python实现登录抓取_Python网页抓取、模拟登录

#-------------------------------------------------------------------------------

# Name: 模拟登录web

# Purpose:

#

# Author: huwei

#

# Created: 26/10/2010

# Copyright: (c) huwei 2010

# Licence:

#-------------------------------------------------------------------------------

#!/usr/bin/env python

import time,urllib2,urllib

def main():

#登录博客园

loginCNblogs()

pass

#登录博客园

def loginCNblogs():

try:

#设置 cookie

cookies = urllib2.HTTPCookieProcessor()

opener = urllib2.build_opener(cookies)

urllib2.install_opener(opener)

parms = {"tbUserName":"用户名","tbPassword":"密码","__EVENTTARGET":"btnLogin","__EVENTARGUMENT":"",

"__VIEWSTATE":"/wEPDwULLTExMDE0MzIzNDRkGAEFHl9fQ29udHJvbHNSZXF1aXJlUG9zdEJhY2tLZXlfXxYBBQtjaGtSZW1lbWJlcmcJekJlt5rFwfnjeMMnX9V58Xhg",

"__EVENTVALIDATION":"/wEWBQKit6iCDALyj/OQAgK3jsrkBALR55GJDgKC3IeGDK6TQlRlirS2Zja1Lmeh02u4XMwV",

"txtReturnUrl":"http://bboy.cnblogs.com"}

loginUrl = "http://passport.cnblogs.com/login.aspx"

login = urllib2.urlopen(loginUrl,urllib.urlencode(parms))

#print(unicode(login.read(),"utf8"))

#显示配置页面

avatar = urllib2.urlopen("http://home.cnblogs.com/set/avatar/")

#print(avatar.read().decode("utf8"))

except Exception,e:

print(e)

pass

if __name__ == '__main__':

main()