利用正则表达式过滤掉HTML字符及自己指定的字符

using System;

using System.Collections.Generic;

using System.Linq;

using System.Text;

using System.Text.RegularExpressions;

using System.Web;

 

namespace Utility

{

    public class StringUtil

    {

        /// <summary>

        /// 过滤掉HTML标签

        /// </summary>

        /// <param name="Htmlstring"></param>

        /// <returns></returns>

        public static string NoHTML(string Htmlstring)

        {

            //正则表达式&.*?; 可以去掉所有的“&开头;结尾的”

            //正则表达式 <.*?> 可以去掉所有 <> </>之类的

            //正则表达式 >(.*)</li> 获取<li>和</li>之间的内容

            //正则表达式 <[^>]*> 获取网页文本内容

 

            //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.Replace("|", "");

            Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

            return Htmlstring;

 

        }

    }

}