C#网页自动登录和提交POST信息的多种方法

网页自动登录和提交POST信息的核心就是分析网页的源代码（HTML），在C#中，可以用来提取网页HTML的组件比较多，常用的用WebBrowser、WebClient、HttpWebRequest这三个。

 

以下就分别用这三种方法来实现：

1、WebBrowser是个"迷你"浏览器，其特点是Post时不用关心Cookie、内置JS等问题

WebBrowser是VS2005新提供的组件（其实就是封装了IE接口），实现POST功能一般在webBrowser的DocumentCompleted中分析HtmlDocument 来实现，代码如下：

 

           HtmlElement ClickBtn =null;

           if (e.Url.ToString().ToLower().IndexOf("http://sandou.cnblogs.com/") > 0)   //登陆页面

            {

                HtmlDocument doc = webBrowser1.Document;

                for (int i = 0; i < doc.All.Count ; i++)

                {

                    if (doc.All[i].TagName.ToUpper().Equals("INPUT"))

                    {

                        switch (doc.All[i].Name)

                        {

                            case "userCtl":

                                doc.All[i].InnerText = "user01";

                                break;

                            case "passCt1":

                                doc.All[i].InnerText = "mypass";

                                break;

                            case "B1":

                                ClickBtn = doc.All[i]; //提交按钮

                                break;

                        }

                    }

                }

                ClickBtn.InvokeMember("Click");   //执行按扭操作

            }

 

2、WebClient封装了HTTP的一些类，操作简单，相较于webBrowser，特点是可以自设代理，缺点是对COOKIE的控制

WebClient的运行全在后台，并且提供了异步操作的能力，这样很方便并发多个任务，然后等待结果的返回，再逐个处理。多任务异步调用的代码如下：

 

 private void StartLoop(int ProxyNum)

        {

           WebClient []  wcArray = new WebClient[ProxyNum];  //初始化

             for (int idArray = 0; idArray< ProxyNum;idArray++)

            {

                 wcArray[idArray] = new WebClient();

                wcArray[idArray].OpenReadCompleted += new OpenReadCompletedEventHandler(Pic_OpenReadCompleted2);

                wcArray[idArray].UploadDataCompleted += new UploadDataCompletedEventHandler(Pic_UploadDataCompleted2);

                try

                {

                  

                    wcArray[idArray].Proxy = new WebProxy(proxy[1], port);

                    wcArray[idArray].OpenReadAsync(new Uri("http://sandou.cnblogs.com/")); //打开WEB;

                    proxy = null;

                }

                catch

                {

                }

            }

        }

 

        private void Pic_OpenReadCompleted2(object sender, OpenReadCompletedEventArgs e)

        {

                if (e.Error == null)

                {

                            string textData = new StreamReader(e.Result, Encoding.Default).ReadToEnd();  //取返回信息

                             ..

                              String cookie = ((WebClient)sender).ResponseHeaders["Set-Cookie"];

                             ((WebClient)sender).Headers.Add("Content-Type", "application/x-www-form-urlencoded");

                            ((WebClient)sender).Headers.Add("Accept-Language", "zh-cn");

                            ((WebClient)sender).Headers.Add("Cookie", cookie);

 

                            string postData = ""

                            byte[] byteArray = Encoding.UTF8.GetBytes(postData); // 转化成二进制数组

                           ((WebClient)sender).UploadDataAsync(new Uri("http://sandou.cnblogs.com/"), "POST", byteArray);

                }

         }

 

        private void Pic_UploadDataCompleted2(object sender, UploadDataCompletedEventArgs e)

        {

                 if (e.Error == null)

                {

                    string returnMessage = Encoding.Default.GetString(e.Result);

                  

                }

       }

 

 

3、HttpWebRequest较为低层，能实现的功能较多，Cookie操作也很简单:

 

 

       private bool  PostWebRequest()      

        {

                   CookieContainer cc = new CookieContainer();

                    string pos tData = "user=" + strUser + "&pass=" + strPsd;

                    byte[] byteArray = Encoding.UTF8.GetBytes(postData); // 转化

 

                    HttpWebRequest webRequest2 = (HttpWebRequest)WebRequest.Create(new Uri(http://sandou.cnblogs.com/));

                    webRequest2.CookieContainer = cc;

                    webRequest2.Method = "POST";

                    webRequest2.ContentType = "application/x-www-form-urlencoded";

                    webRequest2.ContentLength = byteArray.Length;

                    Stream newStream = webRequest2.GetRequestStream();

                    // Send the data.

                    newStream.Write(byteArray, 0, byteArray.Length);    //写入参数

                    newStream.Close();

 

                    HttpWebResponse response2 = (HttpWebResponse)webRequest2.GetResponse();

                    StreamReader sr2=new StreamReader(response2.GetResponseStream(), Encoding.Default);

                    string text2 =  sr2.ReadToEnd();

                

        }   

 

HttpWebRequest 实现， 这个是从网上COPY 的！我以前用相关的代码登录到WWW.ASP.NET上，并且成功post，可惜代码不知道放什么地方了。

 

HttpWebRequest自动登录网站并获取网站内容（不包含验证码的网站）

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：

 

 

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

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=dDwtMTcwMzgxNjQ2Mjs7bDxDU

0ROVXNlckxvZ2luOmNiX1NhdmVTdGF0ZTtDU0ROVXNlckxvZ2luOkltYWdlX0xvZ2luOz4%2Btu

1q2wmRZoAJTi9L73w1zBleylY%3D&CSDNUserLogin%3Atb_UserName=testusername&CSDN

UserLogin%3Atb_Password=testpassword&CSDNUserLogin%3Atb_ExPwd=9232

 

 

 

        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("47bDxcZTs%2BPjs%2BOzs%2BOz4%2BOz6aX2dtqkJTK%2BKbNPsjd7Op%2Fl26Iw%3D%3D&txtUserName=hxf&txtPassword=hxf0000&btnEnter=%E7%99%BB%E5%BD%95","http://www.mystand.com.cn/login.aspx">http://www.mystand.com.cn/login.aspx","__VIEWSTATE=dDwtNjkzMjUyNDczO3Q8O2w8aTwzPjs%2BO2w8dDxwPHA8bDxUZXh0Oz47bDxcZTs%2BPjs%2BOzs%2BOz4%2BOz6aX2dtqkJTK%2BKbNPsjd7Op%2Fl26Iw%3D%3D&txtUserName=hxf&txtPassword=hxf0000&btnEnter=%E7%99%BB%E5%BD%95","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, */// <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;

        }

 

技术应用——网页自动登录（提交Post内容）的用途很多，如验证身份、程序升级、网络投票等，以下是用C#实现的方法.

 

未解决问题——目前最大问题无法绕过验证码——我曾经和同事讨论图片的算法，基本上很难识别，网上也有很多识别验证码的例子，但是对于简单的噪声还是可以的，可是对于复杂的就一点用都没有了！到目前为止，我没有测试成功过！如果你有测试成功过，请帖代码，我们一起研究研究。