C#解析HTML

第一种方法：用正则表达式来分析

转自网上的一个实例：所有的href都抽取出来：
using System;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;
namespace HttpGet
{
    class Class1
    {
        [STAThread]
        static void Main(string[] args)
        {
            System.Net.WebClient client = new WebClient();
            byte[] page = client.DownloadData("http://www.google.com");
            string content = System.Text.Encoding.UTF8.GetString(page);
            string regex = "href=[\\\"\\\'](http:\\/\\/|\\.\\/|\\/)?\\w+(\\.\\w+)*(\\/\\w+(\\.\\w+)?)*(\\/|\\?\\w*=\\w*(&\\w*=\\w*)*)?[\\\"\\\']";
            Regex re = new Regex(regex);
            MatchCollection matches = re.Matches(content);

            System.Collections.IEnumerator enu = matches.GetEnumerator();
            while (enu.MoveNext() && enu.Current != null)
            {
                Match match = (Match)(enu.Current);
                Console.Write(match.Value + "\r\n");
            }
        }
    }
}

一些爬虫的HTML解析中也是用的类似的方法。

第二中方法： 利用Winista.Htmlparser.Net 解析Html

1.  下载：

http://www.netomatix.com/Products/DocumentManagement/HTMLParserNet.aspx

2. 使用实例1

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");
        }

        

    }
}

运行效果：
实现取来很容易，结合Winista.Htmlparser源码很快就可以实现想要的效果。

3. 使用实例2

using Winista.Text.HtmlParser;

using Winista.Text.HtmlParser.Tags;

using Winista.Text.HtmlParser.Filters;

using Winista.Text.HtmlParser.Util;

            string str = "<table><tr><td>姓名</td><td>林肯</td></tr><tr><td>年龄</td><td>28</td></tr><tr><td>性别</td><td>男</td></tr><tr><td>姓名</td><td>克林顿</td></tr><tr><td>年龄</td><td>38</td></tr><tr><td>性别</td><td>男</td></tr></table>";

            Parser parser = Parser.CreateParser( str , null );

            NodeList nodes = parser.ExtractAllNodesThatMatch( new TagNameFilter("td") );

            this.Page.Response.Write("<b>原来的html:</b>" + str  );

            this.Page.Response.Write("<b>转换后的html:</b><br>" );

            for( int i = 5 ; i >= 0 ; i-- )

            {

                this.Page.Response.Write( nodes[i*2].FirstChild.ToHtml() + nodes[i*2+1].FirstChild.GetText() + "<br>" );

            }

运行结果如下：

原来的html:

姓名	林肯
年龄	28
性别	男
姓名	克林顿
年龄	38
性别	男

转换后的html:

性别男

年龄38

姓名克林顿

性别男

年龄28

姓名林肯

0

0

0