C#去除HTML标记

标签: net
49人阅读 评论(0) 收藏 举报
分类:

1、

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text.RegularExpressions;
using System.Web;
using System.Web.UI;
using System.Web.UI.WebControls;

namespace WebApplication2
{
    public partial class WebForm1 : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {

        }

        ZKWebForm1219_20171128Entities db = new ZKWebForm1219_20171128Entities();
        protected void Button1_Click(object sender, EventArgs e)
        {
            var htmlstring = "<html xmlns='http://www.w3.org/1999/xhtml'><head runat='server'><meta http-equiv='Content-Type' content='text/html; charset=utf-8'/><title></title>  </head><body><form id='form1' runat='server'><div><asp:Button ID='Button1' runat='server' Text='Button'  /></div><div>武汉</div> </form><script src='Scripts/jquery-1.10.2.min.js'></script></body></html>";

            htmlstring = Extenions.RemoveHTML(htmlstring);
            Response.Write(htmlstring);      
        }
    }

    public static class Extenions
    {
        ///   <summary>   
        ///   去除HTML标记   
        ///   </summary>   
        ///   <param   name="NoHTML">包括HTML的源码   </param>   
        ///   <returns>已经去除后的文字</returns>   
        public static string RemoveHTML(this 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;
        }

    }
}


查看评论

asp.net去除html标记

  • 2008年12月12日 15:34
  • 3KB
  • 下载

C#中除去所有在HTML元素中标记

/// 除去所有在HTML元素中标记  public static string StripHTML(string strHtml)  {   string strOutput=strHtml;   ...
  • JOHNCOOLS
  • JOHNCOOLS
  • 2006-05-01 13:36:00
  • 1300

使用C#将HTML文本转换为普通文本,去掉所有的Html标记

using System; using System.Collections.Generic; using System.Linq; using System.Text; //首先需要...
  • Denghejing
  • Denghejing
  • 2014-12-25 18:29:58
  • 6743

.NET(C#)用正则表达式清除HTML标签(包括script和style),保留纯本文

如今是互联网时代,随时随刻都在接触网页数据。那么对于.NET的开发人员来说,处理网页源码就是有时候就不能避免了。今天给大家分享.NET用正则表达式清除HTML标签的通用方法。使其保留网页源码中的纯文本...
  • my98800
  • my98800
  • 2016-10-25 08:36:51
  • 2212

C# 正则表达式,去除所有HTML标签

protected string str = "sdasasdsddsdsaaassss 说是道 ";     protected void Page_Load(object sender, E...
  • liwateryi
  • liwateryi
  • 2015-03-01 16:58:58
  • 1732

去除文字里的html标签的C#方法

/// /// 清除文本中Html的标签 /// /// /// protected string ClearH...
  • hougelou
  • hougelou
  • 2012-08-23 18:07:11
  • 8321

PHP去掉特定html标签的正则表达式

$html="font";      $str="123456789789";      @$reg='#\#i';      echo $str;      echo "";      e...
  • ZHIMING_huang
  • ZHIMING_huang
  • 2018-01-02 23:20:28
  • 50

.net中去除HTML标记的类

  • 2009年02月12日 13:31
  • 2KB
  • 下载

C#去掉HTML标记

(1)方法一   public string RemoveHTMLTags(string htmlStream)         {             if (htmlStream =...
  • my98800
  • my98800
  • 2016-05-18 09:40:38
  • 165

C#去除所有HTML标记

C#去除所有HTML标记 ! 联合正则表达式发出的强大魅力!!
  • Hndy173
  • Hndy173
  • 2010-11-15 11:34:00
  • 689
    个人资料
    持之以恒
    等级:
    访问量: 4万+
    积分: 2199
    排名: 2万+
    最新评论