asp.net过滤HTML标签，只保留换行与空格

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› ASP.NET›ASP.NET编程经验

原作者: [db:作者] 来自: [db:来源] 收藏邀请

自己从网上找了一个过滤HTML标签的方法，我也不知道谁的才是原创的，反正很多都一样。我把那方法复制下来，代码如下：

///   <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;
}

以上代码是从网上直接复制过来的，这个确实能过滤掉所有的HTML标签，但是这个不是我想要的，这个过滤得太干净了，我如果用textarea输入框的话，我是要保留空格跟换行的。

然后我就自己改了一下这个方法，textarea的换行是\n，所以我得把这些标签重新匹配替换成<br>，这样的话从数据库中读取到页面时，就能正确的换行了，把空格替换成HTML的空格符，大功告成。

       ///   <summary>
        ///   去除HTML标记(保留br跟\r\n)（此方法由博客园-三卷天书修改成）
        ///   </summary>
        ///   <param   name="NoHTML">包括HTML的源码   </param>
        ///   <returns>已经去除后的文字</returns>
        public static string NewNoHTML(string Htmlstring)
        {
            //Htmlstring.Replace("\\r\\n", "%r%n").Replace("<br>","%br%").Replace("<br/>","%br&%").Replace("\\n","%n");
            //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, @"-->", "", 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);
            Htmlstring = Regex.Replace(Htmlstring, @"((\r\n))", "<br>");
            Htmlstring = Regex.Replace(Htmlstring, @"(\r|\n)", "<br>");
            Htmlstring = Regex.Replace(Htmlstring, @"(\s)", "&nbsp;");
            return Htmlstring;
        }