How can I extract tables from a PDF using the PDF Extract API?

Use the PDF Extract API to process your PDF document. The API will identify tables within the PDF. It will then output these tables into formats like CSV or XLSX files. You can then use these files in spreadsheet programs or databases.

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

Feature PDF Extract API Document Generation API. Main Purpose Turns PDFs into structured data (JSON, Markdown) Creates new PDFs or Word documents from data and templates Direction PDF -> Data Data -> PDF/Word Use Cases Automating data entry, analysis, search Creating invoices, reports, personalized letters

Extract Financial Lines in Adobe Acrobat — How-to & AI prompts

AI prompts

1 way to ask · copy any one

BImprove — “do it better”When exporting the income statement and balance sheet to [excel], ensure column headers match…+

When exporting the income statement and balance sheet to [excel], ensure column headers match our model: unify date formats, remove footnote rows, map account names to our chart (Revenue, COGS, OpEx, Net Income; Assets, Liabilities, Equity), and flag any OCR uncertainties for manual check.

when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed.

How to do it

the tool · the steps · what to avoid

1
Open your PDF file in Adobe Acrobat.
2
Select the Export PDF tool from the right pane.
3
Choose Spreadsheet as the export format.
4
Select either Microsoft Excel Workbook (*.xlsx) or Comma Separated Values (*.csv) as your output format.
5
Click Export.
6
If prompted, specify the location and file name for the exported file, then save.
7
Open the exported file in Excel or your preferred spreadsheet application to review and analyze the extracted table data.
Best practiceIf tables are not extracted cleanly, try using the 'Organize Pages' tool to split the PDF into smaller sections before exporting, as some blogs suggest this improves accuracy for complex layouts.

In the appWith the API

You can preview the table structure in the export dialog before saving to ensure the data is being recognized correctly.

This runs in the Acrobat app - there is no separate API for this task.

Glossary

words on this page

APIA way for different software to talk to each other automatically.ExampleAn online store uses an API to automatically send shipping details to a delivery service.

JSONJSON is a simple way to store and share data. It looks like text and is easy for computers to read and write.ExampleA weather app might use JSON to send temperature and forecast data to your phone.

MarkdownMarkdown is a simple text format. It is used to write documents that can be easily converted to other formats like HTML.ExampleYou write an email in Markdown, and it converts to a formatted message.

The real tasks

the one, listed here

Extract the income statement and balance sheet lines into a spreadsheet so I can run the forecast model.

FAQ

about this task

The PDF Extract API helps you get structured data from your PDF files. This means it can turn text, tables, and even images into organized formats like JSON or Markdown. This is useful for automating tasks, like putting information into other systems or analyzing large amounts of data quickly.

Use the PDF Extract API to process your PDF document.
The API will identify tables within the PDF.
It will then output these tables into formats like CSV or XLSX files.
You can then use these files in spreadsheet programs or databases.

Yes, the PDF Extract API can work with scanned PDFs. It uses smart technology (Sensei-powered) to read text and data even from scanned documents. This means you can still get structured information from images of documents.

Structured JSON or Markdown is better because it keeps the organization of the data. Plain text is just words, but structured data tells you what each piece of information is (like a heading, a table cell, or a paragraph). This makes it much easier for other computer programs to understand and use the data automatically.

Feature	PDF Extract API	Document Generation API
Main Purpose	Turns PDFs into structured data (JSON, Markdown)	Creates new PDFs or Word documents from data and templates
Direction	PDF -> Data	Data -> PDF/Word
Use Cases	Automating data entry, analysis, search	Creating invoices, reports, personalized letters

Extract Financial Lines

When to use it

AI prompts

How to do it

Glossary

The real tasks

Who does this

FAQ

Sources