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
1 # 594595116@qq.com 2 3 import re 4 import urllib 5 import urllib2 6 import cookielib 7 import json 8 import sys 9 import time 10 from urllib import quote,unquote 11 from urllib2 import HTTPError 12 from urllib2 import URLError 13 14 def t(): 15 print "按(Y/y)继续，其他退出！" 16 t = raw_input(">>") 17 if (t=="y" or t=="Y"): 18 Login() 19 else : 20 print "感谢您的使用。" 21 print "email:594595116@qq.com" 22 time.sleep(5) 23 24 25 #登陆模块 26 def Login(): 27 28 ID = raw_input("百度账号(暂不支持手机和邮箱登陆) :") 29 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 30 PassWord = raw_input("密码 :") 31 32 try : 33 cj = cookielib.CookieJar(); 34 opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)); 35 urllib2.install_opener(opener); 36 37 #打开百度获得 cookie 38 baidu_URL = "http://www.baidu.com" 39 staticpage = "http://www.baidu.com/cache/user/html/jump.html"; 40 baidu_Login_URL = "https://passport.baidu.com/v2/api/?login"; 41 baidu_OPEN = urllib2.urlopen(baidu_URL) 42 43 #获得所需的数据 token 44 getapiUrl = "https://passport.baidu.com/v2/api/?getapi&class=login&tpl=mn&tangram=true"; 45 getapiResp = urllib2.urlopen(getapiUrl); 46 getapiRespHtml = getapiResp.read(); 47 48 foundTokenVal = re.search("bdPass\.api\.params\.login_token='(?P<tokenVal>\w+)';", getapiRespHtml); 49 tokenVal = foundTokenVal.group("tokenVal"); 50 51 #生成要发送的数据 52 if(foundTokenVal): 53 LoginData = { 54 'staticpage':staticpage,#'http://www.baidu.com/cache/user/html/v3Jump.html', 55 'charset':'UTF-8', 56 'token':tokenVal, 57 'tpl':'mn', 58 #'apiver':'v3', 59 #'tt':'1375838455898', 60 #'codestring':'', 61 'isPhone':'false', 62 #'safeflg':'0', 63 #'u':'http://www.baidu.com/', 64 #'quick_user':'0', 65 'username':ID1, 66 'password':PassWord, 67 #'verifycode':'', 68 'mem_pass':'on', 69 #'ppui_logintime':'11211', 70 'callback':'parent.bdPass.api.login._postCallback', 71 }; 72 73 74 75 #把发送数据转换格式 76 LoginData = urllib.urlencode(LoginData); 77 78 #生成请求数据 79 baidu_Login_Request = urllib2.Request(baidu_Login_URL, LoginData); 80 81 #添加数据头部 82 baidu_Login_Request.add_header('Content-Type', "application/x-www-form-urlencoded"); 83 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"); 84 85 #发送请求，尝试登陆 86 baidu_Login_Open = urllib2.urlopen(baidu_Login_Request); 87 88 #验证登陆是否成功 89 #tt = urllib2.urlopen(baidu_URL).read().encode("gb18030") 90 #print tt 91 #ttt = re.search(r'href="/p/([0-9A-Za-z%]*)\?from=super"',tt).grop(1) 92 #print ttt 93 yanzheng_url = "http://www.baidu.com/p/" + ID1 94 yanzheng_open = urllib2.urlopen(yanzheng_url) 95 yanzheng_open = yanzheng_open.read().encode("gb18030") 96 yanzheng = re.search(r"'sexTitle' : '([^ ]*)'", yanzheng_open).group(1) 97 98 if(yanzheng == "我"): 99 print "%s 成功登陆, ^_^" %ID 100 print "签到正在进行中。。" 101 Sign(ID) 102 else: 103 print "%s 登陆失败! 请稍后尝试! " %ID 104 Login() 105 else: 106 print "%s 登陆失败! 请稍后尝试! " %ID 107 Login() 108 # print "Fail to extract token value from html=",getapiRespHtml; 109 110 except : 111 print "登陆出错啦！" 112 t() 113 114 115 #签到模块 116 def Sign(ID): 117 118 try : 119 #签到请求地址 120 Sign_Request_Url = "http://tieba.baidu.com/sign/add" 121 122 #用户的贴吧 123 ID_Tieba_Url = "http://www.baidu.com/p/" + ID + "?from=tieba" 124 ID_Tieba_Open = urllib2.urlopen(ID_Tieba_Url).read() 125 126 #i贴吧id 127 itieba_id = re.search(r'i\\/([0-9]*)\\/others\?from=princess', ID_Tieba_Open).group(1) 128 index = "http://tieba.baidu.com/i/" + itieba_id + "?fr=index" 129 130 #匹配贴吧 131 index_open = urllib2.urlopen(index).read() 132 Tieba = re.findall(r'kw=([0-9A-Za-z%]*)&fr=itb_favo&fp=favo" target="_blank">([^ ]*)</a>', index_open) 133 134 if Tieba != []: 135 for i in range(len(Tieba)): 136 Tieba_Url = "http://tieba.baidu.com/f?kw=" + Tieba[i][0] 137 Tieba_Open = urllib2.urlopen(Tieba_Url).read() 138 139 #获取tbs 140 Get_Tbs = re.search(r'PageData.tbs = "([0-9a-z]*)";',Tieba_Open).group(1) 141 142 #贴吧名字编码 143 Tieba_Name = urllib.unquote(Tieba[i][0]).decode("gb18030").encode("utf-8") 144 kw = Tieba_Name 145 146 #签构造到请求数据 和 编码 147 Sign_Request_Data={'ie':'utf-8','kw':kw,'tbs':Get_Tbs} 148 Sign_Request_Data = urllib.urlencode(Sign_Request_Data) 149 150 #发送签到请求 151 Sign_Request = urllib2.Request(Sign_Request_Url, Sign_Request_Data) 152 Sign_Request.add_header('User-agent', "Mozilla/5.0 (X11; Linux i686)") 153 Sign = urllib2.urlopen(Sign_Request) 154 155 #获取响应数据 156 Response = Sign.read() 157 158 #把响应转成字典 159 Response = json.loads(Response) 160 #print Response 161 162 Tieba_Name = urllib.unquote(Tieba[i][0]).decode("gb18030").encode("utf-8") 163 #print Tieba_Name 164 #print unquote(Tieba[i][0]) 165 #print Tieba[i][0] 166 if(Response['error']=="") : 167 user_sign_rank = int(Response['data']['uinfo']['user_sign_rank']) #第几个签到 168 cont_sign_num = int(Response['data']['uinfo']['cont_sign_num']) #连续签到 169 cout_total_sing_num = Response['data']['uinfo']['cout_total_sing_num'] #累计签到 170 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) 171 else : 172 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。 173 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 174 time.sleep(3) 175 else : 176 print "你还没有喜欢的贴吧！" 177 178 print "一共有%d个喜欢的吧" %(i+1) 179 t() 180 except : 181 print "签到出错啦! " 182 t() 183 184 185 if __name__ == "__main__" : 186 Login() 187
经验总结：1，编码问题需要注重 2，编码要规范
