自动获取代理ip小脚本

一个自动爬取代理ip的脚本分享给大家

import requests
from lxml import etree
import csv
import time
def pc(url):
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'}
    response = requests.get(url=url, headers=header)
    selector = etree.HTML(response.content.decode())
    time.sleep(1)
    for i in range(1,16):
        time.sleep(1)
        ip = selector.xpath('//*[@id="list"]/table/tbody/tr[%d]/td[1]/text()' %(i))[0]
        port = selector.xpath('//*[@id="list"]/table/tbody/tr[%d]/td[2]/text()' %(i))[0]
        write([ip,port])
def write(lis):
    with open('代理.txt', 'a', newline="",encoding='utf-8') as f:
        csw = csv.writer(f)
        csw.writerow(lis)
if __name__=='__main__':
    for i in range(1,3517):
        print("正在打印第" str(i) "页ip")
        url = 'https://www.kuaidaili.com/free/inha/' str(i)
        pc(url)运行截图

注:

本文只提供技术分享，请勿用作其他非法用途。如果造成任何法律部后果  与本文作者无关