C#解析单层html的中的文本,然后拼接起来

匹配单层html的小demo,应该能匹配大多数html字符串.多层(嵌套)html标签解析不出来.可能有小bug,我抛砖引玉下,哈哈.

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Text.RegularExpressions;
using System.Threading.Tasks;

namespace ResolveHtmlText
{
    class Program
    {
        static void Main(string[] args)
        {
            string text = @"&nbsp;<span style='color:#1F497D'><span>y<span></span>&nbsp; &nbsp;<span style='color:#1F497D;'>1</span>&nbsp;<span style='color:#1F497D;background-color:#123456'>2</span><span style='color:#1F497D;background-color:#123456;text-align:center'>3</span>  <span style='color:#1F497D;background-color:#123456;text-align:center;'>4</span> <span style='color:#1F497D;background-color:#123456;text-align:center;tt-l: 134;'>5</span>ggjf<a>123456</a>";
            Console.WriteLine("原字符串:" + text);
            text = text.Replace("\"", "'");
            text = text.Replace("&quot;", "'");
            text = text.Replace("&nbsp;", "");
            text = text.Replace("&lt;", "<");//将<的转义码&lt;都替换成<
            text = text.Replace("&gt;", ">");//将>的转义码&gt;都替换成>

            //string matchStr = @"<\s*[a-zA-Z0-9]+\s*>[^<^>]*<\s*/\s*[a-zA-Z0-9]+\s*>";
            string matchStr = @"<\s*[a-zA-Z0-9]+\s*[a-zA-Z]+\s*=\s*'\s*[a-zA-Z]"
                            + @"+\s*:\s*[^<^>];?'\s*>[^<^>]"
                            + @"*<\s*/\s*[a-zA-Z0-9]+\s*>|<\s*[a-zA-Z0-9]"
                            + @"+\s*(\s*[a-zA-Z-]+\s*=\s*'(\s*[a-zA-Z-]+\s*:"
                            + @"\s*[^:^;^<^>]+\s*;\s*)*(\s*[a-zA-Z-]+\s*:\s*"
                            + @"[^:^;^<^>]+\s*)\s*;?\s*'\s*)*"
                            + @"\s*>[^<^>]*<\s*/\s*[a-zA-Z0-9]+\s*>";

            Regex htmlReg = new Regex(matchStr);
            string result = null;
            MatchCollection htmlMatchCollection = htmlReg.Matches(text);
            StringBuilder sb = new StringBuilder();
            
            foreach (Match m in htmlMatchCollection) 
            {
                if (m != null && m.Groups != null && m.Groups.Count > 0)
                {
                    string temp = m.Groups[0].Value;
                    Console.WriteLine("临时值:" + temp);
                    //Regex textReg1 = new Regex(@"[^<^>]+");
                    //Match textMatch1 = textReg1.Match(temp);
                    //if (textMatch1 != null && textMatch1.Groups != null && textMatch1.Groups.Count > 0)
                    //{
                    //    result = textMatch1.Groups[0].Value;
                    //    sb.Append(result);
                    //}
                    Regex textReg = new Regex(@">.+<");
                    Match textMatch = textReg.Match(temp);
                    if (textMatch != null && textMatch.Groups != null && textMatch.Groups.Count > 0)
                    {
                        result = textMatch.Groups[0].Value;
                        if (result.Length > 2)
                        {
                            result = result.Substring(1, result.Length - 2);
                            sb.Append(result);
                        }
                    }                   
                }
            }

            

            Console.WriteLine("解析出的结果:" + sb.ToString());
            Console.ReadLine();
        }
    }
}