Title: How to extract PDF content with page numbers using Docling?

[luedblra]

Hi community,

I have a question regarding PDF processing with Docling. I'm trying to convert a PDF and would like to retain the page number information for the extracted content.

Is there a way to either:

Extract content page by page, or

Have the extracted text indicate which page each section belongs to?

Any guidance or suggestions would be greatly appreciated. Thanks in advance!

https://docling-project.github.io/docling/reference/document_converter/

[onpillow]

You could try converting a specific page with:

result = converter.convert(Path(pdf_path), page_range=(page_no, page_no))

In my case, page number detection isn’t obvious when converting the whole PDF at once. I use page_range to handle one page at a time, add the page number in the resulting Markdown, and then repeat the same process for the remaining pages.