How to clean up poorly formed HTML using HTML Agility Pack

Question

I am attempting to replace this god awful collection of regular expressions that is currently used to clean up blocks of poorly formed HTML and stumbled upon the HTML Agility Pa

Answer 1

On HtmlNode, the method RemoveChild has this overload:

public HtmlNode RemoveChild(HtmlNode oldChild, bool keepGrandChildren);

So this is how you would do it:

HtmlDocument doc = new HtmlDocument();
doc.Load("yourfile.htm");

foreach (HtmlNode font in doc.DocumentNode.SelectNodes("//font"))
{
    font.ParentNode.RemoveChild(font, true);
}

EDIT: It looks like the Replace w/ keepGrandChildren option is not working as expected, so here is an alternate implementation:

public static HtmlNode RemoveChild(HtmlNode parent, HtmlNode oldChild, bool keepGrandChildren)
{
    if (oldChild == null)
        throw new ArgumentNullException("oldChild");

    if (oldChild.HasChildNodes && keepGrandChildren)
    {
        HtmlNode prev = oldChild.PreviousSibling;
        List nodes = new List(oldChild.ChildNodes.Cast());
        nodes.Sort(new StreamPositionComparer());
        foreach (HtmlNode grandchild in nodes)
        {
            parent.InsertAfter(grandchild, prev);
        }
    }
    parent.RemoveChild(oldChild);
    return oldChild;
}

// this helper class allows to sort nodes using their position in the file.
private class StreamPositionComparer : IComparer
{
    int IComparer.Compare(HtmlNode x, HtmlNode y)
    {
        return y.StreamPosition.CompareTo(x.StreamPosition);
    }
}