Python实现模拟登陆

大家经常会用Python进行数据挖掘的说，但是有些网站是需要登陆才能看到内容的，那怎么用Python实现模拟登陆呢？其实网路上关于这方面的描述很多，不过前些日子遇到了一个需要cookie才能登陆的网站，而且这个网站还有些问题，于是费了好大的劲才搞定，现在贴出来给大家分享下。

首先是用Python3标准库里的urllib包实现的一个版本，不需要考虑许多细节：

 #! /usr/bin/env python
 # -*- coding:utf-8 -*-

 import urllib.request
 import urllib.parse
 import http.cookiejar

 StudentInfoURL = 'http://210.x.x.1:90/student/index.jsp'
 loginURL = 'http://210.x.x.1:90/login.jsp'
 loginCheckURL = 'http://210.x.x.1:90/j_security_check'
 post_data = urllib.parse.urlencode({'j_username': 'xxxxxxx', 'j_password': 'xxxxxxx'})
 headers = {
     'Content-Type': 'application/x-www-form-urlencoded',
     'UserAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1700.107 Safari/537.36'
 }

 cj = http.cookiejar.CookieJar()
 opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
 #此处一定要链接一次，否则得不到cookie
 opener.open(loginCheckURL)
 urllib.request.install_opener(opener)

 ######################此处加入异常处理，再登一次即可######################
 request = urllib.request.Request(loginCheckURL, post_data, headers)
 try:
     response = urllib.request.urlopen(request)
 except:
     response = urllib.request.urlopen(request)
 print(response.read().decode('GBK'))

 ######################可以开始正常访问啦######################
 request = urllib.request.Request(StudentInfoURL, headers=headers)
 fp =  urllib.request.urlopen(request)
 print(fp.read().decode('GBK'))

下面是另一个版本，用的是比较底层的http包里的client模块实现的，个人很喜欢这个版本：

 #!/usr/bin/env python
 #  -*- coding:utf-8 -*-

 import http.client

 ###########################################################
 HOST = '210.x.x.1:90'
 UserName =  "xxxxxxx"
 PassWord =  "xxxxxxx"
 data =  "j_username=%s&j_password=%s"        %(UserName,PassWord)
 Headers = {
     "Content-Type":"application/x-www-form-urlencoded",
     "User-Agent":"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729)",
     }
 ###########################################################

 #连接服务器
 conn = http.client.HTTPConnection(HOST,timeout=30)
 conn.connect()

 #GET到登录页，以获取cookies
 conn.request("GET","/j_security_check",None,Headers)
 res = conn.getresponse()
 m_cookie = res.getheader("Set-Cookie").split(';')[0]
 res.read()

 #POST到登录页，进行登录
 Headers["Cookie"] = m_cookie
 conn.request("POST","/j_security_check",data,Headers)
 res = conn.getresponse()
 res.read()
 if res.status == 400:
     #再次链接到登录页
     conn.request("POST","/j_security_check",data,Headers)
     res = conn.getresponse()
     res.read()
 conn.close()

 ######################可以开始正常访问啦######################
 conn2 = http.client.HTTPConnection(HOST)
 conn2.request("GET","/student/index.jsp",None,Headers)
 fp = conn2.getresponse()
 print(fp.status)
 print(fp.read().decode("GBK"))
 ###########################################################

欢迎大家批评