zoukankan      html  css  js  c++  java
  • asp.net 字符串过滤

    /// <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, @"([ ])[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(" ", "");
    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;
    }

    编程不是为了生存,更多的是乐趣和成就感~
  • 相关阅读:
    [Debug] Make python2.7 use the right version of opencv
    路线图 | 学习OpenCV路线图
    学习笔记 | Princeton
    书单 | 2017年阅读书单
    路线图 | 摄影师成长路线
    学习笔记 | Morvan
    如何在pycharm中进入shell脚本调试代码
    python3运行报错:TypeError: Object of type 'type' is not JSON serializable解决方法(详细)
    动态规划的引入 P1616 疯狂的采药【完全背包】
    动态规划的引入 P1048 采药【01背包】
  • 原文地址:https://www.cnblogs.com/dckhello/p/5536931.html
Copyright © 2011-2022 走看看