快速读取zip压缩包内的文件 支持在线url以及本地path

fast_read_the_file_in_the_zip.py

import requests,tempfile, zipfile,os
def read_file_for_zip(zip_url, callback=None):
    """
    读取zip包内的文件
    :param zip_url:zip路径/url
    :param callback:读取操作的回调函数 若函数返回false 则不会读取下一个文件
    :return:
    """
    with tempfile.TemporaryFile('w+b') as tmpfile:  # 生成临时文件

        # 判断是否为本地文件
        if os.path.isfile(zip_url):
            #进行本地复制。没必要
            # with open(zip_url,'rb') as f:
            #     while True:
            #         chunk = f.read(1024)
            #         if not chunk:
            #             break
            #         tmpfile.write(chunk)
            tmpfile = zip_url
        else:#进行http请求
            r = requests.get(zip_url, stream=True)
            for chunk in r.iter_content(chunk_size=1024):
                if chunk:
                    tmpfile.write(chunk)
        assert zipfile.is_zipfile(tmpfile), '不是zip文件'
        zf = zipfile.ZipFile(tmpfile)
        for name in zf.namelist():  # list e.g. ['Brave Browser.url', 'Express VPN.url', 'ssl.txt', 'What is my IP.url']
            if callable(callback):
                # zf.read(name) #读取
                if callback(name, zf) is False:# 函数返回false 会终止下一个文件的读取
                    break


### 例子

def cb(filename,context):
    if filename.endswith('.txt'):
        print(context.read(filename).decode('utf-8'))
    # print( context.read(filename))
        return False #终止下一个文件的读取

read_file_for_zip('https://cdn-01.openload.cc/S9Y7m488n8/22c3c58b-1571037628/ssl_proxies.zip',cb)