asp.net文本去除<html>标记

先引入

using System.Text.RegularExpressions;

再编写一个方法去除HTML标记

private string NoHTML(string Htmlstring)
    {

        //删除脚本

        Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);

        //删除HTML
        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 = 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.Replace("<", "");

        Htmlstring.Replace(">", "");

        Htmlstring.Replace("\r\n", "");

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

        return Htmlstring;

    }

posted @ 2010-09-16 11:51  西湖小巷  阅读(324)  评论(0)    收藏  举报