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

How to recursively remove a given list of unwanted html tags from an html string

I took @mathias answer and improved his extension method so that you can supply a list of tags to exclude as a List (e.g. {"a","p","hr"}). I also fixed the logic so that it works recursively properly:

public static string RemoveUnwantedHtmlTags(this string html, List unwantedTags)
    {
        if (String.IsNullOrEmpty(html))
        {
            return html;
        }

        var document = new HtmlDocument();
        document.LoadHtml(html);

        HtmlNodeCollection tryGetNodes = document.DocumentNode.SelectNodes("./*|./text()");

        if (tryGetNodes == null || !tryGetNodes.Any())
        {
            return html;
        }

        var nodes = new Queue(tryGetNodes);

        while (nodes.Count > 0)
        {
            var node = nodes.Dequeue();
            var parentNode = node.ParentNode;

            var childNodes = node.SelectNodes("./*|./text()");

            if (childNodes != null)
            {
                foreach (var child in childNodes)
                {
                    nodes.Enqueue(child);                       
                }
            }

            if (unwantedTags.Any(tag => tag == node.Name))
            {               
                if (childNodes != null)
                {
                    foreach (var child in childNodes)
                    {
                        parentNode.InsertBefore(child, node);
                    }
                }

                parentNode.RemoveChild(node);

            }
        }

        return document.DocumentNode.InnerHtml;
    }