python代理IP池爬取

代码语言：javascript复制

import parsel
import requests

url = ''
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36',
}
html = requests.get(url=url, headers=headers).text
html = parsel.Selector(html)
Ip = html.xpath('//td[@data-title="IP"]/text()').extract()
Port = html.xpath('//td[@data-title="PORT"]/text()').extract()
LeiXing = html.xpath('//td[@data-title="类型"]/text()').extract()
result = []
for i in range(len(Ip)):
    a = (LeiXing[i]   '://'   Ip[i]   ':'   Port[i])
    pro = {LeiXing[i]: a}
    result.append(pro)

for i in result:
    try:
        ssss = requests.get(url='http://www.baidu.com', headers=headers, proxies=i, timeout=1).status_code
        if ssss == 200:
            print(i)
    except:
        print('不合格')

python ip

0 人点赞