form1.cs

C#编写的网络爬虫程序 效率很高 很好用！

using System;
using System.Drawing;
using System.Collections;
using System.ComponentModel;
using System.IO;
using System.Net;
using System.Text.RegularExpressions;
using System.Windows.Forms;

using mshtml;

using Mf.Service.WebSpider;
using Mf.Util;

namespace Spider
{
	/// <summary>
	/// Summary description for Form1.
	/// </summary>
	public class Form1 : System.Windows.Forms.Form
	{
      private System.Windows.Forms.TabControl tabControl1;
      private System.Windows.Forms.StatusBar statusBar;
      private System.Windows.Forms.StatusBarPanel statusBarPanel;
      private System.Windows.Forms.TabPage tabPage1;
      private System.Windows.Forms.TabPage tabPage2;
      private System.Windows.Forms.Label lblFailedLinks;
      private System.Windows.Forms.Label label1;
      private System.Windows.Forms.TextBox txtOutput;
      private System.Windows.Forms.TextBox txtBaseUri;
      private System.Windows.Forms.Button btnStartStop;
      private System.Windows.Forms.NumericUpDown spnProcessUriMax;
      private System.Windows.Forms.TextBox txtUri;
      private System.Windows.Forms.Label label4;
      private System.Windows.Forms.Label lblBaseUrl;
      private System.Windows.Forms.Label lblUrl;
      private System.Windows.Forms.Label label2;
      private System.Windows.Forms.Button button1;
      private System.Windows.Forms.TextBox txtUrlGraphicsRipper;
      private AxSHDocVw.AxWebBrowser axWebBrowser;
		/// <summary>
		/// Required designer variable.
		/// </summary>
		private System.ComponentModel.Container components = null;

      [STAThread]
      static void Main() 
      {
         Application.Run(new Form1());
      }

		public Form1()
		{
			//
			// Required for Windows Form Designer support
			//
			InitializeComponent();

      }

		/// <summary>
		/// Clean up any resources being used.
		/// </summary>
		protected override void Dispose( bool disposing )
		{
			if( disposing )
			{
				if(components != null)
				{
					components.Dispose();
				}
			}
			base.Dispose( disposing );
		}

