getweblink.aspx.cs

ASP C#代码实例 适合初学人士学习使用

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

namespace Example_12_25
{
	/// <summary>
	/// GetWebLink 的摘要说明。
	/// </summary>
	public class GetWebLink : System.Web.UI.Page
	{
		protected System.Web.UI.WebControls.Label Label1;
		protected System.Web.UI.WebControls.TextBox urlTextBox;
		protected System.Web.UI.WebControls.Button scrapeButton;
		protected System.Web.UI.WebControls.Label TipResult;
		protected System.Web.UI.WebControls.TextBox resultLabel;
	
		private StringBuilder report = new StringBuilder();
		private String webPage;
		private int countOfMatches;

		private void Page_Load(object sender, System.EventArgs e)
		{			
			Label1.Text = "请输入一个URL地址：";
			scrapeButton.Text = "分离Href链接";
		}

		#region Web 窗体设计器生成的代码
		override protected void OnInit(EventArgs e)
		{
			//
			// CODEGEN: 该调用是 ASP.NET Web 窗体设计器所必需的。
			//
			InitializeComponent();
			base.OnInit(e);
		}
		
		/// <summary>
		/// 设计器支持所需的方法 - 不要使用代码编辑器修改
		/// 此方法的内容。
		/// </summary>
		private void InitializeComponent()
		{    
			this.scrapeButton.Click += new System.EventHandler(this.scrapeButton_Click);
			this.Load += new System.EventHandler(this.Page_Load);

		}
		#endregion

		private void scrapeButton_Click(object sender, System.EventArgs e)
		{
			webPage = GrabUrl();

			MatchEvaluator myDelegate = new MatchEvaluator(MatchHandler);

			Regex linksExpression = new Regex(@"\<a.+?href=['""](?!http\:\/\/)(?!mailto\:)(?>foundAnchor>[^'"">]+?)[^>]*?\>",
				RegexOptions.Multiline | RegexOptions.IgnoreCase | RegexOptions.IgnorePatternWhitespace);
			String newWebPage = linksExpression.Replace(webPage, myDelegate);

			TipResult.Text = "<h2>从 " + urlTextBox.Text + "分离出的Href链接</h2>" + "<b>找到并整理"
				+ countOfMatches.ToString() + " 个链接</b><br><br>" + report.ToString().Replace(Environment.NewLine, "<br>");
			TipResult.Text += "<h2>整理过的页面</h2><script>window.document.title='抓取网页中的链接'</script>";
			resultLabel.Text = newWebPage;
		}

		private String MatchHandler(Match m)
		{
			String link = m.Groups["foundAnchor"].Value;
			Regex rTol = new Regex("^",RegexOptions.Multiline | RegexOptions.RightToLeft);
			int col,row;
			int lineBegin = rTol.Match(webPage,m.Index).Index;
			row = rTol.Matches(webPage,m.Index).Count;
			col = m.Index - lineBegin;
			report.AppendFormat("Link <b>{0}</b>, fixed at row:{1},col:{2}{3}",
				Server.HtmlEncode(m.Groups[0].Value),row,col,Environment.NewLine);

			String newLink;
			if(link.StartsWith("/") == true)
			{
				newLink = link.Substring(1);
			}
			else
			{
				newLink = link;
			}
			countOfMatches++;
			return(m.Groups[0].Value.Replace(link,newLink));
		}

		private String GrabUrl()
		{
			WebClient wclient = new WebClient();
			Stream stream = wclient.OpenRead(urlTextBox.Text);
			StreamReader readStream = new StreamReader(stream,Encoding.Default);
		
			String url = readStream.ReadToEnd();
			stream.Close();

			return(url);
		}
	}
}