去除HTML标记

最新推荐文章于 2024-06-17 09:46:50 发布

储采珍

最新推荐文章于 2024-06-17 09:46:50 发布

阅读量272

点赞数

分类专栏： Html 文章标签： html string class 脚本

本文链接：https://blog.csdn.net/kong1yi/article/details/5809314

版权

Html 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

using System;
using System.Data;
using System.Configuration;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Web.UI.HtmlControls;
using System.Text.RegularExpressions;

/// <summary>
/// HtmlCode 的摘要说明
/// </summary>
public class HtmlCode
{
public HtmlCode()
{
  //
  // TODO: 在此处添加构造函数逻辑
  //
}

                    ///   <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 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;
                    }
            #region
            ///   移除HTML标签
            ///   </summary>
            ///   <param   name="HTMLStr">HTMLStr</param>
            public static string ParseTags(string HTMLStr)
            {
              return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");
            }

            #endregion

}