用python代码构建代理IP池并过滤代理IP

很多小伙伴在获得了批量的代理IP后，对IP的清洗存在疑问，这篇就叫你快速过滤代理IP

import requests


def proxy_use():
  	# 以百度为目标url
    url = "http://www.baidu.com" 

	# 设置headers
    headers = {
        "User-Agent": "Mozilla/5.0 (Wind ows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.86 Safari/537.36"
        }   
	
	# 代理格式：
    # {"协议":"IP:port"}
    # 常见协议 HTTP, HTTPS


    # 设置批量 IP代理池
    proxy_list = [
       	 {"https": "123.34.567.89:8888"},
         {"https": "123.34.567.89:8888"},
         {"https": "123.34.567.89:8888"},
         {"https": "123.34.567.89:8888"}
    ]

    # 过滤 能用 IP
    use_proxy = []
    for proxy in proxy_list:
        try:
        	# 发送请求，带上timeout参数用来检测代理IP的质量，timeout的参数看具体情况而定
            response = requests.get(url, headers=headers, proxies=proxy,timeout=3)
            if response.status_code == 200:
                use_proxy.append(proxy)
        except Exception as e:
            print(e)
    # 打印 use_proxy，查看符合要求的IP
    print(use_proxy)


if __name__ == '__main__':
    proxy_use()