取得到网页原码后如何分析其中内容，使其变成DOM树结构？

谢谢你的回答。。为什么我在你这个网站查内容就查不到这样的东西？这个是 axWebBrowser 与 mshtml 的组合。
现在我已经有一个 string html 了。怎么使其成为 DOM 树结构。。或是不用 mshtml 也可以。

我找到这篇文章应该对你有帮助的！
http://www.talkaboutsoftware.com/group/microsoft.public.inetsdk.programming.html_objmodel/messages/5247.html

用dom对象的fromtext方法（）；

默認的情況IE中就有一個DOM树﹐只要你按照DOM树方式就可以提取或更新數據。

我做的方式就是截取到html源码后，对具体需要的内容已string的方式获得，然后再添加些元素，使其成为一个xml文件，然后再作后面的工作

using System;
using System.Drawing;
using System.Collections;
using System.ComponentModel;
using System.Windows.Forms;
using System.Data;
using System.Text.RegularExpressions;
using System.IO;namespace CSharpHTMLExtractor
{
/// <summary>
/// Summary description for Form1.
/// </summary>
public class frmHTMLExtractor : System.Windows.Forms.Form
{ Int32 intMatchesMade = 0;
Regex extractHTMLRegex =
new Regex("<(?<outertag>[a-z]+[\\d]?)(?<attributes> [^>]*)*>" +
"(?<innerhtml>(<(?<innertag>[a-z]+[\\d]?)[^>]*>.*?</\\k<innertag>>|" +
"<[a-z]+[\\d]?[^>]*>|(?>[^<]*))*(?=</\\k<outertag>>))?",
RegexOptions.IgnoreCase |
RegexOptions.Compiled |
RegexOptions.ExplicitCapture |
RegexOptions.Singleline);

internal System.Windows.Forms.OpenFileDialog OpenFileDialog1;
internal System.Windows.Forms.TextBox txtInputText;
internal System.Windows.Forms.Button cmdDisplayHTML;
internal System.Windows.Forms.TreeView HTMLTreeView;
internal System.Windows.Forms.Button cmdOpenHTML;
/// <summary>
/// Required designer variable.
/// </summary>
private System.ComponentModel.Container components = null; public frmHTMLExtractor()
{
//
// Required for Windows Form Designer support
//
InitializeComponent(); //
// TODO: Add any constructor code after InitializeComponent call
//
} /// <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()
{
         this.OpenFileDialog1 = new System.Windows.Forms.OpenFileDialog();
         this.txtInputText = new System.Windows.Forms.TextBox();
         this.cmdDisplayHTML = new System.Windows.Forms.Button();
         this.HTMLTreeView = new System.Windows.Forms.TreeView();
         this.cmdOpenHTML = new System.Windows.Forms.Button();
         this.SuspendLayout();
         //
         // OpenFileDialog1
         //
         this.OpenFileDialog1.Filter = "Web Pages|*.htm;*.html;*.asp;";
         this.OpenFileDialog1.FileOk += new System.ComponentModel.CancelEventHandler(this.OpenFileDialog1_FileOk);
         //
         // txtInputText
         //
         this.txtInputText.Font = new System.Drawing.Font("Verdana", 9F, System.Drawing.FontStyle.Regular, System.Drawing.GraphicsUnit.Point, ((System.Byte)(0)));
         this.txtInputText.Location = new System.Drawing.Point(32, 69);
         this.txtInputText.Multiline = true;
         this.txtInputText.Name = "txtInputText";
         this.txtInputText.ScrollBars = System.Windows.Forms.ScrollBars.Vertical;
         this.txtInputText.Size = new System.Drawing.Size(704, 243);
         this.txtInputText.TabIndex = 31;
         this.txtInputText.Text = "";
         //
         // cmdDisplayHTML
         //
         this.cmdDisplayHTML.Font = new System.Drawing.Font("Verdana", 9F, System.Drawing.FontStyle.Regular, System.Drawing.GraphicsUnit.Point, ((System.Byte)(0)));
         this.cmdDisplayHTML.Location = new System.Drawing.Point(205, 20);
         this.cmdDisplayHTML.Name = "cmdDisplayHTML";
         this.cmdDisplayHTML.Size = new System.Drawing.Size(161, 39);
         this.cmdDisplayHTML.TabIndex = 30;
         this.cmdDisplayHTML.Text = "Display HTML Tree";
         this.cmdDisplayHTML.Click += new System.EventHandler(this.cmdDisplayHTML_Click);
         //
         // HTMLTreeView
         //
         this.HTMLTreeView.CausesValidation = false;
         this.HTMLTreeView.Font = new System.Drawing.Font("Microsoft Sans Serif", 9F, System.Drawing.FontStyle.Regular, System.Drawing.GraphicsUnit.Point, ((System.Byte)(0)));
         this.HTMLTreeView.ImageIndex = -1;
         this.HTMLTreeView.Location = new System.Drawing.Point(32, 336);
         this.HTMLTreeView.Name = "HTMLTreeView";
         this.HTMLTreeView.Nodes.AddRange(new System.Windows.Forms.TreeNode[] {
                                                                                 new System.Windows.Forms.TreeNode("HTML Document")});
         this.HTMLTreeView.SelectedImageIndex = -1;
         this.HTMLTreeView.Size = new System.Drawing.Size(704, 320);
         this.HTMLTreeView.TabIndex = 29;
         //
         // cmdOpenHTML
         //
         this.cmdOpenHTML.Font = new System.Drawing.Font("Verdana", 9.75F, System.Drawing.FontStyle.Regular, System.Drawing.GraphicsUnit.Point, ((System.Byte)(0)));
         this.cmdOpenHTML.Location = new System.Drawing.Point(31, 20);
         this.cmdOpenHTML.Name = "cmdOpenHTML";
         this.cmdOpenHTML.Size = new System.Drawing.Size(161, 39);
         this.cmdOpenHTML.TabIndex = 28;
         this.cmdOpenHTML.Text = "Open HTML File";
         this.cmdOpenHTML.Click += new System.EventHandler(this.cmdOpenHTML_Click);
         //
         // frmHTMLExtractor
         //
         this.AutoScaleBaseSize = new System.Drawing.Size(6, 15);
         this.ClientSize = new System.Drawing.Size(776, 687);
         this.Controls.AddRange(new System.Windows.Forms.Control[] {
                                                                      this.cmdDisplayHTML,
                                                                      this.HTMLTreeView,
                                                                      this.cmdOpenHTML,
                                                                      this.txtInputText});
         this.Name = "frmHTMLExtractor";
         this.Text = "HTML Extractor";
         this.ResumeLayout(false);      }
#endregion /// <summary>
/// The main entry point for the application.
/// </summary>
[STAThread]
static void Main()
{
Application.Run(new frmHTMLExtractor());
} private void cmdOpenHTML_Click(object sender, System.EventArgs e)
{
OpenFileDialog1.ShowDialog();
} private void cmdDisplayHTML_Click(object sender, System.EventArgs e)
{
intMatchesMade = 0;
HTMLTreeView.Nodes.Clear();
HTMLTreeView.Nodes.Add(populateTagNode(this.txtInputText.Text, "HTML Document"));
HTMLTreeView.ExpandAll();
MessageBox.Show("Completed " + intMatchesMade + " matches");
} private void OpenFileDialog1_FileOk(object sender, System.ComponentModel.CancelEventArgs e)
{
String filePath = OpenFileDialog1.FileName;
StreamReader streamReaderRegex = File.OpenText(filePath);
this.txtInputText.Text = streamReaderRegex.ReadToEnd();
streamReaderRegex.Close();
} private  TreeNode populateTagNode(String sInputString,
String sTitleText)
{

