Extract data from the PDF file

[Th11]

Hi all, I am new to the power automate. I am working on a scenario where I need to extract the data from a PDF document that contains 15 to 20 pages. Each page contains the same kind of structured data. Can anyone help me with how to extract those data from the PDF file?

[AlexEncodian · Accepted solution]

@Th11 

AI builder is the most flexible tool, especially if your data is unstructured (currently you can only submit a page at a time so use Split PDF if you have multi page documents.

Ecodian has various solutions that might be simpler if your data is structured. It really depends on your document format / content that you are looking to extract. Can you provide examples?

1) Extract Text from Regions

If your document has a fixed format, you can zonally extract data from a PDF.

2) Get PDF Text Layer

You could get the PDF text layer and see if you can extract the correct string using Power Automate expressions / Encodian Utility actions like Utility - Search Text (Regex) / Utility - Extract Text between Values / Utility - Extract URL's from Text / Utility - Extract Email Addresses from Text (*utility actions are cheaper...you can use them 20x and they use only 1 action credit...i.e. 0.05 credits per run)

3) Get PDF Form Data

If your PDF document is a PDF form, you can extract data using this action.

4) Convert PDF to Word and then Convert Word to txt

You can then apply Power Automate functions to search the string (Search Word Documents with Microsoft Power Automate)

5) Extract Images from PDF
Enables images to be extracted from specified regions of a PDF document and returns an array of extract image files.

[takolota]

You can also now try this…

This template processes any document just using the less expensive image recognition AI Builder service & GPT.

It seems much less expensive with a much lower barrier to entry only requiring a premium Power Automate license with 5000 AI Builder credits per month & some on-going LLM / GPT costs…

https://powerusers.microsoft.com/t5/Power-Automate-Cookbook/Extract-Data-From-PDFs-and-Images-With-G...

If I’m looking at this right, this method should cost

Image recognition +.0017

GPT prompt & output +.007

Flow actions +.00375

So about $ .013 per page.

Less expensive than any of the other microsoft document/receipt/invoice processing options. And several of those take about 30 seconds to run.
And the 5000 AI Builder credits that come with the now $15 premium Power Automate license is enough for 1500 Image recognition pages. So you could probably pro...

[Dave1968777]

Hi @Th11,

PDFco offers a powerful solution for extracting data from PDFs, and when combined with the automation capabilities of Power Automate, you have a winning combination that can save you time and effort.

We're thrilled to provide you with a comprehensive tutorial that demonstrates how to use PDFco and Power Automate for extracting data from PDF files. This tutorial will guide you step by step through the process, making it easy for you to set up and utilize this powerful solution.

You can access the tutorial here: https://pdf.co/parser-pdf-document-using-power-automate-cloud

Should you have any questions or encounter any challenges while following the tutorial, please don't hesitate to get in touch with our dedicated customer support team at support@bytescout.com.

 We're here to assist you every step of the way.

We're excited to see how this solution can enhance your workflow and productivity. 

Wishing you a fantastic day ahead!