• 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:
    数据持久化的基础知识
    svn常用命令
    关于SVN 目录结构
    linux查看CPU信息
    一个服务器上启动两台tomcat
    centos6.0 配置SVN
    mysql插入表情
    MAC 安装 PIL
    安装freetype
    Hadoop基本文件命令
  • 原文地址:https://www.cnblogs.com/dizhi/p/6428928.html
Copyright © 2020-2023  润新知