写了个爬虫代理ip的脚本给大家使用

写了个爬虫代理ip的脚本给大家使用

一.代码

复制import requests
from lxml.html import etree


url = 'http://www.kuaidaili.com/free/'
rp =requests.get(url)
rp_html = etree.HTML(rp.text)

#找xpath
ip_xpath = '//*[@id="list"]/table/tbody/tr/td[1]/text()'
port_xpath = '//*[@id="list"]/table/tbody/tr/td[2]/text()'
http_or_https_xpath ='//*[@id="list"]/table/tbody/tr/td[4]/text()'

#匹配内容
ip_list = rp_html.xpath(ip_xpath)
port_list = rp_html.xpath(port_xpath)
http_or_https_list = rp_html.xpath(http_or_https_xpath)

#进行组合
list_zip = zip(ip_list,port_list,http_or_https_list)
proxy_dict= {}
proxy_list = []
for ip,port,http_or_https in list_zip:
    proxy_dict[http_or_https] = f'{ip}:{port}'
    proxy_list.append(proxy_dict)
    proxy_dict = {}
print(proxy_list)
#list就是啦,你们可以用random模块随机选一个进行后续的爬取

#一页不够嘛那我们就爬十写
#先看规则
'''
第一页:https://www.kuaidaili.com/free/inha/1/
第二页: https://www.kuaidaili.com/free/inha/2/
后面就不用说了吧
'''

http://www.kuaidaili.com/free/这个ip代理网站不错哈