asp.net过滤HTML标签的几个函数

以下是引用片段：
　　-----
/**/
///   <summary>
///   去除HTML标记
///   </summary>
///   <param   name="NoHTML">包括HTML的源码   </param>
///   <returns>已经去除后的文字</returns>
public static string NoHTML(string Htmlstring)
{
  //删除脚本
  Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "",
    RegexOptions.IgnoreCase);
  //删除HTML
  Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", "   ",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9",
    RegexOptions.IgnoreCase);
  Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "",
    RegexOptions.IgnoreCase);

  Htmlstring.Replace("<", "");
  Htmlstring.Replace(">", "");
  Htmlstring.Replace("\r\n", "");
  Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

  return Htmlstring;
}

/**/ ///提取HTML代码中文字的C#函数
///   <summary>
///   去除HTML标记
///   </summary>
///   <param   name="strHtml">包括HTML的源码   </param>
///   <returns>已经去除后的文字</returns>
using System;
using System.Text.RegularExpressions;
public class StripHTMLTest
{
  public static void Main()
  {
    string s = StripHTML(
      "<HTML><HEAD><TITLE>中国石龙信息平台</TITLE></HEAD><BODY>faddfs龙信息平台</BODY></HTML>");
    Console.WriteLine(s);
  }

  public static string StripHTML(string strHtml)
  {
    string[]aryReg =
    {
      @"<script[^>]*?>.*?</script>",

      @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\["
        "'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", @"([\r\n])[\s]+", @
        "&(quot|#34);", @"&(amp|#38);", @"&(lt|#60);", @"&(gt|#62);", @
        "&(nbsp|#160);", @"&(iexcl|#161);", @"&(cent|#162);", @"&(pound|#163);",
        @"&(copy|#169);", @"&#(\d+);", @"-->", @"<!--.*\n"
    };

    string[]aryRep =
    {
      "", "", "", "\"", "&", "<", ">", "   ", "\xa1",  //chr(161),
      "\xa2",  //chr(162),
      "\xa3",  //chr(163),
      "\xa9",  //chr(169),
      "", "\r\n", ""
    };

    string newReg = aryReg[0];
    string strOutput = strHtml;
    for (int i = 0; i < aryReg.Length; i++)
    {
      Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
      strOutput = regex.Replace(strOutput, aryRep[i]);
    }
    strOutput.Replace("<", "");
    strOutput.Replace(">", "");
    strOutput.Replace("\r\n", "");
    return strOutput;
  }
}

写一个静态方法移除HTML标签
#region
///移除HTML标签
 /**/ ///   <summary>
///   移除HTML标签
///   </summary>
///   <param   name="HTMLStr">HTMLStr</param>
public static string ParseTags(string HTMLStr)
{
  return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");
}

#endregion
   
///   取出文本中的图片地址
#region
///   取出文本中的图片地址
 /**/ ///   <summary>
///   取出文本中的图片地址
///   </summary>
///   <param   name="HTMLStr">HTMLStr</param>
public static string GetImgUrl(string HTMLStr)
{
  string str = string.Empty;
  string sPattern = @"^<img\s+[^>]*>";
  Regex r = new Regex(@"<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>",
    RegexOptions.Compiled);
  Match m = r.Match(HTMLStr.ToLower());
  if (m.Success)
    str = m.Result("${url}");
  return str;
}

#endregion


本文来源：IT传媒网
原文链接：http://www.cniter.com/tech/asp.net/csharp/remove_html_tag_10806_1.html

以下是引用片段：　　-----/**//// <summary>/// 去除HTML标记/// </summary>/// <param name="NoHTML">包括HTML的源码 </param>/// <returns>已经去除后的文字</returns>public static string NoHTML(string Htmlstring){ //删除脚本 Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase); //删除HTML Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"", @"<!--.*\n" };
string[]aryRep = { "", "", "", "\"", "&", "<", ">", " ", "\xa1", //chr(161), "\xa2", //chr(162), "\xa3", //chr(163), "\xa9", //chr(169), "", "\r\n", "" };
string newReg = aryReg[0]; string strOutput = strHtml; for (int i = 0; i < aryReg.Length; i++) { Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase); strOutput = regex.Replace(strOutput, aryRep[i]); } strOutput.Replace("<", ""); strOutput.Replace(">", ""); strOutput.Replace("\r\n", ""); return strOutput; }}
写一个静态方法移除HTML标签#region///移除HTML标签 /**/ /// <summary>/// 移除HTML标签/// </summary>/// <param name="HTMLStr">HTMLStr</param>public static string ParseTags(string HTMLStr){ return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");}
#endregion /// 取出文本中的图片地址#region/// 取出文本中的图片地址 /**/ /// <summary>/// 取出文本中的图片地址/// </summary>/// <param name="HTMLStr">HTMLStr</param>public static string GetImgUrl(string HTMLStr){ string str = string.Empty; string sPattern = @"^<img\s+[^>]*>"; Regex r = new Regex(@"<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>", RegexOptions.Compiled); Match m = r.Match(HTMLStr.ToLower()); if (m.Success) str = m.Result("${url}"); return str;}
#endregion

本文来源：IT传媒网原文链接：http://www.cniter.com/tech/asp.net/csharp/remove_html_tag_10806_1.html

posted @ 2016-08-24 11:38 银河系上的地球阅读(1385) 评论(0) 编辑收藏举报

刷新页面返回顶部

银河系

asp.net过滤HTML标签的几个函数

公告