Python解压zip文件名乱码问题的具体分析和解决方案

import zipfile
import tarfile
import gzip
import bz2
import os
import shutil

def extract_archive(archive_path, extract_to='.', encoding='utf-8'):
    """支持中文路径的解压函数"""
    comp_type = detect_compression(archive_path)

    # 根据类型调用对应解压方法
    if comp_type == 'zip':
        # 关键修复：强制使用指定编码
        with zipfile.ZipFile(archive_path, 'r') as zip_ref:
            # 处理乱码：将乱码文件名转换为正确编码
            for file in zip_ref.namelist():
                try:
                    # 尝试用指定编码解析文件名
                    fixed_name = file.encode('cp437').decode(encoding)
                except:
                    fixed_name = file
                # 重命名文件
                zip_ref.NameToInfo[file].filename = fixed_name
            zip_ref.extractall(extract_to)
            
    elif comp_type == 'tar':
        # 关键修复：指定编码打开tar
        with tarfile.open(archive_path, 'r', encoding=encoding) as tar_ref:
            tar_ref.extractall(extract_to)
            
    elif comp_type == 'gz':
        # 注意：gz通常只压缩单个文件，文件名需手动处理
        raw_name = os.path.basename(archive_path)[:-3]
        output_path = os.path.join(extract_to, raw_name)
        with gzip.open(archive_path, 'rb') as gz_ref:
            with open(output_path, 'wb') as out_file:
                shutil.copyfileobj(gz_ref, out_file)
                
    elif comp_type == 'bz2':
        raw_name = os.path.basename(archive_path)[:-4]
        output_path = os.path.join(extract_to, raw_name)
        with bz2.open(archive_path, 'rb') as bz2_ref:
            with open(output_path, 'wb') as out_file:
                shutil.copyfileobj(bz2_ref, out_file)
    else:
        print(f"不支持的压缩格式: {archive_path}")