用asp.net实现取页面中的所有链接

OGeek|极客世界-中国程序员成长平台 › 门户 › 编程› 服务器相关›DOS 命令学习手册

原作者: [db:作者] 来自: [db:来源] 收藏邀请

private void Page_Load(object sender, System.EventArgse)
  {
   //在此处放置用户代码以初始化页面

   string url =https://www.ogeek.net;
   System.Net.HttpWebRequesthttpReq;
   System.Net.HttpWebResponsehttpRes;
   System.UrihttpURL = new Uri(url);
   httpReq =(System.Net.HttpWebRequest)System.Net.WebRequest.Create(httpURL);
   httpReq.Method= "GET";
   httpRes= (System.Net.HttpWebResponse)httpReq.GetResponse();
   httpReq.KeepAlive= false;
   System.IO.StreamReadersReader = newSystem.IO.StreamReader(httpRes.GetResponseStream(),System.Text.Encoding.GetEncoding("GB2312"));
   stringres = sReader.ReadToEnd();
   //以下是利用正则表达式对获取的文本流进行过滤
   stringstrRegex = @"<a.+?a>";
   System.Text.RegularExpressions.Regexr;
   System.Text.RegularExpressions.MatchCollectionm;
   r = newSystem.Text.RegularExpressions.Regex(strRegex,System.Text.RegularExpressions.RegexOptions.IgnoreCase);
   m =r.Matches(res);
   Response.Write("该页共有"+m.Count + " 个超连接<br/>");
   for (inti = 0; i < m.Count; i++)
   {
    Response.Write(m[i].Value+ "<br/>");
   }
  }