I have a question.
I need to get data from a document. But the client has a lot of suppliers, and they all have a slightly different version of the same standard document. It contains text-typed and hand-typed text in various combinations. And it is in a multitude of languages.
I don't think this can be done with alternative layouts because there is nothing to classify the document as they all contain the same information.
How would I go about extracting data from these documents?
I only need information from 4 sections of the docs.
I added a screenshot to clarify.
These are some of the variations for section 1 of the document.
if someone has an idea, greatly appreciated