ASP.NET過濾HTML字串方法總結

本文執行個體講述了ASP.NET過濾HTML字串的方法，供大家參考使用，具體代碼如下：

///  <summary>去除HTML標記 ///     ///  </summary>   ///  <param name="Htmlstring">包括HTML的源碼</param>   ///  <returns>已經去除後的文字</returns>   public static string GetNoHTMLString(string Htmlstring) {   //刪除指令碼     Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);   //刪除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; }  /// <summary>擷取顯示的字串，可顯示HTML標籤，但把危險的HTML標籤過濾，如iframe,script等。 ///  /// </summary> /// <param name="str">未處理的字串</param> /// <returns></returns> public static string GetSafeHTMLString(string str) {   str = Regex.Replace(str, @"<applet[^>]*?>.*?</applet>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<body[^>]*?>.*?</body>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<embed[^>]*?>.*?</embed>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<frame[^>]*?>.*?</frame>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<frameset[^>]*?>.*?</frameset>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<html[^>]*?>.*?</html>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<iframe[^>]*?>.*?</iframe>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<style[^>]*?>.*?</style>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<layer[^>]*?>.*?</layer>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<link[^>]*?>.*?</link>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<ilayer[^>]*?>.*?</ilayer>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<meta[^>]*?>.*?</meta>", "", RegexOptions.IgnoreCase);   str = Regex.Replace(str, @"<object[^>]*?>.*?</object>", "", RegexOptions.IgnoreCase);   return str; }