Python爬取免费代理

1.使用python爬取快代理（http://www.kuaidaili.com）的免费代理IP

import requests
import parsel
import time

proxies_list = []
for page in range(1,5):#爬取1~4页的代理ip
    
    print('=========正在获取第{}页数据===='.format(page))
    base_url = 'http://www.kuaidaili.com/free/inha/{}/'.format(str(page))
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}
    response = requests.get(base_url,headers = headers)
    data = response.text

    html_data = parsel.Selector(data)
    parse_list = html_data.xpath('//table[@class="table table-bordered table-striped"]/tbody/tr')


    for tr in parse_list:
        dict_proxies = {}
        http_type = tr.xpath('./td[4]/text()').extract_first()  #协议类型
        ip_num = tr.xpath('./td[1]/text()').extract_first()  #协议类型
        ip_port = tr.xpath('./td[2]/text()').extract_first()  #协议类型


        dict_proxies[http_type] = ip_num + ':' + ip_port
        print(dict_proxies)
        proxies_list.append(dict_proxies)
        time.sleep(0.5)
print("总爬取IP代理列表")
print(proxies_list)
print('获取到的代理ip的数量：',len(proxies_list))