Converting specific HTML structure to specific XML structure

Question

I have been struggling with this for quite some time now.

I want to convert the html to xml. The structures is shown below.

I am using "HtmlAgilityPack" to convert the html to valid xml structure. So, after this, my HTML looks like this:

<div class="menuItem1" video="" preview="">
    Menu 1
    <div class="subMenu1">
        <div class="menuItem2" video="" preview="">
            Menu 2
            <div class="subMenu2">
                <div class="menuItem3" video="" preview="">
                    Menu 3
                    <div class="subMenu3">
                        <div class="" video="" preview="">Menu 4</div>
                    </div>
                    <div class="treeExpand"></div>
                </div>
                <div class="menuItem3" video="" preview="">Menu 3</div>
                <div class="menuItem3" video="" preview="">Menu 3</div>
            </div>
            <div class="treeExpand"></div>
        </div>
    </div>
    <div class="treeExpand"></div>
</div>
<div class="menuItem1" video="" preview="">
    Menu 1
    <div class="subMenu1">
        <div class="menuItem2" video="" preview="">
            Menu 2
            <div class="subMenu2">
                <div class="menuItem3" video="" preview="">
                    Menu 3
                    <div class="subMenu3">
                        <div class="" video="" preview="">Menu 4</div>
                    </div>
                    <div class="treeExpand"></div>
                </div>
                <div class="menuItem3" video="" preview="">Menu 3</div>
                <div class="menuItem3" video="" preview="">Menu 3</div>
            </div>
            <div class="treeExpand"></div>
        </div>
    </div>
    <div class="treeExpand"></div>
</div>

Which is exactly what I want. Now I can get this into an XElement, using this C# code:

XDocument doc = XDocument.Parse(THE_HTML_STRING_AS_SHOWN_ABOVE);
XDocument docw = new XDocument(new XElement("Navigation", doc.Root));
XElement root = docw.Root;

I created a method, which I can pass the root into:

GenerateXmlFromHtml(root);

The code for this method:

private string GenerateXmlFromHtml(XElement elem)
{
    StringBuilder sbNavigationXml = new StringBuilder();
    try
    {
        //HTML will always have a video and preview, according to the generation of the html structure.

        string text = string.Empty;
        string videopath = string.Empty;
        string previewpath = string.Empty;
        XText textNode;

        foreach (XElement element in elem.Elements())
        {
            element.Name = "MenuItem"; //Change element name.

            string htmlClass;
            try { htmlClass = element.Attribute("class").Value; }
            catch { htmlClass = ""; }

            if (!string.IsNullOrEmpty(htmlClass))
            {
                if (htmlClass.Contains("subMenu"))
                {
                    element.AddBeforeSelf(element.Elements());
                    element.Remove();
                    GenerateXmlFromHtml(element);
                }
                else if (htmlClass.Contains("menuItem"))
                {
                    textNode = element.Nodes().OfType<XText>().FirstOrDefault();
                    text = textNode.Value;
                    videopath = element.Attribute("video").Value;
                    previewpath = element.Attribute("preview").Value;

                    if (element.HasElements)
                    {
                        sbNavigationXml.AppendLine("<MenuItem Text=\"" + text + "\" VideoPath=\"" + videopath + "\" PreviewPath=\"" + previewpath + "\">");
                        sbNavigationXml.AppendLine(GenerateXmlFromHtml(element));
                        sbNavigationXml.AppendLine("</MenuItem>");
                    }
                    else
                    {
                        sbNavigationXml.AppendLine("<MenuItem Text=\"" + text + "\" VideoPath=\"" + videopath + "\" PreviewPath=\"" + previewpath + "\" />");
                    }
                }
                else if (htmlClass.Contains("treeExpand"))
                {
                    element.AddBeforeSelf(element.Elements());
                    element.Remove();
                    GenerateXmlFromHtml(element);
                }
            }
            else
            {
                element.AddBeforeSelf(element.Elements());
                element.Remove();
                GenerateXmlFromHtml(element);
            }
        }
    }
    catch (Exception)
    {
        throw;
    }
    return sbNavigationXml.ToString();
}

At the end, I want this to produce this XML output:

