C#解析HTML代码,CSharp代码库,德仔网

代码语言

代码分类

【CSharp】 C#解析HTML

作者:dezai / 发布于2014/6/5/ 626

利用Winista.Htmlparser.Net 解析Html。这是.NET平台下解析Html的开源代码


	using System;
	using System.Collections.Generic;
	using System.ComponentModel;
	using System.Data;
	using System.Drawing;
	using System.Linq;
	using System.Text;
	using System.Windows.Forms;
	using Winista.Text.HtmlParser;
	using Winista.Text.HtmlParser.Lex;
	using Winista.Text.HtmlParser.Util;
	using Winista.Text.HtmlParser.Tags;
	using Winista.Text.HtmlParser.Filters;

	namespace HTMLParser
	{
	 public partial class Form1 : Form
	 {
	 public Form1()
	 {
	 InitializeComponent();
	 AddUrl();
	 }

	 private void btnParser_Click(object sender, EventArgs e)
	 {
	 #region 获得网页的html
	 try
	 {

	 txtHtmlWhole.Text = "";
	 string url = CBUrl.SelectedItem.ToString().Trim();
	 System.Net.WebClient aWebClient = new System.Net.WebClient();
	 aWebClient.Encoding = System.Text.Encoding.Default;
	 string html = aWebClient.DownloadString(url);
	 txtHtmlWhole.Text = html;
	 }
	 catch (Exception ex)
	 {
	 MessageBox.Show(ex.Message);
	 }
	 #endregion

	 #region 分析网页html节点
	 Lexer lexer = new Lexer(this.txtHtmlWhole.Text);
	 Parser parser = new Parser(lexer);
	 NodeList htmlNodes = parser.Parse(null);
	 this.treeView1.Nodes.Clear();
	 this.treeView1.Nodes.Add("root");
	 TreeNode treeRoot = this.treeView1.Nodes[0];
	 for (int i = 0; i < htmlNodes.Count; i++)
	 {
	 this.RecursionHtmlNode(treeRoot, htmlNodes[i], false);
	 }

	 #endregion

	 }

	 private void RecursionHtmlNode(TreeNode treeNode, INode htmlNode, bool siblingRequired)
	 {
	 if (htmlNode == null || treeNode == null) return;

	 TreeNode current = treeNode;
	 TreeNode content ;
	 //current node
	 if (htmlNode is ITag)
	 {
	 ITag tag = (htmlNode as ITag);
	 if (!tag.IsEndTag())
	 {
	 string nodeString = tag.TagName;
	 if (tag.Attributes != null && tag.Attributes.Count > 0)
	 {
	 if (tag.Attributes["ID"] != null)
	 {
	 nodeString = nodeString + " { id=\"" + tag.Attributes["ID"].ToString() + "\" }";
	 }
	 if (tag.Attributes["HREF"] != null)
	 {
	 nodeString = nodeString + " { href=\"" + tag.Attributes["HREF"].ToString() + "\" }";
	 }
	 }
	
	 current = new TreeNode(nodeString);
	 treeNode.Nodes.Add(current);
	 }
	 }

	 //获取节点间的内容
	 if (htmlNode.Children != null && htmlNode.Children.Count > 0)
	 {
	 this.RecursionHtmlNode(current, htmlNode.FirstChild, true);
	 content = new TreeNode(htmlNode.FirstChild.GetText());
	 treeNode.Nodes.Add(content);
	 }

	 //the sibling nodes
	 if (siblingRequired)
	 {
	 INode sibling = htmlNode.NextSibling;
	 while (sibling != null)
	 {
	 this.RecursionHtmlNode(treeNode, sibling, false);
	 sibling = sibling.NextSibling;
	 }
	 }
	 }
	 private void AddUrl()
	 {
	 CBUrl.Items.Add("http://www.hao123.com");
	 CBUrl.Items.Add("http://www.sina.com");
	 CBUrl.Items.Add("http://www.heuet.edu.cn");
	 }

	

	 }
	}

评论列表

本站所提供的代码，版权归原作者所有，若有侵犯作者版权，请与我们联系，我们将立即删除或修改。谢谢!
本站所有代码发布及提供者。

试试其它关键字

　解析HTML　

同语言下

可能有用的

dezai贡献的其它代码(1065)