Add Parsed PDF Data to Google Sheets Using PDF.co and Zapier

6 Minutes Read

This tutorial shows how to monitor a Google Drive folder, extract structured data from newly added PDFs with PDF.co, and add the results to Google Sheets.

Prerequisites

A Google Drive folder for incoming PDFs
A Google Sheets spreadsheet with column headers for the extracted data
A PDF.co Document Parser template
PDF.co and Zapier accounts

Create and test your extraction template in the PDF.co Document Parser Template Editor before building the Zap.

IN THIS TUTORIAL

Create the Google Drive Trigger

Add the PDF.co Document Parser

Prepare Google Sheets

Add the Google Sheets Action

Test and Publish the Zap

Step 1: Create the Google Drive Trigger

Create a new Zap and configure the trigger:

Select Google Drive.
Choose New File in Folder.
Connect your Google Drive account.
Select the drive and folder containing the incoming PDFs.
Test the trigger and select a sample PDF.

The Zap will run whenever a new file is added to this folder.

Step 2: Add the PDF.co Document Parser

Add an action and configure it as follows:

Select PDF.co.
Choose Document Parser.
Sign in and authorize Zapier to access your PDF.co account.

Complete the action fields:

Document URL: Map the file returned by the Google Drive trigger. When Zapier offers both a link and a file object, use the File value.
Template ID: Select or enter the ID of your PDF.co Document Parser template.

Test the action. PDF.co should return the extracted information in outputs including body and simplifiedData. Use simplifiedData for straightforward field mapping in the next step.

Step 3: Prepare Google Sheets

Create a spreadsheet with a header row that matches the information extracted from the PDF.

For example:

Invoice Number | Invoice Date | Customer | Total

Zapier uses these headers as fields when configuring the Google Sheets action.

Step 4: Add the Google Sheets Action

Add another action:

Select Google Sheets.
Choose Create Spreadsheet Row.
Connect your Google account.
Select the drive, spreadsheet, and worksheet.
Map each spreadsheet column to the corresponding value from PDF.co’s simplifiedData.

For example:

Invoice Number: Map the parsed invoice number.
Invoice Date: Map the parsed date.
Customer: Map the parsed customer name.
Total: Map the parsed total.

Step 5: Test and Publish the Zap

Test the Google Sheets action and confirm that a new row is created with the correct values.

Publish the Zap after the test succeeds. Each new PDF added to the selected Google Drive folder will now be parsed by PDF.co, and its extracted data will be added to Google Sheets automatically.

Conclusion

You now have an automated workflow for transferring structured information from PDF documents into Google Sheets. The extraction fields can be changed by updating the PDF.co Document Parser template and the corresponding Google Sheets mappings.

See the PDF.co Document Parser documentation for current input and output fields.