自学Python五 爬虫基础练习之SmartQQ协议

　　BAT站在中国互联网的顶端，引导着中国互联网的发展走向。。。既受到了多数程序员的关注，也在被我们所惦记着。。。

　　关于SmartQQ的协议来自HexBlog，根据他的博客我自己也一步一步的去分析，去尝试，自己不了解不知道的总是神秘的，如果你有这种好奇心，那么真相就只有一个。接下来我先把协议放出来，至于分析方法，以后有机会再谈谈。。。其实我也是个半吊子水平。。。谁知道下次改了协议还灵不灵呢！

　　登录之前，获取二维码：https://ssl.ptlogin2.qq.com/ptqrshow?appid=501004106&e=0&l=M&s=5&d=72&v=4&t=0.22925435146316886，refer为：https://ui.ptlogin2.qq.com/cgi-bin/login

　　循环获取二维码状态（是否失效，是否在手机上授权）：https://ssl.ptlogin2.qq.com/ptqrlogin?webqq_type=10&remember_uin=1&login2qq=1&aid=501004106&u1=http%3A%2F%2Fw.qq.com%2Fproxy.html%3Flogin2qq%3D1%26webqq_type%3D10&ptredirect=0&ptlang=2052&daid=164&from_ui=1&pttype=1&dumy=&fp=loginerroralert&action=0-0-136435&mibao_css=m_webqq&t=undefined&g=1&js_type=0&js_ver=10139&login_sig=&pt_randsalt=0   refer为：https://ui.ptlogin2.qq.com/cgi-bin/login

　　获取cookie中ptwebqq：这次的url是手机扫描二维码之后得到的返回值。refer不变。

　　获取返回值vfwebqq：http://s.web2.qq.com/api/getvfwebqq?ptwebqq=" + ptwebqq + "&clientid=53999199&psessionid=&t=1446710396202。refer为http://s.web2.qq.com/proxy.html?v=20130916001&callback=1&id=1。

　　成功登录，得到uin，psessionid：http://d.web2.qq.com/channel/login2，refer为http://d.web2.qq.com/proxy.html?v=20130916001&callback=1&id=2，数据为："r=%7B%22ptwebqq%22%3A%22"+ptwebqq+"%22%2C%22clientid%22%3A53999199%2C%22psessionid%22%3A%22%22%2C%22status%22%3A%22online%22%7D"，host地址为："d1.web2.qq.com"

　　根据得到的信息获取好友列表：http://s.web2.qq.com/api/get_user_friends2，数据为：data="r=%7B%22vfwebqq%22%3A%22"+vfwebqq+"%22%2C%22hash%22%3A%22"+__hash+"%22%7D"，refer为：http://d.web2.qq.com/proxy.html?v=20130916001&callback=1&id=2

　　让我们来看看程序：

　　

　　下面我们用python来尝试一下（分为两个文件，其中继续沿用我们的HttpClient类，以及WebQQ类，代码如下）：

 #HttpClient.py
　　# -*- coding: utf-8 -*-
 import cookielib, urllib, urllib2, socket

 class HttpClient:
   __cookie = cookielib.CookieJar()
   __req = urllib2.build_opener(urllib2.HTTPCookieProcessor(__cookie))
   __req.addheaders = [
     ('Accept', 'application/javascript, */*;q=0.8'),
     ('User-Agent', 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)')
   ]
   urllib2.install_opener(__req)

   def Get(self, url, refer=None):
     try:
       req = urllib2.Request(url)
       if not (refer is None):
         req.add_header('Referer', refer)
       return urllib2.urlopen(req, timeout=120).read()
     except urllib2.HTTPError, e:
       return e.read()
     except socket.timeout, e:
       return ''
     except socket.error, e:
       return ''

   def GetWithOutRead(self, url, refer=None):
     try:
       req = urllib2.Request(url)
       if not (refer is None):
         req.add_header('Referer', refer)
       return urllib2.urlopen(req, timeout=120)
     except urllib2.HTTPError, e:
       return e.read()
     except socket.timeout, e:
       return ''
     except socket.error, e:
       return ''

