does adobe scan output pdf? or a html wrapper?

im trying to extract data from my adobe scanned files. 
as a coding newbie, im having a bit of trouble. 
i tried using the PDF Extract API but i ran into issues. 
the type of documents im working with are printed papers from the POS of a register. 
i'd like to extract, for example, the date from the printed report (just as an example).

should i just stick to chatgpt to do this or is adobe's pdf services able to extract information accurately?

😵