运用C#在采集时进行自动验证登录[转]

首先打开网站，查看源文件，找到他的登录表单部分。
比如：

<form name="login" action="loginMain.jsp" method="POST" target="_top">
      <table width="218" border="0" cellspacing="0" cellpadding="0">
        <tr>
          <td width="50" height="28" class="hui"><div align="right">用户名：</div></td>
          <td width="168" height="28"><input class="hui" id="username" 
            maxlength="40" size="23" name="username" id="username" /></td>
        </tr>
        <tr>
          <td height="28" class="hui"><div align="right">密　码：</div></td>
          <td height="28"><input class="hui" id="passwd" 
            maxlength="40" size="23" name="passwd" type="password" id="passwd" /></td>
        </tr>
      </table>
</form>

 

从以上表单可以看出，表单提交的方法是：POST，提交至loginMain.jsp处理,共有两个表单项即：username、passwd

下面是C#模仿登录程序:Login.cs

using System;
using System.Data;
using System.Net;
using System.Text;
using System.IO;
using System.Text.RegularExpressions;

/// <summary>
 /// 登录网站并获取Cookies
 /// </summary>
 /// <returns>成功登录的Cookie信息</returns>
public static CookieContainer Get_Login()
 {
             CookieContainer cc = new CookieContainer();
            string FormURL="http://blog.hnce.net/loginMain.jsp";                
//处理表单的绝对URL地址
            string FormData = "username=slick&passwd=hedy12345";    
//表单需要提交的参数，注意改为你已注册的信息。
             ASCIIEncoding encoding = new ASCIIEncoding();
            byte[] data = encoding.GetBytes(FormData);

             HttpWebRequest request = (HttpWebRequest)WebRequest.Create(FormURL);
             request.Method = "POST";    //数据提交方式
             request.ContentType = "application/x-www-form-urlencoded";
             request.ContentLength = data.Length;
             request.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)";
            //模拟一个UserAgent
             Stream newStream = request.GetRequestStream();
             newStream.Write(data, 0, data.Length);

             newStream.Close();
                   
             request.CookieContainer = cc;
                   
             HttpWebResponse response = (HttpWebResponse)request.GetResponse();
             cc.Add(response.Cookies);
             Stream stream = response.GetResponseStream();
            string WebContent = new StreamReader(stream, System.Text.Encoding.Default).ReadToEnd();
            return cc;
}

 

调用以上的方法来获取需要登录才能查看的内容。

 

 

CookieContainer cc = new CookieContainer();
             cc = Login.Get_Login();            //获取登录Cookies

            string PhotoClassURL = "http://blog.hnce.net/xxx.jsp";
             HttpWebRequest Myrequest = (HttpWebRequest)WebRequest.Create(PhotoClassURL);
             Myrequest.CookieContainer = cc;
             HttpWebResponse Myresponse = (HttpWebResponse)Myrequest.GetResponse();
             cc.Add(Myresponse.Cookies);
             Stream Mystream = Myresponse.GetResponseStream();
            string sHtml = new StreamReader(Mystream, System.Text.Encoding.Default).ReadToEnd();

 

sHtml即为你登录之后看到的内容