Asp.net：清空一段文字内的所有html标签

最新推荐文章于 2021-06-20 21:14:51 发布

原创最新推荐文章于 2021-06-20 21:14:51 发布 · 1.7k 阅读

1 ·

CC 4.0 BY-SA版权

Asp.net 专栏收录该内容

41 篇文章

订阅专栏

本文介绍了一个用于清除HTML标签的C#类库，通过正则表达式匹配并移除HTML标签，确保文本内容的纯净。提供了详细的代码实现及使用示例。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

优快云广告是越来越多了，所有博客笔记不再更新，新网址 DotNet笔记

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

/// <summary>
/// ClearHTML 的摘要说明
/// </summary>
public class ClearHTML
{
    public ClearHTML()
    {

    }
    /// <summary>
    /// 清除文本中Html的标签
    /// </summary>
    /// <param name="Content"></param>
    /// <returns></returns>
    public string Clear(string Content)
    {
        Content = Zxj_ReplaceHtml("&#[^>]*;", "", Content);
        Content = Zxj_ReplaceHtml("</?marquee[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?object[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?param[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?embed[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?table[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml(" ", "", Content);
        Content = Zxj_ReplaceHtml("</?tr[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?p[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?a[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?img[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?tbody[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?li[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?span[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?div[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?td[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?script[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("(javascript|jscript|vbscript|vbs):", "", Content);
        Content = Zxj_ReplaceHtml("on(mouse|exit|error|click|key)", "", Content);
        Content = Zxj_ReplaceHtml("<\\?xml[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("<\\/?[a-z]+:[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?font[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?b[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?u[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?i[^>]*>", "", Content);
        Content = Zxj_ReplaceHtml("</?strong[^>]*>", "", Content);
        string clearHtml = Content;
        return clearHtml;
    }

    /// <summary>
    /// 清除文本中的Html标签
    /// </summary>
    /// <param name="patrn">要替换的标签正则表达式</param>
    /// <param name="strRep">替换为的内容</param>
    /// <param name="content">要替换的内容</param>
    /// <returns></returns>
    private string Zxj_ReplaceHtml(string patrn, string strRep, string content)
    {
        if (string.IsNullOrEmpty(content))
        {
            content = "";
        }
        Regex rgEx = new Regex(patrn, RegexOptions.IgnoreCase);
        string strTxt = rgEx.Replace(content, strRep);
        return strTxt;
    }
}

调用方式：

            string str = "<a href='www.baidu.com'>这里空气清新，大神指日可待！</a><b>你好a酸大苏打 ，</b><span>这是我的清楚标签的示例，<b>请你测试一下，我试验过，正确的啊！</b></span>";
            ClearHTML c = new ClearHTML();
            str = c.Clear(str);