模拟网页登录高分求助

736在哪里？
这是响应头，里面JSESSIONID这个有用，在POST时需要带上这个

using System;
using System.Collections.Generic;
using System.Text;
using System.Net;
using System.IO;
namespace bot
{
  public class Html
    {
        /// <summary>
        /// httpwebrequest类中的一些属性的集合
        /// </summary>
        public struct RequestPPT
        {
            private string strAccept;
            /// <summary>
            /// 获取或设置request类中的Accept属性
            /// 用以设置接受的文件类型
            /// </summary>
            public string Accept
            {
                get
                {
                    return strAccept;
                }
                set
                {
                    strAccept = value;
                }
            }
            private string strContentType;
            /// <summary>
            /// 获取或设置request类中的ContentType属性
            /// 用以设置请求的媒体类型
            /// </summary>
            public string ContentType
            {
                get
                {
                    return strContentType;
                }
                set
                {
                    strContentType = value;
                }
            }
            /// <summary>
            /// 获取或设置request类中的UserAgent属性
            /// 用以设置请求的客户端信息
            /// </summary>
            private string strUserAgent;
            public string UserAgent
            {
                get
                {
                    return strUserAgent;
                }
                set
                {
                    strUserAgent = value;
                }
            }
            private string strMethod;
            /// <summary>
            /// 获取或设置request类中的Method属性
            /// 可以将 Method 属性设置为任何 HTTP 1.1 协议谓词：GET、HEAD、POST、PUT、DELETE、TRACE 或 OPTIONS。
            /// 如果 ContentLength 属性被设置为 -1 以外的任何值，则必须将 Method 属性设置为上载数据的协议属性。
            /// </summary>
            public string Method
            {
                get
                {
                    return strMethod;
                }
                set
                {
                    strMethod = value;
                }
            }
        }
        /// <summary>
        /// 构建一个httt请求以获取目标链接的cookies,需要传入目标的登录地址和相关的post信息,返回完成登录的cookies,以及返回的html内容
        /// </summary>
        /// <param name="url">登录页面的地址 </param>
        /// <param name="post">post信息 </param>
        /// <param name="strHtml">输出的html代码 </param>
        /// <param name="rppt">请求的标头所需要的相关属性设置 </param>
        /// <returns>请求完成后的cookies </returns>
        public CookieCollection funGetCookie(string url, byte[] post, out string strHtml, RequestPPT rppt,string server)
        {

            CookieCollection ckclReturn = new CookieCollection();
            CookieContainer cc = new CookieContainer();
            HttpWebRequest hwRequest;
            HttpWebResponse hwResponse;
            //请求cookies的格式
            //hwRequest = (HttpWebRequest)HttpWebRequest.Create(new Uri(url));
            //hwResponse = (HttpWebResponse)hwRequest.GetResponse();
            //string cookie = hwResponse.Headers.Get("Set-Cookie");
            //cookie = cookie.Split(';')[0];
            //hwRequest = null;
            //hwResponse = null;
            //构建即将发送的包头
            //cc.SetCookies(new Uri(server), cookie);
            hwRequest = (HttpWebRequest)HttpWebRequest.Create(new Uri(url));
            hwRequest.CookieContainer = cc;
            hwRequest.Accept = rppt.Accept;
            hwRequest.ContentType = rppt.ContentType;
            hwRequest.UserAgent = rppt.UserAgent;
            hwRequest.Method = rppt.Method;
            hwRequest.ContentLength = post.Length;
            //写入标头
            Stream stream;
            stream = hwRequest.GetRequestStream();
            stream.Write(post, 0, post.Length);
            stream.Close();
            //发送请求获取响应内容
            hwResponse = (HttpWebResponse)hwRequest.GetResponse();
            stream = hwResponse.GetResponseStream();
            StreamReader sReader = new StreamReader(stream, Encoding.Default);
            strHtml = sReader.ReadToEnd();
            sReader.Close();
            stream.Close();
            //获取缓存内容
            ckclReturn = hwResponse.Cookies;
            return ckclReturn;
        }
      /// <summary>
      /// 根据已经获取的有效cookies来获取目标链接的内容
      /// </summary>
      /// <param name="strUri">目标链接的url </param>
      /// <param name="ccl">已经获取到的有效cookies </param>
      /// <param name="rppt">头属性的相关设置 </param>
      /// <returns>目标连接的纯文本:"txt/html" </returns>
      public string funGetHtmlByCookies(string strUri, CookieCollection ccl, RequestPPT rppt)
      {
          CookieContainer cc = new CookieContainer();
          HttpWebRequest hwRequest;
          HttpWebResponse hwResponse;

