Hi,
I’m running n8n on a local machine. I’d like to automate lots of things and first of all, i’d like to test if pdf files stored in a shared folder are OCR PDF or not. Then, I’d like to have them listed in an Excel file (or text file whatever) so I know which are and which are not.
I tried the “read files from disk” but everytime I execute this step it says no result. Am I not supposed to have an output here ?
Would somebody be kind enough to help me create this workflow ?
The filnal aim would be to have only OCR PDF from which I could get many information to create an XML metadata file associated to each PDF and be able to have a summary of each file thanks to an AI agent.
Here is a workflow for you to start with:
It reads/extracts the PDF files provided, then determines if the content is text by checking the content text length and then writes the result to google sheet.
The is how the final result looked for me:
1 Like
Many thanks for your example. Having this helped me find what was wrong with my “Read/write files” configuration.
I can now easily find my OCR files and list them. Now I can try to create my next step !
Amazing! Kindly mark the answer as solution if it helped. Thank you!
Cheers
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.