这期内容当中小编将会给大家带来有关利用ASP.NET怎么对HTML字符串进行过滤,文章内容丰富且以专业的角度为大家分析和叙述,阅读完这篇文章希望大家可以有所收获。
具体代码如下:
/// <summary>去除HTML标记 /// /// </summary> /// <param name="Htmlstring">包括HTML的源码</param> /// <returns>已经去除后的文字</returns> public static string GetNoHTMLString(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", ""); Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim(); return Htmlstring; } /// <summary>获取显示的字符串,可显示HTML标签,但把危险的HTML标签过滤,如iframe,script等。 /// /// </summary> /// <param name="str">未处理的字符串</param> /// <returns></returns> public static string GetSafeHTMLString(string str) { str = Regex.Replace(str, @"<applet[^>]*?>.*?</applet>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<body[^>]*?>.*?</body>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<embed[^>]*?>.*?</embed>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<frame[^>]*?>.*?</frame>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<frameset[^>]*?>.*?</frameset>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<html[^>]*?>.*?</html>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<iframe[^>]*?>.*?</iframe>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<style[^>]*?>.*?</style>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<layer[^>]*?>.*?</layer>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<link[^>]*?>.*?</link>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<ilayer[^>]*?>.*?</ilayer>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<meta[^>]*?>.*?</meta>", "", RegexOptions.IgnoreCase); str = Regex.Replace(str, @"<object[^>]*?>.*?</object>", "", RegexOptions.IgnoreCase); return str; }
上述就是小编为大家分享的利用ASP.NET怎么对HTML字符串进行过滤了,如果刚好有类似的疑惑,不妨参照上述分析进行理解。如果想知道更多相关知识,欢迎关注亿速云行业资讯频道。
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。