去除HTML标记 .

 /// 去除HTML标记
        public static string NoHTML(string strHtml)
        {
            strHtml= Regex.Replace(strHtml, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);           

 strHtml= Regex.Replace(strHtml, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"([/r/n])[/s]+", "", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"-->", "", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"<!--.*", "", RegexOptions.IgnoreCase);

            strHtml= Regex.Replace(strHtml, @"&(quot|#34);", "/"", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(iexcl|#161);", "/xa1", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(cent|#162);", "/xa2", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(pound|#163);", "/xa3", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&(copy|#169);", "/xa9", RegexOptions.IgnoreCase);
            strHtml= Regex.Replace(strHtml, @"&#(/d+);", "", RegexOptions.IgnoreCase);

            strHtml.Replace("<", "");
            strHtml.Replace(">", "");
            strHtml.Replace("/r/n", "");
            strHtml= HttpContext.Current.Server.HtmlEncode(strHtml).Trim();

            return strHtml;
        }

 

 

posted @ 2012-12-03 07:48  Damon201611  阅读(166)  评论(0编辑  收藏  举报