          //构建即将发送的包头
          hwRequest = (HttpWebRequest)HttpWebRequest.Create(new Uri(strUri));
          cc.Add(ccl);
          hwRequest.CookieContainer = cc;
          hwRequest.Accept = rppt.Accept;
          hwRequest.ContentType = rppt.ContentType;
          hwRequest.UserAgent = rppt.UserAgent;
          hwRequest.Method = rppt.Method;
          hwRequest.ContentLength = 0;

          //发送请求获取响应内容
          hwResponse = (HttpWebResponse)hwRequest.GetResponse();
          Stream stream;
          stream = hwResponse.GetResponseStream();
          StreamReader sReader = new StreamReader(stream, Encoding.Default);
          string strHtml = sReader.ReadToEnd();
          sReader.Close();
          stream.Close();           //返回值
          return strHtml;
      }
      /// <summary>
      /// 根据已经获取的有效cookies来获取目标链接的内容
      /// </summary>
      /// <param name="strUri">目标链接的url </param>
      /// <param name="post">post的byte信息 </param>
      /// <param name="ccl">已经获取到的有效cookies </param>
      /// <param name="rppt">头属性的相关设置 </param>
      /// <returns>目标连接的纯文本:"txt/html" </returns>
      public string funGetHtmlByCookies(string strUri,byte[] post, CookieCollection ccl, RequestPPT rppt)
      {
          CookieContainer cc = new CookieContainer();
          HttpWebRequest hwRequest;
          HttpWebResponse hwResponse;           //构建即将发送的包头
          hwRequest = (HttpWebRequest)HttpWebRequest.Create(new Uri(strUri));
          cc.Add(ccl);
          hwRequest.CookieContainer = cc;
          hwRequest.Accept = rppt.Accept;
          hwRequest.ContentType = rppt.ContentType;
          hwRequest.UserAgent = rppt.UserAgent;
          hwRequest.Method = rppt.Method;
          hwRequest.ContentLength = post.Length;
          //写入post信息
          Stream stream;
          stream = hwRequest.GetRequestStream();
          stream.Write(post, 0, post.Length);
          stream.Close();
          //发送请求获取响应内容
          hwResponse = (HttpWebResponse)hwRequest.GetResponse();

          stream = hwResponse.GetResponseStream();
          StreamReader sReader = new StreamReader(stream, Encoding.Default);
          string strHtml = sReader.ReadToEnd();
          sReader.Close();
          stream.Close();           //返回值
          return strHtml;
      }
    }
}

这里是上面那个类的调用方法,构建post中的内容也就是你抓包抓下来的部分,你自己参考下代码多,最好放vs里面看!
using System;
using System.IO;
using System.Collections.Generic;
using System.Text;
using System.Net;
using System.Data;
using System.Xml;
using System.Text.RegularExpressions;
using System.Collections;
namespace bot
{
    public class SisHtml :Html
    {
        public SisHtml()
        {         }         /// <summary>
        /// 设置主机ip地址
        /// </summary>
        public string Host
        {
            get {
                return strHost;             }
            set {
                strHost = value;
            }
        }         private string strHost;         /// <summary>
        /// 获取目标登录链接的cookies
        /// </summary>
        /// <param name="url">目标的登录链接 </param>
        /// <param name="dir">构造头的泛型键值对 </param>
        /// <param name="strHtml">登录后返回的页面内容 </param>
        /// <returns>登录后的cookies </returns>
        public CookieCollection funGetCookie(string url, Dictionary <string, string> dir, out string strHtml)
        {
            CookieCollection cc = new CookieCollection();
            RequestPPT rppt = new RequestPPT();             //构建post内容
            string strPost = funMakePost(dir);
            byte[] post = Encoding.Default.GetBytes(strPost);             //设置标头属性
            rppt.Accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, */*";
            rppt.ContentType = "application/x-www-form-urlencoded";
            rppt.Method = "Post";
            rppt.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; InfoPath.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022)";
            string server ="http://"+ new Uri(url).Host;
            return cc = base.funGetCookie(url, post, out strHtml, rppt, server);
        }         /// <summary>
        /// 根据已经获取到cookies来获取目标链接的内容
        /// </summary>
        /// <param name="strUri">目标的url </param>
        /// <param name="ccl">已经获取好的cookies </param>
        /// <returns>目标url的纯文本:"txt/html" </returns>
        public string funGetHtmlByCookies(string strUri,CookieCollection ccl )
        {

