python版 百度签到

经常玩贴吧，刚学python ，所以自己弄了一个python版的签到程序。自己的东西总是最好的。

登陆模块参考的http://www.crifan.com/emulate_login_website_using_python/。签到模块自己找百度瞎糊弄的，写的很烂，代码一点都不规范。有什么建议可以提

 # 594595116@qq.com

 import re
 import urllib
 import urllib2
 import cookielib
 import json
 import sys
 import time
 from urllib import quote,unquote
 from urllib2 import HTTPError
 from urllib2 import URLError

 def t():
     print "按(Y/y)继续，其他退出！"
     t = raw_input(">>")
     if (t=="y" or t=="Y"):
         Login()
     else :
         print "感谢您的使用。"
         print "email:594595116@qq.com"
         time.sleep(5)  

 #登陆模块
 def Login():

     ID = raw_input("百度账号(暂不支持手机和邮箱登陆) :")
     ID1 = ID.decode("gb18030").encode("utf-8") #--注意编码，可能网站会识别不了而导致登陆失败
     PassWord = raw_input("密码 :")    

     try :
         cj = cookielib.CookieJar();
         opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj));
         urllib2.install_opener(opener); 

         #打开百度获得 cookie
         baidu_URL = "http://www.baidu.com"
         staticpage = "http://www.baidu.com/cache/user/html/jump.html";
         baidu_Login_URL = "https://passport.baidu.com/v2/api/?login";
         baidu_OPEN = urllib2.urlopen(baidu_URL)

         #获得所需的数据 token
         getapiUrl = "https://passport.baidu.com/v2/api/?getapi&class=login&tpl=mn&tangram=true";
         getapiResp = urllib2.urlopen(getapiUrl);
         getapiRespHtml = getapiResp.read();

         foundTokenVal = re.search("bdPass\.api\.params\.login_token='(?P<tokenVal>\w+)';", getapiRespHtml);
         tokenVal = foundTokenVal.group("tokenVal");

         #生成要发送的数据
         if(foundTokenVal):
             LoginData = {
                 'staticpage':staticpage,#'http://www.baidu.com/cache/user/html/v3Jump.html',
                 'charset':'UTF-8',
                 'token':tokenVal,
                 'tpl':'mn',
                 #'apiver':'v3',
                 #'tt':'1375838455898',
                 #'codestring':'',
                 'isPhone':'false',
                 #'safeflg':'0',
                 #'u':'http://www.baidu.com/',
                 #'quick_user':'0',
                 'username':ID1,
                 'password':PassWord,
                 #'verifycode':'',
                 'mem_pass':'on',
                 #'ppui_logintime':'11211',
                 'callback':'parent.bdPass.api.login._postCallback',
                 }; 

             #把发送数据转换格式
             LoginData = urllib.urlencode(LoginData);    

             #生成请求数据
             baidu_Login_Request = urllib2.Request(baidu_Login_URL, LoginData);

             #添加数据头部
             baidu_Login_Request.add_header('Content-Type', "application/x-www-form-urlencoded");
             baidu_Login_Request.add_header('User-Agent', "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.64 Safari/537.31");

             #发送请求，尝试登陆
             baidu_Login_Open = urllib2.urlopen(baidu_Login_Request);

             #验证登陆是否成功
             #tt = urllib2.urlopen(baidu_URL).read().encode("gb18030")
             #print tt
             #ttt = re.search(r'href="/p/([0-9A-Za-z%]*)\?from=super"',tt).grop(1)
             #print ttt
             yanzheng_url = "http://www.baidu.com/p/" + ID1
             yanzheng_open = urllib2.urlopen(yanzheng_url)
             yanzheng_open = yanzheng_open.read().encode("gb18030")
             yanzheng = re.search(r"'sexTitle' : '([^ ]*)'", yanzheng_open).group(1)

             if(yanzheng == "我"):
                 print "%s  成功登陆, ^_^" %ID
                 print "签到正在进行中。。"
                 Sign(ID)
             else:
                 print "%s  登陆失败! 请稍后尝试! " %ID
                 Login()
         else:
             print "%s  登陆失败! 请稍后尝试! " %ID
             Login()
                # print "Fail to extract token value from html=",getapiRespHtml;    

     except :
         print "登陆出错啦！"
         t()     

