HTML agility pack - removing unwanted tags without removing content?

Question

I\'ve seen a few related questions out here, but they don’t exactly talk about the same problem I am facing.

I want to use the HTML Agility Pack to remove unwa

Answer 1

Try the following, you might find it a bit neater than the other proposed solutions:

public static int RemoveNodesButKeepChildren(this HtmlNode rootNode, string xPath)
{
    HtmlNodeCollection nodes = rootNode.SelectNodes(xPath);
    if (nodes == null)
        return 0;
    foreach (HtmlNode node in nodes)
        node.RemoveButKeepChildren();
    return nodes.Count;
}

public static void RemoveButKeepChildren(this HtmlNode node)
{
    foreach (HtmlNode child in node.ChildNodes)
        node.ParentNode.InsertBefore(child, node);
    node.Remove();
}

public static bool TestYourSpecificExample()
{
    string html = "
my paragraph 
and my div
 are italic and bold
";
    HtmlDocument document = new HtmlDocument();
    document.LoadHtml(html);
    document.DocumentNode.RemoveNodesButKeepChildren("//div");
    document.DocumentNode.RemoveNodesButKeepChildren("//p");
    return document.DocumentNode.InnerHtml == "my paragraph and my div are italic and bold";
}