PDF Parsing output

Hi!

I'm trying to parse a PDF with multiple page and section. Basically, you have a kind of header par with some text and after a table. Both are parsed, but thetable are parsed in the CSV  and the "header" in the json and there's no way to match both part together. So I cannot know to which part the table belong too. Is there any solution for that?

Or can we split PDF based on text string?

Thanks