首页 > Windows开发 > 详细

C# 清除文本中的HTML标签

时间:2016-01-26 15:05:28      阅读:224      评论:0      收藏:0      [点我收藏+]

/// <summary> 

        /// 清除文本中Html的标签 
        /// </summary> 
        /// <param name="Content"></param> 
        /// <returns></returns> 
        public static string ClearHtml(string Content) 
        { 
            Content = Zxj_ReplaceHtml("&#[^>]*;", "", Content); 
            Content = Zxj_ReplaceHtml("</?marquee[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?object[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?param[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?embed[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?table[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml(" ", "", Content); 
            Content = Zxj_ReplaceHtml("</?tr[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?p[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?a[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?img[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?tbody[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?li[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?span[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?div[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?td[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?script[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("(javascript|jscript|vbscript|vbs):", "", Content); 
            Content = Zxj_ReplaceHtml("on(mouse|exit|error|click|key)", "", Content); 
            Content = Zxj_ReplaceHtml("<\\?xml[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("<\\/?[a-z]+:[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?font[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?b[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?u[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?i[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?strong[^>]*>", "", Content); 
            Content = Zxj_ReplaceHtml("</?strong[^>]*>", "", Content); 
   
            Content = Zxj_ReplaceHtml(" ", "", Content); 
            Regex r = new Regex(@"\s+"); 
            Content = r.Replace(Content, ""); 
   
            Content.Trim(); 
            string clearHtml = Content; 
            return clearHtml; 
        } 
   
        /// <summary> 
        /// 清除文本中的Html标签 
        /// </summary> 
        /// <param name="patrn">要替换的标签正则表达式</param> 
        /// <param name="strRep">替换为的内容</param> 
        /// <param name="content">要替换的内容</param> 
        /// <returns></returns> 
        private static string Zxj_ReplaceHtml(string patrn, string strRep, string content) 
        { 
            if (string.IsNullOrEmpty(content)) 
            { 
                content = ""; 
            } 
            Regex rgEx = new Regex(patrn, RegexOptions.IgnoreCase); 
            string strTxt = rgEx.Replace(content, strRep); 
            return strTxt; 
        }

C# 清除文本中的HTML标签

原文:http://www.cnblogs.com/a-mumu/p/5160393.html

踩
(0)
赞
(0)
   
举报
评论 一句话评论(0)
关于我们 - 联系我们 - 留言反馈 - 联系我们:wmxa8@hotmail.com
© 2014 bubuko.com 版权所有
打开技术之扣,分享程序人生!