python爬虫模拟人人网登陆并发表更新状态

网上找了一些资源，python爬虫模拟登陆人人网的例子，但是应该是比较早期的版本，大多已经无法登陆。而且人人网也在做一些信息验证机制也在变化，自己做了一个小爬虫，模拟登陆后在人人网发表自己的状态。

登陆是需要的信息：

    postData = {'email':username,'password':password}

发表心情是所需的信息：

            statusData = {'content':msg,
                        '_rtk':self.rtkToken,
                        'channel':'renren',
                        'hostid':self.userid,#测试中此参数没有亦可请求成功
                        'requestToken':self.requestToken}

此处无论是登陆，还是心情发表操作都不需要headers信息验证。但是_rtk,channel确实必须的。

# -*-coding:utf-8-*-
import urllib2
from urllib import urlencode
import re

class Renren:
    requestToken = ''
    rtkToken = ''
    userid = ''
    __isLogin = False
    newStatusUrl = 'http://shell.renren.com/{}/status'
    LoginUrl = 'http://www.renren.com/PLogin.do'

    # 登录
    def Login(self, username, password):
        postData = {'email':username,
                'password':password}
        postData = urlencode(postData)
        cookieFile = urllib2.HTTPCookieProcessor()
        self.opener = urllib2.build_opener(cookieFile)
        req = urllib2.Request(self.LoginUrl, postData)
        result = self.opener.open(req)
        if result.geturl() == 'http://www.renren.com/home' or 'http://guide.renren.com/guide':
            print "login success..."
            pass
        else:
            return False
        rawHtml = result.read()
        # 获取用户id
        useridPattern = re.compile(r"'id':'(\d+)'")
        self.userid = useridPattern.search(rawHtml).group(1)
        # 查找requestToken
        requestToken = re.compile(r"get_check:'(\d+)'")
        requestToken2 = re.compile(r"get_check:'(-\d+)'")
        token = requestToken.search(rawHtml) if requestToken.search(rawHtml) else requestToken2.search(rawHtml)
        if token is None:
            raise ValueError("requestToken search failed...")
        self.requestToken = token.group(1)
        #获取_rtkToken，更新个人状态时需要此参数
        rtkPattern = re.compile(r"get_check_x:'(\w+)'")
        rtktoken = rtkPattern.search(rawHtml)
        if rtktoken is None:
            raise ValueError("rtk token search failed...")
        self.rtkToken = rtktoken.group(1)
        print self.rtkToken
        self.__isLogin = True
        return self.__isLogin

    # 获取RequestToken
    def GetRequestToken(self):
        return self.requestToken

    # 发布个人状态
    def PostStatus(self, msg):
        headers = {
            "Host":"shell.renren.com",
            "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:27.0) Gecko/20100101 Firefox/27.0",
            "Referer":"http://shell.renren.com/ajaxproxy.htm"
        }
        if self.__isLogin:
            statusData = {'content':msg,
                        '_rtk':self.rtkToken,
                        'channel':'renren',
                        'hostid':self.userid,#测试中此参数没有亦可请求成功
                        'requestToken':self.requestToken}
            postStatusData = urlencode(statusData)
            self.newStatusUrl = self.newStatusUrl.format(self.userid)
            # print self.newStatusUrl
            updataReq = urllib2.Request(self.newStatusUrl, postStatusData, headers= headers)
            # print updataReq
            updataResult = self.opener.open(updataReq)
            if not updataResult:
                raise ValueError("update failed...")
            print "status update success..."
            return True
        return False