I have an untagged pdf which contains a fairly standard business form that contains a table (a row of headers with rows of data). However, as it is untagged “Indicate element” can only see the whole page. What is the best approach for extracting the table? I have looked at converting the pdf to tagged, but that isn’t possible. Anchor base doesn’t have an obvious anchor because its a set of rows under headings. Do I need to down the Document Understanding route or is there another simpler way?
All help gratefully received