Help creating an automated workflow - extract data from .pdfs

RakeshS

400ixl said:

You could do it with the Microsoft 365 Power platform if your company has M365 licenses.
Do you need it back into another PDF?
Example of doing the extract into Excel is https://www.process.st/how-to/extract-data-from-pdf-to-excel-using-power-automate/

Doesn't have to be a PDF, I guess. Outputting to Word or Excel doc should also work as well, i reckon.
I was looking at power automate but couldn't work out how to do it.
I'll look into it a bit more. Thanks.

If anyone else has any suggestions, I'd definitely consider them.
Someone also mentioned paying a programmer to code something specific. No idea where I'd start with something like that but it might be an option, depending on cost.

PHK

At work we receive PDFs from a variety of sources. 
Rules in Outlook save the attachment to a specific folder on our private network. 

Once a minute these are opened by Power Automate, data extracted to a file in another directory and the PDF moved to an Archive. 

I'm not in the IT team so I don't know exactly how they use Automate but just wanted to let you know it's possible. 

GDB2222

[Deleted User] said:

Have you tried something like Bard, Claude or ChatGPT?  Try "Can you extract certain pieces of information from a pdf?" and see what happens from there.

I just copied the OP into ChatGPT, and it suggested:

Use a PDF extraction library to parse the content of the PDF and extract the required information. Libraries such as PyPDF2, PyMuPDF, or pdfplumber in Python can be helpful for this task.

It also gave a code snippet, etc. That may be helpful for Rakesh, depending on his programming skills.