使用C#将HTML文本转换为普通文本,去掉所有的Html标记(转)

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


//首先需要导入命名空间
using System.Text.RegularExpressions;


namespace WindowsFormsApplication1
{
   public class Class1
    {
       /// <summary>
       /// 将html文本转化为 文本内容方法NoHTML
       /// </summary>
       /// <param name="Htmlstring">HTML文本值</param>
       /// <returns></returns>
        public 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);
            //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;
        }
    }
}

简单版本:

public string NoHtml(string html)
{
    string StrNohtml = System.Text.RegularExpressions.Regex.Replace(html, "<[^>]+>", "");
    StrNohtml = System.Text.RegularExpressions.Regex.Replace(StrNohtml, "&[^;]+;", "");
    return StrNohtml;
}
原文地址:https://www.cnblogs.com/coolsundy/p/4821361.html