Extract Text from a Scanned PDF Using PDF.co and Zapier

Step 1: Set Up the Google Drive Trigger

Upload a sample scanned PDF to a dedicated Google Drive folder.

Create a Zap and select Google Drive → New File in Folder. Connect your Google Drive account, select the drive and folder to monitor, and test the trigger.

Choose your sample PDF from the results.

Step 2: Connect PDF.co

Add PDF.co → PDF to Anything.

Connect your PDF.co account using OAuth by signing in and authorizing Zapier.

Step 3: Configure Text Extraction

Set the following fields:

• Output Format: Select Plain Text.
• Source PDF URL: Map the File value from Google Drive.
• Page Selection: Leave blank to process all pages.
• Output File Name: Enter extracted-text.txt.
• Inline Output Option: Select False to receive a downloadable text file.
• OCR Language for Scanned Documents: Select the language used in the PDF.

Leave Extraction Region blank to extract text from the entire page.

For selected pages, use zero-based numbering: 0 selects the first page, and 0-2 selects the first three pages. See the PDF to Anything documentation for configuration details.

Step 4: Test the Extraction

Test the PDF.co action and open the returned url to view or download the text file.

Compare the extracted text with the scanned document, especially names, dates, and numbers. OCR accuracy depends on the clarity of the source scan.

If you need the text directly in a later Zap step, set Inline Output Option to True and map the returned body field.

Step 5: Save the Text File

With inline output set to False, add Google Drive → Upload File.

Choose an output folder and map the PDF.co output url to File. Use a different folder from the watched input folder to prevent the saved text file from triggering the workflow again.

Test the upload, then publish the Zap. New scanned PDFs added to the input folder will be converted into text files and saved to Google Drive.