C# 移除富文本多余标签
t-jian 时间:2022-05-06
/// <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, " ", ""); 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, " ", ""); txt = Regex.Replace(txt, "<p></p>", ""); txt = Regex.Replace(txt, "figure", "p"); return txt; }
特别声明:本站部分内容收集于互联网是出于更直观传递信息的目的。该内容版权归原作者所有,并不代表本站赞同其观点和对其真实性负责。如该内容涉及任何第三方合法权利,请及时与824310991@qq.com联系,我们会及时反馈并处理完毕。