去除HTML标记

来源：互联网发布：淘宝客服能学到什么编辑：程序博客网时间：2024/04/28 00:11

/// 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;
}