去除html标记和替换script标记

   1:   /// <summary>

   2:          /// 去除HTML标记

   3:          /// </summary>

   4:          /// <param name="NoHTML">包括HTML的源码 </param>

   5:          /// <returns>已经去除后的文字</returns>

   6:          public static string RemoveHTML(string Htmlstring)

   7:          {

   8:              if (string.IsNullOrEmpty(Htmlstring))

   9:              {

  10:                  return string.Empty;

  11:              }

  12:              //删除脚本

  13:              Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);

  14:   

  15:              //删除HTML

  16:              Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);

  17:              Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase);

  18:              Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);

  19:              Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);

  20:              Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase);

  21:              Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);

  22:              Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);

  23:              Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);

  24:              Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);

  25:              Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);

  26:              Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);

  27:              Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);

  28:              Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);

  29:              Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "", RegexOptions.IgnoreCase);

  30:              Htmlstring.Replace("<", "");

  31:              Htmlstring.Replace(">", "");

  32:              Htmlstring.Replace("\r\n", "");

  33:   

  34:              return Htmlstring;

  35:          }

  36:   

  37:   

  38:          #region 正则表达式替换包含script脚本攻击的script代码

  39:          /// <summary>

  40:          /// 正则表达式替换包含script脚本攻击的script代码

  41:          /// author:Andrew.He

  42:          /// </summary>

  43:          /// <param name="scriptString">包含脚本攻击的字符串</param>

  44:          /// <returns>替换脚本攻击的字符串</returns>

  45:          public static string RemoveScript(string scriptString)

  46:          {

  47:              if (string.IsNullOrEmpty(scriptString))

  48:              {

  49:                  return scriptString;

  50:              }

  51:   

  52:              //执行替换操作

  53:              scriptString = Regex.Replace(scriptString, @"<[ ]*script", "[script ", RegexOptions.IgnoreCase);

  54:              scriptString = Regex.Replace(scriptString, @"/[ ]*script[ ]*>", " /script]", RegexOptions.IgnoreCase);

  55:   

  56:              return scriptString;

  57:          }

  58:          #endregion