)        image_md5s[md5].append(file_path)        hacker_progress_bar(i+1, total_files, prefix='Progress:', suffix='Scanning', length=50)

    duplicate_files = [paths[1:] for md5, paths in image_md5s.items() if len(paths) > 1]    if duplicate_files:        print(f"n发现共有 {len(duplicate_files)} 组重复图片文件:")        for index, files in enumerate(duplicate_files, 1):            print(f"组 {index}:")            for file in files:                print(f"  {file}")

        remove_duplicates = input("是否删除重复图片文件? (y/n) ")        if remove_duplicates.lower() == 'y':            for files in duplicate_files:                for duplicate_file in files:                    os.remove(duplicate_file)                    print(f"已删除文件: {duplicate_file}")    else:        print("未发现重复图片文件。")

    input("按下回车键退出...")

if __name__ == "__main__":    current_directory = os.getcwd()    remove_duplicate_images(current_directory)