[JavaScript知识库] C# 移除富文本多余标签

开发: C++知识库 Java知识库 JavaScript Python PHP知识库人工智能区块链大数据移动开发嵌入式开发工具数据结构与算法开发测试游戏开发网络协议系统运维
教程: HTML教程 CSS教程 JavaScript教程 Go语言教程 JQuery教程 VUE教程 VUE3教程 Bootstrap教程 SQL数据库教程 C语言教程 C++教程 Java教程 Python教程 Python3教程 C#教程
数码: 电脑笔记本显卡显示器固态硬盘硬盘耳机手机 iphone vivo oppo 小米华为单反装机图拉丁

-> JavaScript知识库 -> C# 移除富文本多余标签 -> 正文阅读

[JavaScript知识库]C# 移除富文本多余标签

/// <summary>
        /// 移除富文本所有标签
        /// </summary>
        /// <param name="txt"></param>
        /// <returns></returns>
        public static string ReplaceAllTag(this string txt)
        {
            txt = Regex.Replace(txt, "<style[^>]*?>[\\s\\S]*?<\\/style>", "");//删除css
            txt = Regex.Replace(txt, "<script[^>]*?>[\\s\\S]*?<\\/script>", "");//删除js
            txt = Regex.Replace(txt, "<[^>]+>", "");//删除html标记
            txt = Regex.Replace(txt, "\\s*|\t|\r|\n", "");//去除tab、空格、空行
            txt = Regex.Replace(txt, "&nbsp;", "");
            txt = txt.Replace(" ", "");
            txt = txt.Replace("\"", "");//去除异常的引号" " "
            txt = txt.Replace("\"", "");
            return txt;
        }
        /// <summary>
        /// 移除富文本多余的属性
        /// </summary>
        /// <param name="txt"></param>
        /// <returns></returns>
        public static string ReplaceContent(this string txt)
        {
            txt = Regex.Replace(txt, "<source.*?>", "");
            txt = Regex.Replace(txt, "<video.*?>", "");
            txt = Regex.Replace(txt, "</video>", "");
            txt = Regex.Replace(txt, "class[^=]*=[\"']*[^\"'>]+[\"']*", "");
            txt = Regex.Replace(txt, "style[^=]*=[\"']*[^\"'>]+[\"']*", "");
            txt = Regex.Replace(txt, "width[^=]*=[\"']*[^\"'>]+[\"']*", "");
            txt = Regex.Replace(txt, "height[^=]*=[\"']*[^\"'>]+[\"']*", "");
            txt = Regex.Replace(txt, "href[^=]*=[\"']*[^\"'>]+[\"']*", "");//去除a标签 href
            txt = Regex.Replace(txt, "<style[^>]*?>[\\s\\S]*?<\\/style>", "");//去除style
            txt = Regex.Replace(txt, "<script[^>]*?>[\\s\\S]*?<\\/script>", "");//去除script
            txt = Regex.Replace(txt, "&nbsp;", "");
            txt = Regex.Replace(txt, "<p></p>", "");
            txt = Regex.Replace(txt, "figure", "p");
            return txt;
        }