#!/usr/bin/python

# -*- encoding:utf-8 -*-

import urllib

import urllib2

import cookielib

import re

import chardet      #判断字符串编码的包,用法为 charset.detect(str)  详细示例 http://www.cnblogs.com/zhanhg/p/4392089.html

filename = 'cookie.txt'

#声明一个MozillaCookieJar对象实例来保存cookie,之后写入文件

cookie = cookielib.MozillaCookieJar(filename)

#handler = urllib2.HTTPCookieProcessor(Cookie)

#opener = urllib2.build_opener(handler)

opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))

postdata = urllib.urlencode({

    'stuid':'*******',

    'pwd':'*******'

    })

#登录chinaunix的url链接

loginurl = 'http://bbs.chinaunix.net/member.php?mod=logging&action=login&logsubmit=yes'

#模拟登录,把cookie保存到变量

result = opener.open(loginurl,postdata)

#保存cookie到cookie.txt文件中

cookie.save(ignore_discard=True, ignore_expires=True)

#查询的链接

gradeurl = 'http://bbs.chinaunix.net/home.php?m*********************'

result = opener.open(gradeurl)

html = result.read()

reg = r'<a href\=\"thread.*?" >(.*?)</a>'

a = re.findall(reg,html)

for x in a:

    print(x.decode('gb2312'))