利用HttpRequest登录到某个网站,然后获取网站信息的程序示例

问题:有的网站的相关内容必须要在登录后才可以查看,其登录信息保存在session变量之中。这样,使用asphttp等组件就难以正确得到所要的信息。

解决:使用asp.net中的httprequest和httpresponse来实现。

要点:
1。 通过附加一个cookiecontainer到httprequest对象中,可以得到登录后返回的代表SESSION ID的COOKIE。 见Login方法
2。 将此COOKIE包含在一个cookiecontainer中并附加到另一个HTTPREQUEST请求中,则可以实现SESSION的还原。见getPage方法

源程序如下:

getHttpInfo.aspx:

<%@ Page language="c#" Codebehind="getHttpInfo.aspx.cs" AutoEventWireup="false" Inherits="PdfTest.getHttpInfo"%>
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" >
<HTML>
<HEAD>
<title>WebForm1</title>
<meta content="Microsoft Visual Studio 7.0" name="GENERATOR">
<meta content="C#" name="CODE_LANGUAGE">
<meta content="JavaScript" name="vs_defaultClientScript">
<meta content="http://schemas.microsoft.com/intellisense/ie5" name="vs_targetSchema">
</HEAD>
<body>
<form id="Form1" method="post" runat="server">
</form>
</body>
</HTML>

getHttpInfo.aspx.cs:

using System;
using System.Collections;
using System.ComponentModel;
using System.Data;
//using System.Data.OleDb;
using System.Drawing;
using System.Web;
using System.Web.SessionState;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.HtmlControls;
using System.Net;
using System.IO;
using System.Text;
using System.Text.RegularExpressions;
using Microsoft.Data.Odbc;

namespace PdfTest
{
/// &lt;summary&gt;
/// Summary description for WebForm1.
/// &lt;/summary&gt;
public class getHttpInfo : System.Web.UI.Page
{
protected static string cookieheader;


private void Page_Load(object sender, System.EventArgs e)
{
// Put user code to initialize the page here

string strResult;

if (HttpContext.Current.Application["cookieheader"] != null)
{
cookieheader
= (string)HttpContext.Current.Application["cookieheader"];
}
else
{
//Login into the website and keep the cookie for the session in the application variable
string strLogin = Login("http://www.thesiteyouwanttovisit/theloginpage.asp", "Action=&USERID=&Password=") ;
}

strResult
= getPage("http://www.thesiteyouwanttovisit/theloginpage.asp", "Action=&data=") ;


//Write the result to htm file
FileStream htmFile = new FileStream("c:\save.htm", FileMode.OpenOrCreate);
StreamWriter sw
= new StreamWriter(htmFile);
sw.Write(strResult);
sw.Close();
htmFile.Close();

// output the result
Response.Write(strResult);
}


public static string Login(String url, String paramList)
{
HttpWebResponse res
= null;
string strResult="";

try
{

HttpWebRequest req
= (HttpWebRequest)WebRequest.Create(url);
req.Method
= "POST";
req.ContentType
= "application/x-www-form-urlencoded";
req.AllowAutoRedirect
= false;
CookieContainer cookieCon
= new CookieContainer();
req.CookieContainer
= cookieCon;

StringBuilder UrlEncoded
= new StringBuilder();
Char[] reserved
= {'?', '=', '&'};
byte[] SomeBytes = null;

if (paramList != null)
{
int i=0, j;
while(i&lt;paramList.Length)
{
j
=paramList.IndexOfAny(reserved, i);
if (j==-1)
{
UrlEncoded.Append(HttpUtility.UrlEncode(paramList.Substring(i, paramList.Length
-i)));
break;
}
UrlEncoded.Append(HttpUtility.UrlEncode(paramList.Substring(i, j
-i)));
UrlEncoded.Append(paramList.Substring(j,
1));
i
= j+1;
}
SomeBytes
= Encoding.UTF8.GetBytes(UrlEncoded.ToString());
req.ContentLength
= SomeBytes.Length;
Stream newStream
= req.GetRequestStream();
newStream.Write(SomeBytes,
0, SomeBytes.Length);
newStream.Close();
}
else
{
req.ContentLength
= 0;
}


