Program.cs


using Html_Serializer;
using System.Linq;
using System.Text.RegularExpressions;

var html = await Load("https://malkabruk.co.il/practicode");
string clean = Regex.Replace(html, @"\s+", " ");
clean = Regex.Replace(clean, @"\s*(<[^>]+>)\s*", "$1");

//var cleanhtml = new Regex("\\s").Replace(html, "");
var htmllines = Regex.Matches(clean, "<.*?>|[^<]+")
                     .Cast<Match>()
                     .Select(m => m.Value.Trim())
                     .Where(s => s.Length > 0);

htmlElement rootElement = new htmlElement();
htmlElement currentElement = new htmlElement();
currentElement = rootElement;
//string root = htmllines.First().ToString();
var arttibutes = new Regex("([^\\s]*?)=\"(.*?)\"").Matches(htmllines.First());
string pattern = @"<\s*(\w+)";
Match match = Regex.Match(" innnnn", pattern);

foreach (var htmlElement in htmllines)
{

    if (htmlElement.Substring(1, htmlElement.Length - 1) == "/html")
        break;
    if (htmlElement.IndexOf('/') == 1)
    {
        currentElement = currentElement.parent;
        continue;
    }
     match = Regex.Match(htmlElement, pattern);
    if (match.Success)
    {
        if (HtmlHelper._instance.HtmlTags.Contains(match.Groups[1].Value) ||
            HtmlHelper._instance.HtmlVoidTags.Contains(match.Groups[1].Value))
        {
            var child = new htmlElement();
            child.Name = match.Groups[1].Value;
            child.parent = currentElement;
            arttibutes = new Regex("([^\\s]*?)=\"(.*?)\"").Matches(htmlElement);
            foreach (Match r in arttibutes)
            {
                string attrName = r.Groups[1].Value;
                string attrValue = r.Groups[2].Value;
                if (attrName == "id")
                    child.Id = attrValue;
                if (attrName == "class")
                    child.Classes = attrValue.Split(' ');
                else 
                    child.Attributes.Add(attrName + "=" + attrValue);
            }
            currentElement.children.Add(child);
            if (!(htmlElement.IndexOf('/') == htmlElement.Length - 2 ||
                HtmlHelper._instance.HtmlVoidTags.Contains(child.Name)))
                currentElement = child;
        }
    }
}

static bool IsMatch(Selector selector,  htmlElement root)
{
    if (selector.TagName.Length > 0 && selector.TagName != root.Name)
        return false;

    if (selector.Id.Length > 0 && selector.Id != root.Id)
        return false;

    if (selector.Classes.Count > 0 && !(selector.Classes.All(root.Classes.Contains)))
        return false;
    return true;

}
static void MatchesSelector(Selector selector, htmlElement root, HashSet<htmlElement> matches)
{
    if (selector == null)
        return;
    List<htmlElement> matchesList = new List<htmlElement>();
    var desElements = root.Descendants();
    foreach (htmlElement c in desElements)
    {
        if (IsMatch(selector, c))
            matchesList.Add(c);
    }
    foreach (htmlElement el in matchesList)
    {
        if (selector.Child == null)
            matches.Add(el);
        else
        {
            var desElements2 = el.Descendants();
            foreach (htmlElement child in desElements2)
                MatchesSelector(selector.Child, child, matches);
        }
    }
}

async Task<string> Load(string url)
{
    HttpClient client = new HttpClient();
    var response = await client.GetAsync(url);
    var html = await response.Content.ReadAsStringAsync();
    return html;
}