Extracting Text from PDFs into a CSV

[Matt_1]

Hello, we have 1,000+ PDFs that are structured roughly the same way and want to extract the line items to put into a CSV (about 4-5 columns, though they don’t have clear lines separating the cells, the formatting is consistent). The data is somewhat messy (lots of various descriptions), but the line items appear in the same place across the pages.

Is there an easy way to do this with KNIME?

Alternatively, we are able to drop the PDF into ChatGPT and it has no issue extracting the data we’re looking for into a table with the right prompt. But, we don’t want to go through and use ChatGPT for each of these. Would there be a KNIME-based solution that could run all of these through ChatGPT to consolidate into a CSV?

[hmfa]

Hi @Matt_1

Have a look at this post.

Challenge 15 - Extracting a Table from a PDF - Solution – adri_agra

Or

Extract Tables from PDF

Hello everyone, It is possible if the PDF allows it, meaning if the string we get from the PDF represents the table so that we can manipulate the String, to extract the table. I took @JAGBI’s example and parsed the first three pages as an example. In order to extract the whole table/document, some more string manipulation would have to be done. The magic happens in the Extract Table metanode, where the string is parsed to an actual table. The workflow would have to be adapted to other PDFs/tab…

Or
https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://medium.com/low-code-for-advanced-data-science/knime-extract-text-and-tables-from-pdf-files-with-python-in-a-low-code-environment-e2949a95e3fc&ved=2ahUKEwjjw7bPsp6MAxVuVaQEHUQkPbEQFnoECFEQAQ&usg=AOvVaw3bc91QuZAfS3pBsQegmESz

Maybe it can help you.
Br

[mlauber71]

@Matt_1 I can offer these examples

KNIME — Extract Text and Tables from PDF Files with Python in a Low-Code...

Edit: @hmfa also posted the link …