Python 刷访问量

最新推荐文章于 2021-06-17 09:36:09 发布

天码行空的码

最新推荐文章于 2021-06-17 09:36:09 发布

阅读量1.1w

点赞数 3

分类专栏： Python 文章标签： Python

本文链接：https://blog.csdn.net/qq_42409788/article/details/93867316

版权

Python 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

代理IP通过https://www.xicidaili.com/wn/ 获取，我使用的的是https 协议的代理。根据自己需求选择http或者https 协议的页面。废话不多说，直接上代码。

# -*- coding:utf-8 -*-
#from urllib import  request
import requests
import random
import time
import re
import threading
user_agent_list=[
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
    'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
    'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
    'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
    'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
    'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
    'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
    'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0',
    'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
]
count=0
def Get_proxy_ip():
    headers = {
        'Host': "www.xicidaili.com",
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36',
        'Accept': r'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3'
    }
    req=requests.get(r'https://www.xicidaili.com/wt/',headers=headers)
    html=req.text
#print  (html)
    proxy_list=[]
    IP_list=re.findall(r'\d+\.\d+\.\d+\.\d+',html)
    port_lits=re.findall(r'<td>\d+</td>',html)
    for  i in range(len(IP_list)):
        ip=IP_list[i]
        port=re.sub(r'<td>|</td>','',port_lits[i])
        proxy='%s:%s' %(ip,port)
        proxy_list.append(proxy)
    return proxy_list
def Proxy_read(proxy_list,user_agent_list,i):
    proxy_ip=proxy_list[i]
    print ('当前代理ip：%s'%proxy_ip)
    user_agent = random.choice(user_agent_list)
    print('当前代理user_agent：%s'%user_agent)
    sleep_time = random.randint(5,15)
    print('等待时间：%s s' %sleep_time)
    time.sleep(sleep_time)
    print('开始获取')
    headers = {
        'User-Agent': user_agent
    }
    proxies={
        'http': proxy_ip
    }
    ###########随机取列表中链接#############################################
    Url=['https://blog.csdn.net/qq_42409788/article/details/95076264',
          'https://blog.csdn.net/qq_42409788/article/details/93755352',
      ]
    url=random.choice(Url)  #随机读取链接
    try:
        req = requests.get(url, headers=headers,proxies=proxies, timeout=5)
        html=req.text
        print (html)
    except Exception as e:
        print('******打开失败！******')
    else:
        global count
        count += 1
        print('OK!总计成功%s次！' % count)

if __name__ == '__main__':
    proxy_list = Get_proxy_ip()
    for i in range(100):
        Proxy_read(proxy_list, user_agent_list, i)