C#中如何去除HTML标记

/// <summary>
  /// 去除HTML标记
  /// </summary>
  /// <param name="Htmlstring">包括HTML的源码 </param>
  /// <returns>已经去除后的文字</returns>
  public string NoHTML(string Htmlstring)
  {
   //删除脚本
   Htmlstring = Htmlstring.Replace("\r\n","");
   Htmlstring = Regex.Replace(Htmlstring,@"<script.*?</script>","",RegexOptions.IgnoreCase);
   Htmlstring = Regex.Replace(Htmlstring,@"<style.*?</style>","",RegexOptions.IgnoreCase);
   Htmlstring = Regex.Replace(Htmlstring,@"<.*?>","",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 = Htmlstring.Replace("<","");
   Htmlstring = Htmlstring.Replace(">","");
   Htmlstring = Htmlstring.Replace("\r\n","");   
   Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
   return Htmlstring;
  }

posted @ 2010-12-21 08:55  黑夜以后  阅读(2272)  评论(0编辑  收藏  举报