I believe there is a pdf->text translator (or plugin with an API). Since text is the lowest common denomonator, I would then convert text to those other formats. You may want to look at the PDF related CPAN modules and see what ones can read in a PDF file, from which you could likely just get the text out of. If I get a chance, I will try to find some URL for you, or you can use Google :)

Cheers,
KM