读取html内容代码,Asp.Net代码库,德仔网

代码语言

代码分类

【Asp.Net】读取html内容

作者:lybwwp / 发布于2014/1/26/ 578

 #region 读取html页面内容
    /// <summary>
    /// 读取html页面内容
    /// </summary>
    /// <param name="uri">网址</param>
    /// <param name="xpath">xpath标签</param>
    /// <returns></returns>
    private string GetWellFormedHTML(string uri, string xpath)
    {
      StreamReader sReader = null;//读取字节流
      StringWriter sw = null;//写入字符串
      SgmlReader reader = null;//sgml读取方法
      XmlTextWriter writer = null;//生成xml数据流
      try
      {
        if (uri == String.Empty)
          uri = "http://www.ypshop.net/list--91-940-940--search-1.html";
        WebClient webclient = new WebClient();
        webclient.Encoding = Encoding.UTF8;
        //页面内容
        string strWebContent = webclient.DownloadString(uri);


        reader = new SgmlReader();
        reader.DocType = "HTML";
        reader.InputStream = new StringReader(strWebContent);


        sw = new StringWriter();
        writer = new XmlTextWriter(sw);
        writer.Formatting = Formatting.Indented;
        while (reader.Read())
        {
          if (reader.NodeType != XmlNodeType.Whitespace)
          {
            writer.WriteNode(reader, true);
          }
        }
        return sw.ToString();
       
      }
      catch (Exception exp)
      {
        writer.Close();
        reader.Close();
        sw.Close();
        sReader.Close();
        return exp.Message;
      }
    }

    #endregion



下面这个是参考的

/// <summary>
 
    private string GetWellFormedHTML_Handle(string uri)
    {
      StreamReader sReader = null;
      StringWriter sw = null;
      SgmlReader reader = null;
      XmlTextWriter writer = null;
      try
      {
        if (uri == String.Empty) uri = "http://www.ypshop.net/list--91-940-940--search-1.html";
       HttpWebRequest req = (HttpWebRequest)WebRequest.Create(uri);
        HttpWebResponse res = (HttpWebResponse)req.GetResponse();
        sReader = new StreamReader(res.GetResponseStream());


        reader = new SgmlReader();
        reader.DocType = "HTML";
        reader.InputStream = new StringReader(sReader.ReadToEnd());


        sw = new StringWriter();
        writer = new XmlTextWriter(sw);
        writer.Formatting = Formatting.Indented;
        while (reader.Read())
        {
          if (reader.NodeType != XmlNodeType.Whitespace)
          {
            writer.WriteNode(reader, true);
          }
        }


        StringBuilder sb = new StringBuilder();
        XPathDocument doc = new XPathDocument(new StringReader(sw.ToString()));
        XPathNavigator nav = doc.CreateNavigator();
        //XPathNodeIterator nodes = nav.Select(xpath);
        //while (nodes.MoveNext())
        //{
        //  sb.Append(nodes.Current.Value + " ");
        //}
        return sb.ToString();


      }
      catch (Exception exp)
      {
        writer.Close();
        reader.Close();
        sw.Close();
        sReader.Close();
        return exp.Message;
      }
    }

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

　读取html内容　

同语言下

可能有用的

lybwwp贡献的其它代码(17)