利用WebClient和WebRequest类获得网页源代码

利用.NET框架提供的 WebClient类和 WebRequest类,我们可以很轻易地得到给定URL地址的源代码,很简单,以下是C#的完整的例子.

查看例子
http://dotnet.aspx.cc/Exam/GetPageHtml.aspx

GetPageHtml.aspx

<%@ Page language="c#" validateRequest = "false" Codebehind="GetPageHtml.aspx.cs"

AutoEventWireup="false" Inherits="eMeng.Exam.GetPageHtml" %>

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" >

<HTML>

<HEAD>

<title>得到网页源代码</title>

</HEAD>

<div align="center" style="FONT-WEIGHT: bold">得到任意网页源代码</div>

<asp:TextBox id="UrlText" runat="server" Width="400px">http://dotnet.aspx.cc/content.aspx

</asp:TextBox>

<asp:Button id="WebClientButton" Runat="server" Text="用WebClient得到"></asp:Button>

<asp:Button id="WebRequestButton" runat="server" Text="用WebRequest得到"></asp:Button>

<br>

<asp:TextBox id="ContentHtml" runat="server" Width="100%" Height="360px" TextMode="MultiLine">

</asp:TextBox>

</form>

</body>

</HTML>

GetPageHtml.aspx.cs

using System;

using System.Collections;

using System.ComponentModel;

using System.Data;

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.IO;

using System.Net;

using System.Text;

using System.Text.RegularExpressions;

namespace eMeng.Exam

{

/// <summary>

/// GetPageHtml 的摘要说明。

/// </summary>

public class GetPageHtml : System.Web.UI.Page

{

protected System.Web.UI.WebControls.Button WebClientButton;

protected System.Web.UI.WebControls.Button WebRequestButton;

protected System.Web.UI.WebControls.TextBox ContentHtml;

protected System.Web.UI.WebControls.TextBox UrlText;

protected System.Web.UI.WebControls.Button GetText;

private string PageUrl = "";

private void Page_Load(object sender, System.EventArgs e)

{ }

Web Form Designer generated code

private void WebClientButton_Click(object sender, System.EventArgs e)

{

PageUrl = UrlText.Text;

WebClient wc = new WebClient();

wc.Credentials = CredentialCache.DefaultCredentials;

///方法一：

Byte[] pageData = wc.DownloadData(PageUrl);

ContentHtml.Text = Encoding.Default.GetString(pageData);

/// 方法二：

/// ***************代码开始**********

/// Stream resStream = wc.OpenRead(PageUrl);

/// StreamReader sr = new StreamReader(resStream,System.Text.Encoding.Default);

/// ContentHtml.Text = sr.ReadToEnd();

/// resStream.Close();

/// **************代码结束********

///

wc.Dispose();

}

private void WebRequestButton_Click(object sender, System.EventArgs e)

{

PageUrl = UrlText.Text;

WebRequest request = WebRequest.Create(PageUrl);

WebResponse response = request.GetResponse();

Stream resStream = response.GetResponseStream();

StreamReader sr = new StreamReader(resStream, System.Text.Encoding.Default);

ContentHtml.Text = sr.ReadToEnd();

resStream.Close();

sr.Close();

}

private void GetText_Click(object sender, System.EventArgs e)

{

PageUrl = UrlText.Text;

WebRequest request = WebRequest.Create(PageUrl);

WebResponse response = request.GetResponse();

Stream resStream = response.GetResponseStream();

StreamReader sr = new StreamReader(resStream, System.Text.Encoding.Default);

ContentHtml.Text = sr.ReadToEnd();

resStream.Close();

sr.Close();

ContentHtml.Text = Regex.Replace(ContentHtml.Text, "<[^>]*>", "");

//替换空格

ContentHtml.Text = Regex.Replace(ContentHtml.Text, "\\s+", " ");

}

http://www.chenjiliang.com/Article/View.aspx?ArticleID=1193&TypeID=5

posted on 2007-01-29 11:12 mbskys 阅读(110) 评论(0) 收藏举报