转：使用C#的HttpWebRequest模拟登陆网站

这篇文章是有关模拟登录网站方面的。

实现步骤；

1. 启用一个web会话
2. 发送模拟数据请求（POST或者GET）
3. 获取会话的CooKie 并根据该CooKie继续访问登录后的页面，获取后续访问的页面数据。

我们以登录人人网为例，首先需要分析人人网登录时POST的数据格式，这个可以通过IE9中只带的F12快捷键，调出开发人员工具。如下图：

通过开始捕获得到POST的地址和POST的数据

POST数据：

email=aaa@163.com&password=111&icode=&origURL=http%3A%2F%2Fwww.renren.com%2Fhome&domain=renren.com&key_id=1&_rtk=90484476

POST地址：

http://www.renren.com/PLogin.do

下面就是代码示例来得到登录后页面（http://guide.renren.com/guide）的数据

HTMLHelper类

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Net;
using System.IO;
using System.Threading;

namespace Test
{
   public class HTMLHelper
    {
       /// <summary>
        /// 获取CooKie
       /// </summary>
       /// <param name="loginUrl"></param>
       /// <param name="postdata"></param>
       /// <param name="header"></param>
       /// <returns></returns>
       public static CookieContainer GetCooKie(string loginUrl, string postdata, HttpHeader header)
       {
           HttpWebRequest request = null;
           HttpWebResponse response = null;
           try
           {
               CookieContainer cc = new CookieContainer();
               request = (HttpWebRequest)WebRequest.Create(loginUrl);
               request.Method = header.method;
               request.ContentType = header.contentType;
               byte[] postdatabyte = Encoding.UTF8.GetBytes(postdata);
               request.ContentLength = postdatabyte.Length;
               request.AllowAutoRedirect = false;
               request.CookieContainer = cc;
               request.KeepAlive = true;

               //提交请求
               Stream stream;
               stream = request.GetRequestStream();
               stream.Write(postdatabyte, 0, postdatabyte.Length);
               stream.Close();

               //接收响应
               response = (HttpWebResponse)request.GetResponse();
               response.Cookies = request.CookieContainer.GetCookies(request.RequestUri);

               CookieCollection cook = response.Cookies;
               //Cookie字符串格式
               string strcrook = request.CookieContainer.GetCookieHeader(request.RequestUri);

               return cc;
           }
           catch (Exception ex)
           {

               throw ex;
           }
       }

       /// <summary>
       /// 获取html
       /// </summary>
       /// <param name="getUrl"></param>
       /// <param name="cookieContainer"></param>
       /// <param name="header"></param>
       /// <returns></returns>
       public static string GetHtml(string getUrl, CookieContainer cookieContainer,HttpHeader header)
       {
           Thread.Sleep(1000);
           HttpWebRequest httpWebRequest = null;
           HttpWebResponse httpWebResponse = null;
           try
           {
               httpWebRequest = (HttpWebRequest)HttpWebRequest.Create(getUrl);
               httpWebRequest.CookieContainer = cookieContainer;
               httpWebRequest.ContentType = header.contentType;
               httpWebRequest.ServicePoint.ConnectionLimit = header.maxTry;
               httpWebRequest.Referer = getUrl;
               httpWebRequest.Accept = header.accept;
               httpWebRequest.UserAgent = header.userAgent;
               httpWebRequest.Method = "GET";
               httpWebResponse = (HttpWebResponse)httpWebRequest.GetResponse();
               Stream responseStream = httpWebResponse.GetResponseStream();
               StreamReader streamReader = new StreamReader(responseStream, Encoding.UTF8);
               string html = streamReader.ReadToEnd();
               streamReader.Close();
               responseStream.Close();
               httpWebRequest.Abort();
               httpWebResponse.Close();
               return html;
           }
           catch (Exception e)
           {
               if (httpWebRequest != null) httpWebRequest.Abort();
               if (httpWebResponse != null) httpWebResponse.Close();
               return string.Empty;
           }
       }
    }

   public class HttpHeader
   {
       public string contentType { get; set; }

       public string accept { get; set; }

       public string userAgent { get; set; }

       public string method{get;set;}

       public int maxTry { get; set; }
   }
}

测试用例：

  HttpHeader header = new HttpHeader();
                header.accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/x-silverlight, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-ms-application, application/x-ms-xbap, application/vnd.ms-xpsdocument, application/xaml+xml, application/x-silverlight-2-b1, */*";
                header.contentType = "application/x-www-form-urlencoded";
                header.method = "POST";
                header.userAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022)";
                header.maxTry = 300;

                string html = HTMLHelper.GetHtml("http://guide.renren.com/guide", HTMLHelper.GetCooKie("http://www.renren.com/PLogin.do",
                    "email=aaa@163.com&password=111&icode=&origURL=http%3A%2F%2Fwww.renren.com%2Fhome&domain=renren.com&key_id=1&_rtk=90484476", header), header);

