Here’s a very simple example of what you could do with it – I’m just extracting inner HTML from any element inside a HTML file which has a css class called “scrape” assigned to it:

using HtmlAgilityPack;

public partial class _Default : System.Web.UI.Page
{
    protected void Page_Load(object sender, EventArgs e)
    {
        HtmlDocument doc = new HtmlDocument();
        doc.Load(Server.MapPath(filePath));
        Parse(doc.DocumentNode);
    }
    private void Parse(HtmlNode n)
    {
        foreach (HtmlAttribute atr in n.Attributes)
        {
            if (atr.Name == "class" && atr.Value == "scrape")
            {
                Response.Write(n.InnerHtml);
            }
        }

        if (n.HasChildNodes)
        {
            foreach (HtmlNode cn in n.ChildNodes)
            {
                Parse(cn);
            }
        }
    }
}

That’s just a very small part of what it could do. I’ll expand upon this and post a few more examples in the future showing some interesting things you could do with this.

protected ArrayList getURL(string txtIn)
{
    ArrayList outURL = new ArrayList();
    Regex r = new Regex("href\\s*=\\s*(?:(?:\\\"(?<url>[^\\\"]*)\\\")|(?<url>[^\\s]* ))");
    MatchCollection mc1 = r.Matches(txtIn);

    foreach (Match m1 in mc1)
    {
        foreach (Group g in m1.Groups)
        {
            outURL.Add(g.Value);
        }
    }

    return outURL;
}

public static string TruncateText(string txtIn, int newLength)
{
    string txtOut = txtIn;
    string pattern = @"<(.|\n)*?>";

    //Strip out HTML tags
    if (Regex.IsMatch(txtIn, pattern, RegexOptions.None))
        txtOut = Regex.Replace(txtIn, pattern, string.Empty, RegexOptions.Multiline).Trim();

    if (txtOut.Length > newLength)
    {
        int endPos = txtOut.LastIndexOf(" ", newLength);
        txtOut = txtOut.Substring(0, endPos) + "...";
    }

    return txtOut;
}