 #签到模块
 def Sign(ID):

     try :
         #签到请求地址
         Sign_Request_Url = "http://tieba.baidu.com/sign/add"

         #用户的贴吧
         ID_Tieba_Url = "http://www.baidu.com/p/" + ID + "?from=tieba"
         ID_Tieba_Open = urllib2.urlopen(ID_Tieba_Url).read()

         #i贴吧id
         itieba_id = re.search(r'i\\/([0-9]*)\\/others\?from=princess', ID_Tieba_Open).group(1)
         index = "http://tieba.baidu.com/i/" + itieba_id + "?fr=index"

         #匹配贴吧
         index_open = urllib2.urlopen(index).read()
         Tieba = re.findall(r'kw=([0-9A-Za-z%]*)&fr=itb_favo&fp=favo" target="_blank">([^ ]*)</a>', index_open)

         if Tieba != []:
             for i in range(len(Tieba)):
                 Tieba_Url = "http://tieba.baidu.com/f?kw=" +  Tieba[i][0]
                 Tieba_Open = urllib2.urlopen(Tieba_Url).read()

                 #获取tbs
                 Get_Tbs = re.search(r'PageData.tbs = "([0-9a-z]*)";',Tieba_Open).group(1)

                 #贴吧名字编码
                 Tieba_Name = urllib.unquote(Tieba[i][0]).decode("gb18030").encode("utf-8")
                 kw = Tieba_Name

                 #签构造到请求数据 和 编码
                 Sign_Request_Data={'ie':'utf-8','kw':kw,'tbs':Get_Tbs}
                 Sign_Request_Data = urllib.urlencode(Sign_Request_Data)

                 #发送签到请求
                 Sign_Request = urllib2.Request(Sign_Request_Url, Sign_Request_Data)
                 Sign_Request.add_header('User-agent', "Mozilla/5.0 (X11; Linux i686)")
                 Sign = urllib2.urlopen(Sign_Request)

                 #获取响应数据
                 Response = Sign.read()

                 #把响应转成字典
                 Response = json.loads(Response)
                 #print Response

                 Tieba_Name = urllib.unquote(Tieba[i][0]).decode("gb18030").encode("utf-8")
                 #print Tieba_Name
                 #print unquote(Tieba[i][0])
                 #print Tieba[i][0]
                 if(Response['error']=="") :
                     user_sign_rank = int(Response['data']['uinfo']['user_sign_rank'])                      #第几个签到
                     cont_sign_num = int(Response['data']['uinfo']['cont_sign_num'])                        #连续签到
                     cout_total_sing_num = Response['data']['uinfo']['cout_total_sing_num']                 #累计签到
                     print "%d..%s             签到成功,第%d个签到,连续签到%d天,累计签到%d天" %(i, unquote(Tieba[i][0]), user_sign_rank, cont_sign_num, cout_total_sing_num)
                 else :
                     print "%d.%s" %(i,unquote(Tieba[i][0]))            # print "%d.%s %s" %(i,unquote(Tieba[i][0]),Response['error'])   不知道为什么这样是不行的,总是乱码。
                     print "--------------------%s"  %Response['error'] # print "%d.%s %s" %(i,Tieba_Name,Response['error'])             这样却可以，所以把他们拆分了
                 time.sleep(3)
         else :
             print "你还没有喜欢的贴吧！"

         print "一共有%d个喜欢的吧" %(i+1)
         t()
     except :
         print "签到出错啦! "
         t()

 if __name__ == "__main__" :
     Login()
     

经验总结：1，编码问题需要注重 2，编码要规范