   def Post(self, url, data, refer=None):
     try:
       #req = urllib2.Request(url, urllib.urlencode(data))
       req = urllib2.Request(url,data)
       if not (refer is None):
         req.add_header('Referer', refer)
       return urllib2.urlopen(req, timeout=120).read()
     except urllib2.HTTPError, e:
       return e.read()
     except socket.timeout, e:
       return ''
     except socket.error, e:
       return ''

   def Download(self, url, file):
     output = open(file, 'wb')
     output.write(urllib2.urlopen(url).read())
     output.close()

   def getCookie(self, key):
     for c in self.__cookie:
       if c.name == key:
         return c.value
     return ''

   def setCookie(self, key, val, domain):
     ck = cookielib.Cookie(version=0, name=key, value=val, port=None, port_specified=False, domain=domain, domain_specified=False, domain_initial_dot=False, path='/', path_specified=True, secure=False, expires=None, discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False)
     self.__cookie.set_cookie(ck)

 #WebQQ.py
 # -*- coding: utf-8 -*-
 from Tkinter import *
 from time import sleep
 from HttpClient import HttpClient
 import json,io
 from multiprocessing import Process
 import multiprocessing
 from PIL import Image, ImageTk
 class WebQQ(HttpClient):
     def __init__(self):
         self.__cookie = ""
         self.__ptwebqq = ""
         self.__vfwebqq = ""
         self.__hash = ""
         self.__uin = ""
         self.__root = ""
         self.__psessionid = ""
         self.queue = multiprocessing.Queue()

     #获取二维码
     def __ptqrshow(self):
         img = self.Get(url="https://ssl.ptlogin2.qq.com/ptqrshow?appid=501004106&e=0&l=M&s=5&d=72&v=4&t=0.4139144900254905")
         if(img!=None):
             data_stream = io.BytesIO(img)
             imgfile = Image.open(data_stream)
             p = Process(target=self._run_proc, args=(imgfile,))
             p.start()
             print(u"二维码下载完毕，请尽快扫描...")
             return True
         else:
             print(u"二维码下载失败")
             return False

     #检测扫码状态，登录进度
     def __ptqrlogin(self):
         res = self.Get("https://ssl.ptlogin2.qq.com/ptqrlogin?webqq_type=10&remember_uin=1"+
                        "&login2qq=1&aid=501004106&u1=http%3A%2F%2Fw.qq.com%2Fproxy.html%3Flogin2qq%3D1%26webqq_type%3D10"+
                        "&ptredirect=0&ptlang=2052&daid=164&from_ui=1&pttype=1&dumy=&fp=loginerroralert&action=0-0-136435"+
                        "&mibao_css=m_webqq&t=undefined&g=1&js_type=0&js_ver=10139&login_sig=&pt_randsalt=0",
                        "https://ui.ptlogin2.qq.com/cgi-bin/login")
         if(res!=None):
             result = res.find("登录成功")
             if(result==-1):
                 sleep(1)

                 return self.__ptqrlogin()
             elif(result!=-1):
                 res = res.decode("UTF-8")
                 return self.__check_sig(res[res.find("http"):res.find(u"','0','登录成功！'")].encode())
             else:
                 return False
         else:
             return False
     #获得ptwebqq  cookie
     def __check_sig(self,url):
         res = self.Get(url=url,refer="https://ui.ptlogin2.qq.com/cgi-bin/login")
         if(res!=None):
             self.__ptwebqq = self.getCookie("ptwebqq")
             self.__getvfwebqq()
             return self.__login2()
         else:
             return False
     #获得vfwebqq  cookie
     def __getvfwebqq(self):
         res = self.Get(url="http://s.web2.qq.com/api/getvfwebqq?ptwebqq="+self.__ptwebqq+
                        "&clientid=53999199&psessionid=&t=1446710396202",
                      refer="http://d.web2.qq.com/proxy.html?v=20130916001&callback=1&id=1")
         if(res!=None):
             jsn = json.loads(res)
             self.__vfwebqq = jsn["result"]["vfwebqq"]
     #登录 获取uin psessionid
     def __login2(self):
         data = "r=%7B%22ptwebqq%22%3A%22"+self.__ptwebqq+"%22%2C%22clientid%22%3A53999199%2C%22psessionid%22%3A%22%22%2C%22status%22%3A%22online%22%7D"

