iLeichun

当前位置: 首页 > C#

C#解析HTML

分类:C#   来源:网络   时间:2010-08-18 11:46:14
方法一:
用System.Net.WebClient下载Web Page存到本地文件或者String中,用正则表达式来分析。这个方法可以用在Web Crawler等需要分析很多Web Page的应用中。
估计这也是大家最直接,最容易想到的一个方法。
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=["¹](http://|./|/)?w+(.w+)*(/w+(.w+)?)*(/|?w*=w*(&w*=w*)*)?["¹]";
            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 + " ");
            }
        }
    }
}

一些爬虫的HTML解析中也是用的类似的方法。
 
方法二:

利用Winista.Htmlparser.Net 解析Html。这是.NET平台下解析Html的开源代码,网上有源码下载,百度一下就能搜到,这里就不提供了。并且有英文的帮助文档。找不到的留下邮箱。
个人认为这是.net平台下解析html不错的解决方案,基本上能够满足我们对html的解析工作。
自己做了个实例:

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");
        } 
    }
}

 

更多