c#两种过滤HTML代码

1 篇文章 0 订阅

public string checkStr(string html)
{

        System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" on[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);

        html = regex1.Replace(html, ""); //过滤<script></script>标记

        html = regex2.Replace(html, ""); //过滤href=javascript: (<A>) 属性

        html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on...事件

        html = regex4.Replace(html, ""); //过滤iframe

        html = regex5.Replace(html, ""); //过滤frameset

        html = regex6.Replace(html, ""); //过滤frameset

        html = regex7.Replace(html, ""); //过滤frameset

        html = regex8.Replace(html, ""); //过滤frameset

        html = regex9.Replace(html, "");

        html = html.Replace(" ", "");

        html = html.Replace("</strong>", "");

        html = html.Replace("<strong>", "");

        return html;

    }
    //去除html标签
    public static string NoHTML(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;
    }
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值