How do I extract data from a scanned PDF using the PDF Extract API?

The PDF Extract API can work with both native (digital) and scanned PDFs. It uses Sensei, which is Adobe's AI technology, to understand the content. You just send your scanned PDF to the API, and it will process it and return structured data, even if the original was a scan.

What is the difference between PDF Extract API and Document Generation API?

Feature Purpose Direction. PDF Extract API Turns PDFs into structured data (JSON, Markdown) PDF -> Data Document Generation API Creates PDFs or Word documents from data and templates Data -> PDF/Word

Why should I use the PDF Extract API instead of just copying and pasting text from a PDF?

Using the PDF Extract API is much better for large amounts of data. Copying and pasting is slow and can lose the structure of tables or reading order. The API automatically gives you structured data like JSON, which is easy for other computer programs to use and analyze.

If my PDF has tables, how does the PDF Extract API handle them?

The PDF Extract API is very good at identifying tables within your PDF. When you extract data, it can convert these tables into formats like CSV or XLSX. This means you get your table data in a spreadsheet format, which is easy to open and work with in programs like Microsoft Excel.

What kind of output can I expect from the PDF Extract API?

Structured JSON or Markdown for text and general content. CSV or XLSX files for tables. PNG images for any pictures found in the PDF.

Integrate PDF data extraction into Power Automate workflows in Adobe Acrobat — How-to & AI prompts

AI prompts

3 ways to ask · copy any one

AExecute — “help me do it”Show me how to set up PDF data extraction from Acrobat…+

Show me how to set up PDF data extraction from Acrobat into Power Automate to send information to [destination system].

when the reply comes backWant to add extra steps, like approval or notifications?

BImprove — “do it better”How can I improve the accuracy of PDF data extraction…+

How can I improve the accuracy of PDF data extraction in my Acrobat and Power Automate workflow for [type of PDF]?

when the reply comes backNeed help mapping PDF fields to your system?

CDecide — “help me choose”Which is better for sending PDF data: Power Automate or [other system]…+

Which is better for sending PDF data from Acrobat: Power Automate or [other system]? Explain the pros and cons for my use case.

when the reply comes backCurious how to handle multiple PDFs at once?

How to do it

the tool · the steps · what to avoid

1
Sign in to your Adobe Developer Console and create a new project or select an existing project.
2
Add the PDF Services API to your project and generate OAuth credentials (Client ID and Client Secret).
CautionStore your Client Secret securely; you will need it for authentication in Power Automate.
3
Download the service account JSON file from the credentials section in the Adobe Developer Console.
4
In Microsoft Power Automate, create a new flow or open an existing flow where you want to add PDF data extraction.
5
Add a trigger for your business process, such as receiving a new email with an attachment or a file upload to SharePoint.
6
Insert an HTTP action to call the Adobe PDF Extract API endpoint, configuring it to use your OAuth credentials and the PDF file from your trigger as the request body.
Best practiceYou can use Power Automate's dynamic content to pass the PDF file directly from the trigger into the HTTP action.
7
Parse the JSON response from the Adobe PDF Extract API using the Parse JSON action in Power Automate.
8
Add subsequent actions in your flow to process, store, or route the extracted data as required by your business process.

In the appWith the API

You can monitor the status and outputs of your PDF extraction flow directly in Power Automate's run history.

The Adobe PDF Extract API endpoint (https://pdf-services.adobe.io/extract) extracts structured data from PDF files for integration into automated workflows.

Glossary

words on this page

Power AutomateA Microsoft tool to connect apps and automate tasks.ExamplePower Automate can automatically save email attachments to your cloud storage and notify you.

PDF Data ExtractionGetting information out of a PDF file so it can be used elsewhere.ExampleSoftware performed PDF data extraction to pull all customer names from the invoices into a spreadsheet.

IntegrationConnecting two different apps so they work together automatically.ExampleThe integration between the calendar and email apps sends meeting invites automatically.

The real tasks

the one, listed here

Convert emailed bills into a standard, editable copy so data can be entered into our ledger.

FAQ

about this task

To connect Acrobat to Power Automate, you use a special connector in Power Automate that lets you pick PDF files and extract their data. After setting up the connector, you can create workflows that automatically move this data to other places, like Excel or SharePoint.

PDF data extraction means pulling out information like names, dates, or totals from a PDF file. Using Power Automate helps you move this data to other apps without copying and pasting, saving time and reducing mistakes.

Yes, you can! Once Power Automate has the PDF data, you can add steps in your workflow to send it to Salesforce, Teams, or many other apps. This helps keep your information up to date everywhere.

Integrating Acrobat with Power Automate lets you automate tasks across many online systems, not just your computer. Desktop-only solutions are limited to one device, but Power Automate works in the cloud and can connect to many services.

Automating PDF data extraction saves you time, reduces errors, and makes sure your data goes exactly where you need it. Manual work can be slow and mistakes are easy to make, especially with lots of files.

Integrate PDF data extraction into Power Automate workflows

When to use it

AI prompts

How to do it

Glossary

The real tasks

Who does this

FAQ

Sources