去除HTML标记

网站上会遇到文字编辑的功能，人们往往喜欢直接在网页复制粘贴，常常就把html标签 直接代入数据库，或者你编辑文本样式的时候也会产生标签

标签会给你的样式带来美感，但是也会给你到来麻烦，例如在gridview显示标签会错乱。恩 ，所以呢，我们需要这样的一个通道。

        /// <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  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", "");

            Regex regex1 = new Regex(@"<[^>]*>", RegexOptions.IgnoreCase);
            Htmlstring = regex1.Replace(Htmlstring, "").Replace("&nbsp;", " ");

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

 

            return Htmlstring;

        }

转载于:https://www.cnblogs.com/chenly-index/archive/2012/06/06/2537685.html