如何提取网页中链接和标题的正则表达式

 

1.远程抓取：

using System.Text.RegularExpressions;
using System.IO; 

WebClient   w   =   new   WebClient();  
  byte[]   bytes   =   w.DownloadData("http://news.sina.com.cn/");  
  string   strHtml   =   System.Text.Encoding.Default.GetString(bytes);  
   
  string   p   =@"/<a.*href/s*=/s*(?:""(?<url>[^""]*)""|'(?<url>[^']*)'|(?<url>[^/>^/s]+)).*/>(?<title>[^/<^/>]*)/<[^/</a/>]*/a/>";  
   
  Regex   reg   =   new   Regex(p,   RegexOptions.IgnoreCase);  
  MatchCollection   ms   =   reg.Matches(strHtml);  
   
  Console.WriteLine("总共抓取了：{0}条链接。",ms.Count);  
   
  foreach(Match   m   in   ms)  
  {  
  Console.WriteLine("{0}/n{1}/n",   m.Groups["title"].Value,   m.Groups["url"].Value);  
  }  

2.本地测试：

using System.Text.RegularExpressions;
using System.IO; 

 string mystr=@"<A HREF=""http://www.youkuaiyun.com"">aaaa</A>";
            string p = @"/<a.*href/s*=/s*(?:""(?<url>[^""]*)""|'(?<url>[^']*)'|(?<url>[^/>^/s]+)).*/>(?<title>[^/<^/>]*)/<[^/</a/>]*/a/>";
            Regex reg = new Regex(p, RegexOptions.IgnoreCase);
            MatchCollection ms = reg.Matches(mystr);
            foreach(Match   m   in   ms)  
              {  
                  MessageBox.Show (m.Groups["title"].Value);
                  MessageBox.Show(m.Groups["url"].Value);  
              }