• 如何去掉HTML代码来获取纯文本?


    public string TextNoHTML(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);
        //替换掉 < 和 > 标记
        Htmlstring.Replace("<", "");
        Htmlstring.Replace(">", "");
        Htmlstring.Replace("/r/n", "");
        //返回去掉html标记的字符串
        return Htmlstring;
    }
    

      

  • 相关阅读:
    FFMPEG音视频基础问题和被面试问到的东西
    OpenGL学习
    FFMPEG起航之旅
    SurfaceView、TextureView对比和学习
    对文件拷贝、删除操作、对时间的计算以及转化
    音视频开发
    企业级Android应用架构设计与开发
    屏幕分辨率的适配&&开发文档的介绍
    设计模式的学习
    自定义Dialog的模版
  • 原文地址:https://www.cnblogs.com/dizhi/p/6428928.html
Copyright © 2020-2023  润新知