TreeNode htmlTagNode = new TreeNode(); try
{
MatchCollection matchesFound;

TreeNode htmlSubTagNode;
String sTag;
matchesFound = extractHTMLRegex.Matches(sInputString); htmlTagNode.Text = sTitleText;
foreach (Match matchMade in matchesFound)
{
intMatchesMade = intMatchesMade + 1;
sTag = "<" + matchMade.Groups[1].Value +
matchMade.Groups[2].Value + ">";
htmlSubTagNode =
populateTagNode(matchMade.Groups[3].Value,
sTag);
htmlTagNode.Nodes.Add(htmlSubTagNode);
}

}
catch (ArgumentException ex)
{
MessageBox.Show("The following error occurred "
+ "\r\n" + ex.Message);
} return htmlTagNode;
}
}
}

摘自C#字符串和正则表达式参考手册(Wrox)
所以说买书并不是坏事！比如就可以加分的说
当然，没有耐心读到后面的章节是不会知道这个问题的解决办法di~~~
所以大家不但要买书，而且还要读书！！像我这样，读了25本及以上的.NET和软件工程以及数学方面的书，忘的不少，但是每及一个问题出现，头脑中便会映出问题的解决方法，最差也会记起在xx书xx页，这不也是学到了东西了么？

string html = "<table><tr><td>test</td></tr></table>";//这里存放着通过其它方法得到
XmlDocument doc = new XmlDocument();
doc.LoadXml(html);//前提是你这个html必须符合xml规范，举个例子，如过获得的html源码有<br>你应该替换成<br/>

to chestnuts(c# Sharp)
>-）,买书好像不可以加分哦，哈哈挺佩服你的，向你学习！

你小子不会把wrox的书都买了吧
----
摘自C#字符串和正则表达式参考手册(Wrox)
所以说买书并不是坏事！比如就可以加分的说
当然，没有耐心读到后面的章节是不会知道这个问题的解决办法di~~~
所以大家不但要买书，而且还要读书！！像我这样，读了25本及以上的.NET和软件工程以及数学方面的书，忘的不少，但是每及一个问题出现，头脑中便会映出问题的解决方法，最差也会记起在xx书xx页，这不也是学到了东西了么？

够强啊，俺可就差远了，.Net的书完完全全看完的也只有一两本。可能是买书买得少的原因啊。书中的内容也记不清，甭说x书y页z行啊。pfpf。从楼上可知，学好.Net，必须要多买书，要想成为高手，至少要看25本以上.Net、软件工程、数学建模、算法等书，要想成为高手中的高手，必须要记得每本书的内容，最差也得知道在###页。 555555555555555555555555，我一生无望啊！！！！

偶也买了2x多本，其中wrox的1x本，大部分看了80％，总是没有坚持看完。降龙十八掌就是练不成，就差那20％

向chestnuts(c# Sharp)学习,我C#的书就看一两本

调试易

取得到网页原码后如何分析其中内容，使其变成DOM树结构？

解决方案 »