清除Html标记的一个封装函数_函数封装去除html标签方法-优快云博客

本文介绍了一种清除HTML标签及特殊字符的方法，并提供了一个具体的C#实现案例。该方法使用正则表达式来移除HTML标签，确保文本的纯净度。

后台.cs文件代码

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

/// <summary>
///AboutClearHtml 的摘要说明
/// </summary>
public class AboutClearHtml
{
public AboutClearHtml()
{
  //
  //TODO: 在此处添加构造函数逻辑
  //
}
    #region 清除HTML函数
    /// <summary>
    /// 清除HTML标记函数
    /// </summary>
    /// <param name="Htmlstring">带Html标记的字符串</param>
    /// <returns>不带Html的字符串</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;

}
#endregion

}

网页中引用：

<%#AboutClearHtml.NoHTML(Eval("DataContent").ToString()).ToString().Length >80?AboutClearHtml.NoHTML(Eval("DataContent").ToString()).ToString().Substring (0,80)+"......": AboutClearHtml.NoHTML(Eval("DataContent").ToString())%>

</a>