Use C # to convert HTML text to normal text, removing all HTML tags (go)

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


// First you need to import the namespace
using System.Text.RegularExpressions;


namespace WindowsFormsApplication1
{
   public class Class1
    {
       /// <summary>
       /// Convert html text to text content method NoHTML
       /// </ summary>
       /// <param name = "Htmlstring"> HTML text value </ param>
       /// <returns> </ returns>
        public string NoHTML (string Htmlstring)
        {
            // Delete script
            Htmlstring = Regex.Replace (Htmlstring, @ "<script [^>] *?>. *? </ Script>", "", RegexOptions.IgnoreCase);
            // Delete 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);
            // Replace the <and> tags
            Htmlstring.Replace ("<", "");
            Htmlstring.Replace (">", "");
            Htmlstring.Replace ("/ r / n", "");
            // Return the string with html tags removed
            return Htmlstring;
        }
    }
} 

Simple version:

 
public string NoHtml(string html)
{ string StrNohtml = System.Text.RegularExpressions.Regex.Replace(html, "<[^>]+>", "");
    StrNohtml = System.Text.RegularExpressions.Regex.Replace(StrNohtml, "&[^;]+;", ""); return StrNohtml;
}

Use C # to convert HTML text to normal text, removing all HTML tags (go)