         res = self.Post(url = "http://d1.web2.qq.com/channel/login2",
                         data = data.encode(encoding="utf8"),
                         refer = "http://d.web2.qq.com/proxy.html?v=20130916001&callback=1&id=2")
         if(res==None):
             return False
         jsn = json.loads(res)
         if(jsn["retcode"]==0):
             self.__uin = jsn["result"]["uin"]
             self.__psessionid = jsn["result"]["psessionid"]
             self.__hash = self.__friendsHash(self.__uin,self.__ptwebqq)
             self.__get_user_friends()
             return True
         else:
             return False
     #好友的hash  参考HexBlog
     def __friendsHash(self,uin,pt):
         N=[0 for x in range(4)]
         V=[0 for x in range(4)]
         U=[0 for x in range(8)]
         #    字符串转换为字符数组
         k=pt.encode(encoding="UTF8")
         n=["","","","","","","","","","","A","B","C","D","E","F"]
         for x in range(len(k)):
             N[x%4]^=ord(k[x])
         x=int(uin)
         V[0] = x >> 24 & 255 ^ 69;
         V[1] = x >> 16 & 255 ^ 67;
         V[2] = x >> 8 & 255 ^ 79;
         V[3] = x & 255 ^ 75;
         for x in range(8):
             U[x]=(x%2==0) and N[x>>1] or V[x>>1]
         result=""
         for x in U:
             result+=n[x>>4&15]
             result+=n[x&15]
         return result
     #获取好友列表
     def __get_user_friends(self):
         data="r=%7B%22vfwebqq%22%3A%22"+self.__vfwebqq+"%22%2C%22hash%22%3A%22"+self.__hash+"%22%7D"
         res=self.Post(url="http://s.web2.qq.com/api/get_user_friends2",
                        data=data.encode(encoding="utf8"),
                          refer="http://s.web2.qq.com/proxy.html?v=20130916001&callback=1&id=1")
         if(res!=None):
             #    记录好友列表
             jsn=json.loads(res)
             if(jsn["retcode"]==0):
                 #    正确返回列表后
                 for x in jsn["result"]["marknames"]:
                     print (x["markname"])
     #心跳包并接收消息，现在不能用了
     #def __poll(self):
     #    data="r=%7B%22ptwebqq%22%3A%22"+self.__ptwebqq+"%22%2C%22clientid%22%3A53999199%2C%22psessionid%22%3A%22"+self.__psessionid +"%22%2C%22key%22%3A%22%22%7D"
     #    res=self.Post(url="http://d1.web2.qq.com/channel/poll2",
     #                  data=data.encode(encoding="utf8"),
     #                  refer="http://d1.web2.qq.com/proxy.html?v=20151105001&callback=1&id=2")
     #    if(res!=None):
     #        print res

     def __check_queue(self):
         try:
             out = self.queue.get_nowait()
             if out == 'stop':
                 self.__do_stop()
                 return
             # Could check for other commands here, too
         except :
             pass
         self.__root.after(100, self.__check_queue)

     def __stop(self):
         self.queue.put('stop')

     def __do_stop(self):
         self.__root.destroy()

     def _run_proc(self,imgfile):
         self.__root = Tk()
         result = ImageTk.PhotoImage(imgfile)
         label = Label(self.__root, image=result)
         label.pack()
         self.__root.after(100, self.__check_queue)
         self.__root.mainloop()
     def run(self):
         if(self.__ptqrshow()):
             if(self.__ptqrlogin()):
                 print(u"登录成功")
                 self.__stop()

 if  __name__ =="__main__":
     qq=WebQQ()
     qq.run()