How to Extract Data from PDF CVs with Different Layouts Using Zapier

This tutorial shows how to extract structured information from PDF CVs using Google Drive, PDF.co Document Parser, and Zapier.

The workflow runs when a CV is added to a designated Google Drive folder. PDF.co extracts the required information, which can then be sent to Google Sheets, an applicant-tracking system, or another application.

What You Will Need

  • A Zapier account
  • A PDF.co account
  • A Google Drive folder for incoming CVs
  • A PDF.co Document Parser template

CVs contain personal information. Ensure that the applications and storage locations used in the workflow meet your organization’s privacy and data-handling requirements.

Step 1: Create a Document Parser Template

Open the PDF.co Document Parser and create a template containing the fields you want to extract.

For example:

  • Candidate name
  • Email address
  • Phone number
  • Location
  • Skills
  • Education
  • Employment history

Test the template with representative CVs before using it in Zapier. If the documents have substantially different layouts, make the extraction rules flexible enough to locate values by labels or surrounding text.

Save the template and copy its template ID.

Step 2: Create the Google Drive Trigger

Create a new Zap and select Google Drive as the trigger application.

Configure the trigger:

  • Trigger Event: New File in Folder
  • Drive: Select the appropriate Google Drive.
  • Folder: Select the folder that will receive the PDF CVs.

Connect your Google account and test the trigger. Confirm that Zapier retrieves a sample PDF and provides its file data.

Step 3: Add the Document Parser Action

Add an action and select PDF.co.

Choose Document Parser as the action event. Connect your PDF.co account when prompted and authorize Zapier to access it.

Step 4: Configure the Parser

Configure the PDF.co action:

  • Document URL: Map the PDF file from the Google Drive trigger. When Zapier provides a file value, use that value as the source document.
  • Template ID: Enter the ID of the Document Parser template created in Step 1.
  • Custom Profiles: Leave blank unless the workflow requires additional processing options.

For the current fields and outputs, see the Document Parser action documentation.

Step 5: Test the Extraction

Test the PDF.co action.

A successful result includes:

  • body: The complete structured parsing result.
  • simplifiedData: A compact version of the extracted values that is easier to map into later Zapier steps.
  • status: The processing status.
  • error: Error information, if applicable.

Review the extracted candidate information and confirm that the expected fields contain the correct values.

Step 6: Save the Extracted Data

Add an action for the application that should receive the CV data.

For example, select Google Sheets and use Create Spreadsheet Row. Map values from the PDF.co simplifiedData output into columns such as:

  • Name
  • Email
  • Phone
  • Skills
  • Education
  • Employment history
  • Source CV

You can also send the extracted information to an applicant-tracking system, CRM, database, or notification workflow.

Test the final action, then publish the Zap.

Conclusion

The Zap will now process each PDF CV added to the selected Google Drive folder, extract the required information with a saved Document Parser template, and send the structured data to the next application automatically.

Related Tutorials

See Related Tutorials