                Console.WriteLine(html);

               Console.ReadLine();

通过程序登录了网站后而直接进入登录后的页面。

首先还是发起一个启用一个web会话，然后发送模拟数据请求，获取会话的CooKie，再根据该CooKie将其写入到本地，通过程序直接打开登录后的页面。

该功能可用于无法修改第三方系统源代码而要做系统单点登录。

我们先在HTMLHelper类中添加一个方法：

 1 /// <summary>
 2 /// 获取CookieCollection
 3 /// </summary>
 4 /// <param name="loginUrl"></param>
 5 /// <param name="postdata"></param>
 6 /// <param name="header"></param>
 7 /// <returns></returns>
 8        public static CookieCollection GetCookieCollection(string loginUrl, string postdata, HttpHeader header)
 9        {
10            HttpWebRequest request = null;
11            HttpWebResponse response = null;
12            try
13            {
14                CookieContainer cc = new CookieContainer();
15                request = (HttpWebRequest)WebRequest.Create(loginUrl);
16                request.Method = header.method;
17                request.ContentType = header.contentType;
18                byte[] postdatabyte = Encoding.UTF8.GetBytes(postdata);
19                request.ContentLength = postdatabyte.Length;
20                request.AllowAutoRedirect = false;
21                request.CookieContainer = cc;
22                request.KeepAlive = true;
23
24                //提交请求
25                Stream stream;
26                stream = request.GetRequestStream();
27                stream.Write(postdatabyte, 0, postdatabyte.Length);
28                stream.Close();
29
30                //接收响应
31                response = (HttpWebResponse)request.GetResponse();
32                response.Cookies = request.CookieContainer.GetCookies(request.RequestUri);
33
34                CookieCollection cook = response.Cookies;
35                //Cookie字符串格式
36                string strcrook = request.CookieContainer.GetCookieHeader(request.RequestUri);
37
38                return cook;
39            }
40            catch (Exception ex)
41            {
42
43                throw ex;
44            }
45        }

再根据获取的CookieCollection写入本地，并打开登录后的页面

 1   [DllImport("wininet.dll", CharSet = CharSet.Auto, SetLastError = true)]
 2
 3         public static extern bool InternetSetCookie(string lpszUrlName, string lbszCookieName, string lpszCookieData);
 4
 5
 6   HttpHeader header = new HttpHeader();
 7                 header.accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/x-silverlight, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-ms-application, application/x-ms-xbap, application/vnd.ms-xpsdocument, application/xaml+xml, application/x-silverlight-2-b1, */*";
 8                 header.contentType = "application/x-www-form-urlencoded";
 9                 header.method = "POST";
10                 header.userAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022)";
11                 header.maxTry = 300;
12
13
14  CookieCollection mycookie = HTMLHelper.GetCookieCollection("http://www.renren.com/PLogin.do",
15                     "email=aaa%40163.com&password=111&icode=&origURL=http%3A%2F%2Fwww.renren.com%2Fhome&domain=renren.com&key_id=1&_rtk=90484476", header);
16
17
18  foreach (Cookie cookie in mycookie) //将cookie设置为浏览的cookie
19                 {
20
21                     InternetSetCookie(
22
23                          "http://" + cookie.Domain.ToString(),
24
25                          cookie.Name.ToString(),
26
27                          cookie.Value.ToString() + ";expires=Sun,22-Feb-2099 00:00:00 GMT");
28
29                 }
30                 System.Diagnostics.Process.Start("http://guide.renren.com/guide");

复制代码

这样即可直接通过程序打开登录后的页面：

以上为转发的原文，原文地址：http://blog.csdn.net/htsnoopy/article/details/7094224

可以看到原文下面的评论有好多问到那个postdata从哪里弄到的，这个可以在IE浏览器的F12下看请求正文，但我的理解是还要看网站的登录是采用什么方式传递的，有的就在这里看不到内容，比如原文实验用的人人网站，现在看来在请求正文中就看不到任何内容，还好我工作中遇到的这个项目在请求正文中里恰好能找到原文作者贴出的那个字符串