C#将内容附带的html标签去掉转成纯文本方法

  public string xxHTML(string html)
    {

        html = html.Replace("(<style)+[^<>]*>[^\0]*(</style>)+", "");
        html = html.Replace(@"\<img[^\>] \>", "");
        html = html.Replace(@"<p>", "");
        html = html.Replace(@"</p>", "");


        System.Text.RegularExpressions.Regex regex0 =
        new System.Text.RegularExpressions.Regex("(<style)+[^<>]*>[^\0]*(</style>)+", System.Text.RegularExpressions.RegexOptions.Multiline);
        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 = regex0.Replace(html, ""); //过滤href=javascript: (<A>) 属性 


        //html = regex10.Replace(html, "");
        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>", "");
        html = html.Replace(" ", "");
        return html;
    }

阅读更多
文章标签: html标签过滤 C#
个人分类: C#
想对作者说点什么? 我来说一句

没有更多推荐了,返回首页

加入CSDN,享受更精准的内容推荐,与500万程序员共同成长!
关闭
关闭