爬虫系列，（2），验证IP地址

import requests
from lxml import etree

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36 Edge/15.15063'}


def proxy():
    with open(r'ip_proxies\ip代理池.txt', 'r', encoding='utf-8') as f:
        r = f.readlines()
        ip_list = []
        for ip in r:
            ip_new = ''.join(ip.split(' ')[0:4])
            proxies = eval(ip_new)
            ip_list.append(proxies)
    return ip_list


def test_ip(ip, headers):
    try:
        # response = requests.get("https://ip.cn/",
        #                         headers=headers, proxies=ip, timeout=3)

        # d = response.content.decode()
        # html = etree.HTML(d)
        # addr = html.xpath('//*[@id="result"]/div/p[2]/code/text()')
        # address = addr[0] if len(addr) > 0 else '未知地点'
        # return ip, address
        response = requests.get("https://www.baidu.com/",
                                headers=headers, proxies=ip, timeout=3)
        if response.status_code == 200:
            return ip
    except:
        return None


f = open(r'ip_proxies\有效ip.txt',
         'w', encoding='utf-8')
for i in proxy():
    result = test_ip(i, headers)
    if result is not None:
        # ip_re, address = result
        # print(ip_re, address)
        ip_re = result
        print(ip_re)
        f.write('{}'.format(ip_re))
        f.write('\n')
f.close()