		#region Windows Form Designer generated code
		/// <summary>
		/// Required method for Designer support - do not modify
		/// the contents of this method with the code editor.
		/// </summary>
		private void InitializeComponent()
		{
			System.Resources.ResourceManager resources = new System.Resources.ResourceManager(typeof(Form1));
			this.tabControl1 = new System.Windows.Forms.TabControl();
			this.tabPage1 = new System.Windows.Forms.TabPage();
			this.lblFailedLinks = new System.Windows.Forms.Label();
			this.label1 = new System.Windows.Forms.Label();
			this.txtOutput = new System.Windows.Forms.TextBox();
			this.txtBaseUri = new System.Windows.Forms.TextBox();
			this.btnStartStop = new System.Windows.Forms.Button();
			this.spnProcessUriMax = new System.Windows.Forms.NumericUpDown();
			this.txtUri = new System.Windows.Forms.TextBox();
			this.label4 = new System.Windows.Forms.Label();
			this.lblBaseUrl = new System.Windows.Forms.Label();
			this.lblUrl = new System.Windows.Forms.Label();
			this.tabPage2 = new System.Windows.Forms.TabPage();
			this.axWebBrowser = new AxSHDocVw.AxWebBrowser();
			this.button1 = new System.Windows.Forms.Button();
			this.txtUrlGraphicsRipper = new System.Windows.Forms.TextBox();
			this.label2 = new System.Windows.Forms.Label();
			this.statusBar = new System.Windows.Forms.StatusBar();
			this.statusBarPanel = new System.Windows.Forms.StatusBarPanel();
			this.tabControl1.SuspendLayout();
			this.tabPage1.SuspendLayout();
			((System.ComponentModel.ISupportInitialize)(this.spnProcessUriMax)).BeginInit();
			this.tabPage2.SuspendLayout();
			((System.ComponentModel.ISupportInitialize)(this.axWebBrowser)).BeginInit();
			((System.ComponentModel.ISupportInitialize)(this.statusBarPanel)).BeginInit();
			this.SuspendLayout();
			// 
			// tabControl1
			// 
			this.tabControl1.Controls.Add(this.tabPage1);
			this.tabControl1.Controls.Add(this.tabPage2);
			this.tabControl1.Location = new System.Drawing.Point(10, 9);
			this.tabControl1.Name = "tabControl1";
			this.tabControl1.SelectedIndex = 0;
			this.tabControl1.Size = new System.Drawing.Size(700, 585);
			this.tabControl1.TabIndex = 0;
			// 
			// tabPage1
			// 
			this.tabPage1.Controls.Add(this.lblFailedLinks);
			this.tabPage1.Controls.Add(this.label1);
			this.tabPage1.Controls.Add(this.txtOutput);
			this.tabPage1.Controls.Add(this.txtBaseUri);
			this.tabPage1.Controls.Add(this.btnStartStop);
			this.tabPage1.Controls.Add(this.spnProcessUriMax);
			this.tabPage1.Controls.Add(this.txtUri);
			this.tabPage1.Controls.Add(this.label4);
			this.tabPage1.Controls.Add(this.lblBaseUrl);
			this.tabPage1.Controls.Add(this.lblUrl);
			this.tabPage1.Location = new System.Drawing.Point(4, 21);
			this.tabPage1.Name = "tabPage1";
			this.tabPage1.Size = new System.Drawing.Size(692, 560);
			this.tabPage1.TabIndex = 0;
			this.tabPage1.Text = "Broken Links";
			// 
			// lblFailedLinks
			// 
			this.lblFailedLinks.Location = new System.Drawing.Point(10, 112);
			this.lblFailedLinks.Name = "lblFailedLinks";
			this.lblFailedLinks.Size = new System.Drawing.Size(120, 25);
			this.lblFailedLinks.TabIndex = 23;
			this.lblFailedLinks.Text = "Failed Links";
			// 
			// label1
			// 
			this.label1.Location = new System.Drawing.Point(259, 78);
			this.label1.Name = "label1";
			this.label1.Size = new System.Drawing.Size(87, 24);
			this.label1.TabIndex = 22;
			this.label1.Text = "-1 Unlimited";
			// 
			// txtOutput
			// 
			this.txtOutput.Font = new System.Drawing.Font("Courier New", 8.25F, System.Drawing.FontStyle.Regular, System.Drawing.GraphicsUnit.Point, ((System.Byte)(0)));
			this.txtOutput.Location = new System.Drawing.Point(10, 138);
			this.txtOutput.Multiline = true;
			this.txtOutput.Name = "txtOutput";
			this.txtOutput.Size = new System.Drawing.Size(672, 370);
			this.txtOutput.TabIndex = 21;
			this.txtOutput.Text = "";
			// 
			// txtBaseUri
			// 
			this.txtBaseUri.Location = new System.Drawing.Point(182, 43);
			this.txtBaseUri.Name = "txtBaseUri";
			this.txtBaseUri.Size = new System.Drawing.Size(500, 21);
			this.txtBaseUri.TabIndex = 20;
			this.txtBaseUri.Text = "http://www.holidaycoast.net.au/";
			// 
			// btnStartStop
			// 
			this.btnStartStop.Location = new System.Drawing.Point(595, 517);
			this.btnStartStop.Name = "btnStartStop";
			this.btnStartStop.Size = new System.Drawing.Size(90, 25);
			this.btnStartStop.TabIndex = 19;
			this.btnStartStop.Text = "Start";
			this.btnStartStop.Click += new System.EventHandler(this.btnStartStop_Click);
			// 
			// spnProcessUriMax
			// 
			this.spnProcessUriMax.Location = new System.Drawing.Point(182, 78);
			this.spnProcessUriMax.Minimum = new System.Decimal(new int[] {
																			 1,
																			 0,
																			 0,
																			 -2147483648});
			this.spnProcessUriMax.Name = "spnProcessUriMax";
			this.spnProcessUriMax.Size = new System.Drawing.Size(68, 21);
			this.spnProcessUriMax.TabIndex = 18;
			this.spnProcessUriMax.Value = new System.Decimal(new int[] {
																		   100,
																		   0,
																		   0,
																		   0});
			// 
			// txtUri
			// 
			this.txtUri.Location = new System.Drawing.Point(182, 9);
			this.txtUri.Name = "txtUri";
			this.txtUri.Size = new System.Drawing.Size(500, 21);
			this.txtUri.TabIndex = 17;
			this.txtUri.Text = "http://www.holidaycoast.net.au/coffsharbour/";
			// 
			// label4
			// 
			this.label4.Location = new System.Drawing.Point(10, 78);
			this.label4.Name = "label4";
			this.label4.Size = new System.Drawing.Size(163, 24);
			this.label4.TabIndex = 16;
			this.label4.Text = "Process Urls (Max)";
			// 
			// lblBaseUrl
			// 
			this.lblBaseUrl.Location = new System.Drawing.Point(10, 43);
			this.lblBaseUrl.Name = "lblBaseUrl";
			this.lblBaseUrl.Size = new System.Drawing.Size(163, 25);
			this.lblBaseUrl.TabIndex = 15;
			this.lblBaseUrl.Text = "Base Url";
			// 
			// lblUrl
			// 
			this.lblUrl.Location = new System.Drawing.Point(10, 9);
			this.lblUrl.Name = "lblUrl";
			this.lblUrl.Size = new System.Drawing.Size(163, 24);
			this.lblUrl.TabIndex = 14;
			this.lblUrl.Text = "Url";
			// 
			// tabPage2
			// 
			this.tabPage2.Controls.Add(this.axWebBrowser);
			this.tabPage2.Controls.Add(this.button1);
			this.tabPage2.Controls.Add(this.txtUrlGraphicsRipper);
			this.tabPage2.Controls.Add(this.label2);
			this.tabPage2.Location = new System.Drawing.Point(4, 21);
			this.tabPage2.Name = "tabPage2";
			this.tabPage2.Size = new System.Drawing.Size(692, 560);