            RequestPPT rppt = new RequestPPT();
            //设置头属性
            rppt.Accept = "txt/html";
            rppt.ContentType = "application/x-www-form-urlencoded";
            rppt.Method = "Post";
            rppt.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; InfoPath.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022)";
            return base.funGetHtmlByCookies(strUri, ccl, rppt);
        }
        /// <summary>
        /// 投票帖子用的方法
        /// </summary>
        /// <param name="strHtml">投票帖子的htmlcode </param>
        /// <param name="ccl">有效的cookies </param>
        /// <returns>投票完成以后的htmlcode </returns>
        public string  funVote(string strHtml,CookieCollection ccl)
        {
          //判断是不是选取投票
            strHtml = strHtml.Substring(strHtml.IndexOf(" <form"), strHtml.LastIndexOf(" </form>") - strHtml.IndexOf(" <form") + 7);
            string strCheck = @"name=""pollanswers[]""";
            //如果代码中包含关键信息说明没有被投票过
            if(strHtml.IndexOf(strCheck)>0)
            {
                //获取post头的需求信息
                string strFormHash = "77b49df4";
                string strPollanswers;
                strPollanswers = strHtml.Substring(strHtml.IndexOf(strCheck)+strCheck.Length, 20).Split('"')[1];
                string strPollansubmit = "提交";
                Dictionary <string,string>dir = new Dictionary <string,string>();
                dir.Add("formhash",strFormHash);
                dir.Add("pollanswers[]",strPollanswers);
                dir.Add("pollsubmit",strPollansubmit);
                string strPost = funMakePost(dir);
                byte[] post = Encoding.Default.GetBytes(strPost);
                //获取请求的路径
                string strUrl= "http://"+Host+"/bbs/";
                string strActionUrl =@"method=""post""";
                strUrl+= strHtml.Substring(strHtml.IndexOf(strActionUrl)+strActionUrl.Length,100).Split('"')[1].Replace("amp;","");
                //构建头
                RequestPPT rppt = new RequestPPT();
                rppt.Accept = "txt/html";
                rppt.ContentType = "application/x-www-form-urlencoded";
                rppt.Method = "Post";
                rppt.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; InfoPath.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022)";
                strHtml = base.funGetHtmlByCookies(strUrl, post, ccl, rppt);
            }
            return strHtml;
        }         /// <summary>
        /// 根据泛型来构建字符串用于post
        /// </summary>
        /// <param name="dir">带有键值对的泛型 </param>
        /// <returns>构建完毕的字符串 </returns>
        private string funMakePost(Dictionary <string,string> dir)
        {
            string strPost="";
            foreach (KeyValuePair <string, string> kvp in dir)
            {
                strPost += kvp.Key + "=";
                if (kvp.Value == "")
                {
                    strPost += "''";
                }
                else
                {
                    strPost += kvp.Value;
                }
                strPost += "&";
            }
            strPost = strPost.Substring(0, strPost.Length - 1);
            return strPost;
        }
没有完

      /// <summary>
        /// 获取下一个列表页面的路径
        /// </summary>
        /// <param name="strHtml">当前页面的htmlcode </param>
        /// <returns>下一个列表页面的路径 </returns>
        public string funGetNextUrl(string strHtml)
        {
            string strUrl = "";
            //判断是否是列表型页面
            if (strHtml.IndexOf(" <form") != -1)
            {
                return strUrl;
            }
            string strKey =@"class=""next""";
            strUrl = "http://"+Host+"/bbs/"+strHtml.Substring(strHtml.IndexOf(strKey) - 100, 100).Split('"')[1].Replace("amp;", "");
            return strUrl;
        }         public DataTable funGetListTable(string strHtml)
        {
            DataTable dt = new DataTable();
            DataColumn dc = new DataColumn("Url");
            dt.Columns.Add(dc);
            DataRow dr ;
            string strReg = @"viewthread.php(\S)+highlight=";
            Regex rg = new Regex(strReg);
            MatchCollection mc = rg.Matches(strHtml);             foreach (Match ms in mc)
            {
                dr = dt.NewRow();
                dr[0] = "http://" + Host + "/bbs/" + ms.ToString().Replace("amp;", "");
                dt.Rows.Add(dr);
            }