<Navigation>
  <MenuItem Text="Menu 1" VideoPath="" PreviewPath="">
    <MenuItem Text="Menu 2">
      <MenuItem Text="Menu 3">
        <MenuItem Text="Menu 4" VideoPath="" PreviewPath="" />
      </MenuItem>
      <MenuItem Text="Menu 3" />
      <MenuItem Text="Menu 3" />
    </MenuItem>
  </MenuItem>
  <MenuItem Text="Menu 1" VideoPath="" PreviewPath="">
    <MenuItem Text="Menu 2">
      <MenuItem Text="Menu 3">
        <MenuItem Text="Menu 4" VideoPath="" PreviewPath="" />
      </MenuItem>
      <MenuItem Text="Menu 3" />
      <MenuItem Text="Menu 3" />
    </MenuItem>
  </MenuItem>
</Navigation>

In other words, the sub menu's should fall away, as well as the tree expand divs, and I then want to produce the XML, but at the moment, I'm still failing miserably. Please ask if something is not clear. Any help appreciated!!!

===================================================================================================

EDIT: The fixed recursive method, for anyone who want to see:

private string GenerateXmlFromHtml(XElement elem)
{
    //HTML will always have a video and preview, according to the generation of the html structure.
    StringBuilder sbNavigationXml = new StringBuilder();
    string text = string.Empty;
    string videopath = string.Empty;
    string previewpath = string.Empty;
    XText textNode;

    try
    {
        foreach (XElement element in elem.Elements())
        {
            //element.Name = "MenuItem"; //Change element name.
            string htmlClass;
            try { htmlClass = element.Attribute("class").Value; }
            catch { htmlClass = ""; }

            if (!string.IsNullOrEmpty(htmlClass))
            {
                if (htmlClass.Contains("subMenu"))
                {
                    if (element.HasElements)
                    {
                        sbNavigationXml.AppendLine(GenerateXmlFromHtml(element));
                    }
                }
                else if (htmlClass.Contains("menuItem"))
                {
                    textNode = element.Nodes().OfType<XText>().FirstOrDefault(); //Get node Text attribute value.
                    text = textNode.Value;
                    videopath = element.Attribute("video").Value; //Get node VideoPath attribute value.
                    previewpath = element.Attribute("preview").Value; //Get node PreviewPath attribute value.

                    if (element.HasElements)
                    {
                        sbNavigationXml.AppendLine("<MenuItem Text=\"" + text + "\" VideoPath=\"" + videopath + "\" PreviewPath=\"" + previewpath + "\">");
                        sbNavigationXml.AppendLine(GenerateXmlFromHtml(element));
                        sbNavigationXml.AppendLine("</MenuItem>");
                    }
                    else
                    {
                        sbNavigationXml.AppendLine("<MenuItem Text=\"" + text + "\" VideoPath=\"" + videopath + "\" PreviewPath=\"" + previewpath + "\" />");
                    }
                }
                else if (htmlClass.Contains("treeExpand"))
                {
                    //DO NOTHING
                }
            }
            else
            {
                if (element.HasElements)
                {
                    sbNavigationXml.AppendLine(GenerateXmlFromHtml(element));
                }
            }
        }
    }
    catch (Exception)
    {
        throw;
    }
    return sbNavigationXml.ToString();
}

Answer 1

Try separating the input and output on different documents.

Then navigate the input and start outputting this to your XmlDocument output (another variable) in the format you want.

Something like...

class Converter
{
    public XmlDocument Convert(XmlDocument inputDocument)
    {
        XmlDocument result = new XmlDocument();
        ConvertNode(inputDocument.DocumentElement, result.DocumentElement, result);
        return result;
    }

    public void ConvertNode(XmlNode inputNode, XmlNode outputNode, XmlDocument outputDoc)
    {
        XmlNode newNode = null;

        // check elemment class
        string htmlClass;
        try { htmlClass = inputNode.Attributes["class"].Value; }
        catch { htmlClass = ""; }

        if(!string.IsNullOrWhiteSpace(htmlClass))
        {
            if (htmlClass.Contains("menuItem"))
            {
                newNode = outputDoc.CreateElement("MenuItem");
                outputNode.AppendChild(newNode);
            }

            /// check other wanted nodes etc..
        }

        if (newNode != null)
        {
            foreach (XmlNode node in inputNode.ChildNodes)
            {
                ConvertNode(node, newNode, outputDoc);
            }
        }
    }
}