Automate PDF Text Extraction and Record-Keeping into Google Sheets

Step 1: Monitor Google Drive for New PDFs

Node: Google Drive Trigger

Settings:

• Trigger On: Changes Involving a Specific Folder
• Folder to Watch: Select your target folder
• Watch For: File Created

Success Looks Like: When you upload a PDF to the watched folder, the workflow automatically triggers and begins processing.

Step 2: Extract Text from PDF

Node: PDF.co API → Convert from PDF

Settings:

• URL: ={{ $json.webContentLink }}
• Convert Type: PDF to Text

Success Looks Like: PDF.co returns a URL containing the extracted text and document metadata.

Step 3: Download Extracted Text

Node: HTTP Request

Settings:

• Method: Get
• URL: ={{ $json.url }}

Purpose: Downloads the actual text content from PDF.co's temporary storage URL.

Success Looks Like: The raw extracted text is now available in the workflow data for logging to Google Sheets.

Step 4: Log to Google Sheets

Node: Google Sheets → Append Row

Settings:

• Document From List: Select your tracking spreadsheet
• Sheet From List: Choose target sheet (usually "Sheet1")

Column Mappings:

• Document Name: ={{ $('PDFco Api').item.json.name }}
• Text: ={{ $json.data }}
• Page Count: ={{ $('PDFco Api').item.json.pageCount }}

Spreadsheet Setup: See sample Google Sheet here

Success Looks Like: Each processed PDF creates a new row with extracted text and metadata.