HttpWebRequest自动登录网站并获取网站内容
可以使用 Visual Sniffer(百度搜索) 来捕捉提交的数据信息:
1. 访问你需要站外提交的页面,比如 CSDN 登陆页 http://www.csdn.net/member/UserLogin.aspx 2. 填写好需要的资料,比如用户名和密码, 3. 打开 Visual Sniffer, 点“开始拦截” 4. 在访问的页面中提交。 5. 等提交成功之后,在 Visual Sniffer 中“停止拦截” 6. 在 Visual Sniffer 的左侧栏的加号中依次点开,右边是它拦截到的内容: 拦截的内容如下 POST http://www.csdn.net/member/UserLogin.aspx HTTP/1.0 Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-shockwave-flash, */* Referer: http://www.csdn.net/member/UserLogin.aspx Accept-Language: zh-cn Content-Type: application/x-www-form-urlencoded UA-CPU: x86 Pragma: no-cache User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; InfoPath.1) Host: www.csdn.net Content-Length: 355 Proxy-Connection: Keep-Alive Cookie: ASPSESSIONIDAAAATBQC=FMEGGCKDBKHAMMCGKPFDMBFG; ASP.NET_SessionId=lusprmnom05lr445tmteaf55; userid=699879 __EVENTTARGET=&__EVENTARGUMENT=&__VIEWSTATE=dDwtMTcwMzgxNjQ2Mjs7bDxDU0ROVXNlckxvZ2luOmNiX1NhdmVTdGF0ZTtDU0ROVXNlckxvZ2luOkltYWdlX0xvZ2luOz4+tu1q2wmRZoAJTi9L73w1zBleylY=&CSDNUserLogin:tb_UserName=testusername&CSDNUserLogin:tb_Password=testpassword&CSDNUserLogin:tb_ExPwd=9232&from=&CSDNUserLogin:Image_Login.x=36&CSDNUserLogin:Image_Login.y=6 GET http://www.csdn.net/mycustompage.htm?aspxerrorpath=/member/UserLogin.aspx HTTP/1.0 Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-shockwave-flash, */* Referer: http://www.csdn.net/member/UserLogin.aspx Accept-Language: zh-cn UA-CPU: x86 Pragma: no-cache User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; InfoPath.1) Host: www.csdn.net Proxy-Connection: Keep-Alive Cookie: ASPSESSIONIDAAAATBQC=FMEGGCKDBKHAMMCGKPFDMBFG; ASP.NET_SessionId=lusprmnom05lr445tmteaf55; userid=699879 以上为拦截内容,其中提交数据的参数部分(程序中的:strArgs)如: __EVENTTARGET=&__EVENTARGUMENT=&__VIEWSTATE=dDwtMTcwMzgxNjQ2Mjs7bDxDU0ROVXNlckxvZ2luOmNiX1NhdmVTdGF0ZTtDU0ROVXNlckxvZ2luOkltYWdlX0xvZ2luOz4+tu1q2wmRZoAJTi9L73w1zBleylY=&CSDNUserLogin:tb_UserName=testusername&CSDNUserLogin:tb_Password=testpassword&CSDNUserLogin:tb_ExPwd=9232 自动登录网站 protected static string cookieHeader; private void Page_Load(object sender, System.EventArgs e) { string strReContent = string.Empty; //登录 strReContent = PostLogin("http://www.mystand.com.cn/login/submit.jsp提交的页面","提交的参数:userid=hgj0000&password=06045369","引用地址:http://www.mystand.com.cn/"); //asp.net登录传递的参数需注意 //strReContent = PostLogin("http://www.mystand.com.cn/login.aspx","__VIEWSTATE=dDwtNjkzMjUyNDczO3Q8O2w8aTwzPjs+O2w8dDxwPHA8bDxUZXh0Oz47bDxcZTs+Pjs+Ozs+Oz4+Oz6aX2dtqkJTK+KbNPsjd7Op/l26Iw==&txtUserName=hxf&txtPassword=hxf0000&btnEnter=登录","http://www.mystand.com.cn/login.aspx"); //获取页面 strReContent = GetPage("http://www.mystand.com.cn/company/getdata.jsp?code=","引用地址:http://www.mystand.com.cn/"); //strReContent = GetPage("http://www.mystand.com.cn/Modules/index.aspx","http://www.mystand.com.cn/login.aspx"); //可以对获得的内容进行处理:strReContent } /** <summary> /// 功能描述:模拟登录页面,提交登录数据进行登录,并记录Header中的cookie /// </summary> /// <param name="strURL">登录数据提交的页面地址</param> /// <param name="strArgs">用户登录数据</param> /// <param name="strReferer">引用地址</param> /// <returns>可以返回页面内容或不返回</returns> public static string PostLogin(string strURL,string strArgs,string strReferer) { string strResult = ""; HttpWebRequest myHttpWebRequest = (HttpWebRequest)WebRequest.Create(strURL); myHttpWebRequest.AllowAutoRedirect = true; myHttpWebRequest.KeepAlive = true; myHttpWebRequest.Accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-excel, application/msword, application/x-shockwave-flash, */*"; myHttpWebRequest.Referer = strReferer; myHttpWebRequest.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; .NET CLR 2.0.50727)"; myHttpWebRequest.ContentType = "application/x-www-form-urlencoded"; myHttpWebRequest.Method = "POST"; CookieCollection myCookies = null; CookieContainer myCookieContainer = new CookieContainer(); myHttpWebRequest.CookieContainer = myCookieContainer; Stream MyRequestStrearm = myHttpWebRequest.GetRequestStream(); StreamWriter MyStreamWriter = new StreamWriter(MyRequestStrearm,Encoding.ASCII); //把数据写入HttpWebRequest的Request流 MyStreamWriter.Write(strArgs); //关闭打开对象 MyStreamWriter.Close(); MyRequestStrearm.Close(); HttpWebResponse response = null; System.IO.StreamReader sr = null; response = (HttpWebResponse)myHttpWebRequest.GetResponse(); cookieHeader = myHttpWebRequest.CookieContainer.GetCookieHeader(new Uri(strURL)); HttpContext.Current.Application.Lock(); HttpContext.Current.Application[" cookieHeader"] = cookieHeader; HttpContext.Current.Application.UnLock(); myCookies = response.Cookies; sr = new System.IO.StreamReader(response.GetResponseStream(),Encoding.GetEncoding("gb2312")); // //utf-8 strResult = sr.ReadToEnd(); return strResult; } /** <summary> /// 功能描述:在PostLogin成功登录后记录下Headers中的cookie,然后获取此网站上其他页面的内容 /// </summary> /// <param name="strURL">获取网站的某页面的地址</param> /// <param name="strReferer">引用的地址</param> /// <returns>返回页面内容</returns> public static string GetPage(string strURL,string strReferer) { string strResult = ""; HttpWebRequest myHttpWebRequest = (HttpWebRequest)WebRequest.Create(strURL); myHttpWebRequest.ContentType = "text/html"; myHttpWebRequest.Method = "GET"; myHttpWebRequest.Referer = strReferer; myHttpWebRequest.Headers.Add("cookie:"+ cookieHeader); HttpWebResponse response = null; System.IO.StreamReader sr = null; response = (HttpWebResponse)myHttpWebRequest.GetResponse(); sr = new System.IO.StreamReader(response.GetResponseStream(), Encoding.GetEncoding("gb2312")); // //utf-8 strResult = sr.ReadToEnd(); return strResult; |