ip代理

IP池ip爬取

import requests
from lxml import etree
kk = []
url = 'https://www.kuaidaili.com/free/'
# https://www.kuaidaili.com/free/inha/3/ 页码数
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
}
ret = requests.get(url=url,headers=headers).text
tree = etree.HTML(ret)
ip = tree.xpath('//*[@id="list"]/table//tr')
for i in ip:
    try:
        zvip = {}
        nip = i.xpath('./td[1]/text()')[0]
        style = i.xpath('./td[4]/text()')[0]
        zvip[style] = nip
        kk.append(zvip)
    except:
        pass
print(kk)