            return dt;
        }
        /// <summary>
        /// 返回一个包含有页面相关数据的datatable
        /// </summary>
        /// <returns> </returns>
        public DataTable funGetRePlayDatatable()
        {
            //获取目标页面所有内容
            DataTable dtpage = new DataTable("page");
            DataColumn dc0 = new DataColumn("标题");
            DataColumn dc1 = new DataColumn("发表人");
            DataColumn dc2 = new DataColumn("发表时间");
            DataColumn dc3 = new DataColumn("发表内容");
            DataColumn dc4 = new DataColumn("楼数");
            DataColumn dc5 = new DataColumn("所属链接");
            DataColumn dc6 = new DataColumn("类型");             dtpage.Columns.Add(dc0);
            dtpage.Columns.Add(dc1);
            dtpage.Columns.Add(dc2);
            dtpage.Columns.Add(dc3);
            dtpage.Columns.Add(dc4);
            dtpage.Columns.Add(dc5);
            dtpage.Columns.Add(dc6);
            return dtpage;         }
        public DataTable funGetCheater(string strHtml)
        {
            //获取到datatable的格式
            DataTable dtpage = funGetRePlayDatatable();
            DataRow dr;
            //获取发表人的数据
            ArrayList alposter = funGetPoster(strHtml);
            //获取内容列表             //获取楼数列表
            //获取连接列表
            return dtpage;
        }
        /// <summary>
        /// 获取发贴人的列表
        /// </summary>
        /// <param name="strHtml">出入的html </param>
        /// <returns>发帖人的名字集合 </returns>
        public ArrayList funGetPoster(string strHtml)
        {
            ArrayList al = new ArrayList();
            //string strReg = @"id=""userinfo(\S)+""(\s)+class=""dropmenu"">";
            //string strReg = @"id=""userinfo(\S)+""(\s)+class=""dropmenu""(\s)+onmouseover=""showMenu(this.id)"">lucky_cky </a> </cite>";
            string strReg = @"id=""userinfo(\S)+""(\s)+class=""dropmenu""(\s)+onmouseover=""showMenu\(this.id\)"">(\S)+ </a>";
            Regex rg = new Regex(strReg);
            MatchCollection mc = rg.Matches(strHtml);
            foreach (Match ma in mc)
            {
                strReg = @">(\S)+ <";
                Regex regx = new Regex(strReg);
                al.Add(regx.Match(ma.Value).Value.Replace(" <","").Replace(">",""));
                //al.Add(mc.ToString());
            }
            return al;
                        }         public ArrayList funGetRepostContent(string strHtml)
        {
          //  strHtml = strHtml.Replace("\n", "");
            ArrayList al = new ArrayList();
            string strReg = @" <div(\s)*id=(\s)*""postmessage_(.)* </div>";
            Regex reg = new Regex(strReg);
            MatchCollection mc = reg.Matches(strHtml);
            foreach (Match ma in mc)
            {
                al.Add(ma.Value);
            }
            return al;
        }
    }
}

GET /personal/interfaces/hainan/index.jsp HTTP/1.1
Accept: */*
Accept-Language: zh-cn
UA-CPU: x86
Accept-Encoding: gzip, deflate
User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; EmbeddedWB 14.52 from: http://www.bsalsa.com/ EmbeddedWB 14.52; .NET CLR 2.0.50727)
Host: 59.50.113.196:9080
Proxy-Connection: Keep-Alive
HTTP/1.1 200 OK
Server: Apache-Coyote/1.1
X-Powered-By: Servlet 2.4; JBoss-4.2.1.GA (build: SVNTag=JBoss_4_2_1_GA date=200707131605)/Tomcat-5.5
Set-Cookie: JSESSIONID=FD9D50AA193FA6E04C6E363BC9740FA2; Path=/
Content-Type: text/html;charset=GB2312
Transfer-Encoding: chunked
Date: Fri, 25 Jul 2008 15:38:23 GMT736<html>
.....
</html>

原来是这个问题！
http://hi.baidu.com/zkheartboy/blog/item/9216a0fd05591e1508244d74.html
看一下Chunked编码即可。
那个736是个十六进制的ASCII码表示的Chunk大小。

   //构建头
                RequestPPT rppt = new RequestPPT();
                rppt.Accept = "*/* ";
                rppt.ContentType = " text/html;charset=GB2312 ";
                rppt.Method = "GET ";
                rppt.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; EmbeddedWB 14.52";
                strHtml = base.funGetHtmlByCookies(strUrl, post, ccl, rppt); 头信息你看看上面这样行不行,不行你自己按照相应的属性像上面这样设置成你抓下来的包信息

调试易

模拟网页登录高分求助

解决方案 »