res
= (HttpWebResponse)req.GetResponse();
cookieheader
= req.CookieContainer.GetCookieHeader(new Uri(url));
HttpContext.Current.Application.Lock();
HttpContext.Current.Application[
"cookieheader"] = cookieheader;
HttpContext.Current.Application.UnLock();

Stream ReceiveStream
= res.GetResponseStream();
Encoding encode
= System.Text.Encoding.GetEncoding("utf-8");
StreamReader sr
= new StreamReader( ReceiveStream, encode );
Char[] read
= new Char[256];
int count = sr.Read( read, 0, 256 );
while (count &gt; 0)
{
String str
= new String(read, 0, count);
strResult
+= str;
count
= sr.Read(read, 0, 256);
}
}
catch(Exception e)
{
strResult
= e.ToString();
}
finally
{
if ( res != null )
{
res.Close();
}
}

return strResult;
}


public static string getPage(String url, String paramList)
{
HttpWebResponse res
= null;
string strResult = "";

try
{

HttpWebRequest req
= (HttpWebRequest)WebRequest.Create(url);
req.Method
= "POST";
req.KeepAlive
= true;
req.ContentType
= "application/x-www-form-urlencoded";
CookieContainer cookieCon
= new CookieContainer();
req.CookieContainer
= cookieCon;
req.CookieContainer.SetCookies(
new Uri(url),cookieheader);
StringBuilder UrlEncoded
= new StringBuilder();
Char[] reserved
= {'?', '=', '&'};
byte[] SomeBytes = null;

if (paramList != null)
{
int i=0, j;
while(i&lt;paramList.Length)
{
j
=paramList.IndexOfAny(reserved, i);
if (j==-1)
{
UrlEncoded.Append(HttpUtility.UrlEncode(paramList.Substring(i, paramList.Length
-i)));
break;
}
UrlEncoded.Append(HttpUtility.UrlEncode(paramList.Substring(i, j
-i)));
UrlEncoded.Append(paramList.Substring(j,
1));
i
= j+1;
}
SomeBytes
= Encoding.UTF8.GetBytes(UrlEncoded.ToString());
req.ContentLength
= SomeBytes.Length;
Stream newStream
= req.GetRequestStream();
newStream.Write(SomeBytes,
0, SomeBytes.Length);
newStream.Close();
}
else
{
req.ContentLength
= 0;
}


res
= (HttpWebResponse)req.GetResponse();
Stream ReceiveStream
= res.GetResponseStream();
Encoding encode
= System.Text.Encoding.GetEncoding("utf-8");
StreamReader sr
= new StreamReader( ReceiveStream, encode );
Char[] read
= new Char[256];
int count = sr.Read( read, 0, 256 );
while (count &gt; 0)
{
String str
= new String(read, 0, count);
strResult
+= str;
count
= sr.Read(read, 0, 256);
}
}
catch(Exception e)
{
strResult
= e.ToString();
}
finally
{
if ( res != null )
{
res.Close();
}
}

return strResult;
}


#region Web Form Designer generated code
override protected void OnInit(EventArgs e)
{
//
// CODEGEN: This call is required by the ASP.NET Web Form Designer.
//
InitializeComponent();
base.OnInit(e);
}

/// &lt;summary&gt;
/// Required method for Designer support - do not modify
/// the contents of this method with the code editor.
/// &lt;/summary&gt;
private void InitializeComponent()
{
this.Load += new System.EventHandler(this.Page_Load);

}
#endregion


}
}

posted @ 2004-12-22 21:08  dudu  阅读(8266)  评论(7编辑  收藏  举报