Not really XML based. PDF structure is very different, if you need to map it onto XML, you would need to 1) do it yourself, 2) apply some mapping rules of your choice and your way of defining such rules — there is no predefined one-to-one correspondence between PDF and XML.
For working with PDF, I would advise to use Open Source iText, more exactly, its .NET port called iTextSharp:
http://en.wikipedia.org/wiki/IText[
^],
http://itextpdf.com/[
^],
http://sourceforge.net/projects/itextsharp/[
^].
—SA