在ASP.NET中过滤HTML字符串总结
内容导读
互联网集市收集整理的这篇技术教程文章主要介绍了在ASP.NET中过滤HTML字符串总结,小编现在分享给大家,供广大互联网技能从业者学习和参考。文章包含3567字,纯文字阅读大概需要6分钟。
内容图文
先记下来,以作备用!
- /// <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;
- }
原文:http://www.cnblogs.com/ranran/p/3878461.html
内容总结
以上是互联网集市为您收集整理的在ASP.NET中过滤HTML字符串总结全部内容,希望文章能够帮你解决在ASP.NET中过滤HTML字符串总结所遇到的程序开发问题。 如果觉得互联网集市技术教程内容还不错,欢迎将互联网集市网站推荐给程序员好友。
内容备注
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 gblab@vip.qq.com 举报,一经查实,本站将立刻删除。
内容手机端
扫描二维码推送至手机访问。