01pyhton学习-地址池1

最新推荐文章于 2022-12-07 22:18:00 发布

miyafung

最新推荐文章于 2022-12-07 22:18:00 发布

阅读量205

点赞数

分类专栏： python 文章标签： python

本文链接：https://blog.csdn.net/m0_38010621/article/details/106917225

版权

python 专栏收录该内容

14 篇文章 0 订阅

订阅专栏

01地址获取

import requests
import parsel
import time

def check_ip(proxies_list):#检测代理ip的质量
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.106 Safari/537.36'}
    can_use = []
    for proxy in proxies_list:
        requests.get('https://www.baidu.com',headers=headers,proxies=proxy,timeout=0.1)

proxies_list = []
for page in range(1,5):
    print('=========正在获取地{}页数据=========='.format(page))
    base_url = 'https://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/83.0.4103.106 Safari/537.36'}

    response =requests.get(base_url,headers=headers)
    # print(response.request.headers)
    data = response.text
    # print(data)

    #转换数据类型
    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()
        ip_num = tr.xpath('./td[1]/text()').extract_first()
        ip_port = tr.xpath('./td[2]/text()').extract_first()
        # print(http_type,ip_num,ip_port)

        #构建字典
        dict_proxies[http_type] = ip_num + ':'+ip_port
        print(dict_proxies)
        proxies_list.append(dict_proxies)
        time.sleep(0.5)

print(proxies_list)
print('获取代理ip的数据量：',len(proxies_list))