Stirling-PDF: local web application to perform various operations on PDFs

Re:Stirling-PDF: local web application to perform various op... by 101008 on Monday December 25, 2023 @04:10PM (#38766139)

I still couldn't find a tool for a difficult problem to solve. I have some magazines in PDF, with layouts in two columns, etc. I want them to be transformed into Markdown. I know, it should identify automatically the two columns, different layouts, etc.

I am not desiring something perfect - I can fix if ther are some errors, but so far nothing has come with a good result.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by layer8 on Monday December 25, 2023 @04:21PM (#38766234)

This can be arbitrarily difficult to do, depending on the PDF. This is generally called PDF reflowing. Another approach is to use column-aware OCR software.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by qingcharles on Monday December 25, 2023 @04:49PM (#38766459)

This is a hard problem. Cut the PDF down so it's only the pages of the article you want and then try feeding it through GPT Pro or Claude?

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by jftuga on Monday December 25, 2023 @04:57PM (#38766520)

Have you tried this (for at least solving part of the problem)?

https://github.com/pdfcpu/pdfcpu

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by stavros on Monday December 25, 2023 @06:21PM (#38767305)

Depending on how much you're willing to pay, the OpenAI GPT-Vision API can definitely do this extremely well.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by 101008 on Monday December 25, 2023 @07:41PM (#38767818)

I am willing to pay for this, I only have around ~80 files, with 30 pages each (average). Is there a quick way to test this without wasting too much on the code part?

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by stavros on Monday December 25, 2023 @07:43PM (#38767837)

Yes, ChatGPT will do it if you upload photos of the page.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by 101008 on Monday December 25, 2023 @08:05PM (#38767958)

I just tried it with the API and it worked better than expected. Now I need to find to convert PDF to JPG with an API, and find the best prompt to ask GPT to only convert to markdown articles and not pages with columns, ads, etc. Thanks!

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by stavros on Monday December 25, 2023 @08:08PM (#38767971)

No problem! There are many Linux programs (some in this thread) to convert a pdf to images, and the prompt will hopefully not be too hard.

I started making app to read our board game cards out loud (with voice) for our horror board game nights (https://boardguru.net) and GPT-4 could read cards that I couldn't make out!

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by slig on Tuesday December 26, 2023 @10:33AM (#38772605)

>Now I need to find to convert PDF to JPG with an API

You can do that very easily with a locally installed ImageMagick. ChatGPT can help with the commands needed, but should be just one to convert a PDF to a number of JPGs and a small shell script to run on all your files.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by solardev on Monday December 25, 2023 @06:23PM (#38767310)

I use Briss for this: https://github.com/mbaeuerle/Briss-2.0

It overlays all the pages on top of each other, you the human draws rectangles around the stacked columns in the easy GUI, and then it processes them into pages.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by jbverschoor on Monday December 25, 2023 @06:28PM (#38767339)

The built-in apple preview application does exactly what you want..

It just looses bold etc.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by pklee on Monday December 25, 2023 @07:44PM (#38767842)

Have you considered marker. Does a very good job of turning PDF into markdown. - https://github.com/VikParuchuri/marker

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by rmbyrro on Monday December 25, 2023 @08:21PM (#38768057)

I bet GPT vision will do that like cutting a piece of cake. It'll even do the OCR for you and organize the text nicely.

[ Parent | on HN ]

Re:Stirling-PDF: local web application to perform various op... by pseingatl on Tuesday December 26, 2023 @09:17PM (#38778363)

There's this: https://www.cp.eng.chula.ac.th/~somchai/cut2col/ Free and it works pretty well.

[ Parent | on HN ]