python爬虫登录网站_Python爬虫实例（四）网站模拟登陆

#-*- coding: utf-8 -*-

importurllib2#构建一个已经登录过的用户的headers信息

headers &＃61;{"Host":"www.renren.com","Connection":"keep-alive","Upgrade-Insecure-Requests":"1","User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36","Accept":"text/html,application/xhtml&＃43;xml,application/xml;q&＃61;0.9,image/webp,*/*;q&＃61;0.8","Accept-Language":"zh-CN,zh;q&＃61;0.8,en;q&＃61;0.6",#添加抓包获取的COOKIE&＃xff0c;这个COOKIE是保存了密码无需重复登录的用户的COOKIE&＃xff0c;里面记录了用户名及密码等登录信息&＃xff08;我这里只显示一部分&＃xff09;

"COOKIE":"anonymid&＃61;j5xitrrwqgbk8; _r01_&＃61;1; loginfrom&＃61;syshome; wp_fold&＃61;0; _de&＃61;BF09EE3FED92E6B65F6A4705D973F1383380866D39FF5;}#通过headers里的报头信息&＃xff08;主要是COOKIE信息&＃xff09;&＃xff0c;构建Request对象

request &＃61; urllib2.Request("http://www.renren.com/", headers &＃61;headers)#直接访问renren主页&＃xff0c;服务器会根据headers报头信息&＃xff08;主要是COOKIE信息&＃xff09;&＃xff0c;判断这是一个已经登录的用户&＃xff0c;并返回相应的页面

response &＃61;urllib2.urlopen(request)#打印响应内容

print response.read()