Extract Ecom Products to Google Sheets (n8n + GPT-4o)

Automatically extract e-commerce products into Google Sheets using n8n + GPT-4o

This n8n workflow pulls product listings from your e-commerce category pages, captures the fully rendered HTML, uses GPT-4o to extract structured product data, and upserts the results into Google Sheets—with error logging included.

What this workflow does

• Runs daily at 11:00 (UTC) via schedule.
• Reads category URLs one-by-one from the “Store Sources” tab in Google Sheets.
• For each URL, it uses Snapshot Site to fetch the fully rendered page HTML (with retry behavior on failures).
• If Snapshot Site fails, the workflow writes the URL, error message, and timestamp to the “Extraction Errors” tab.
• If capture succeeds, it removes scripts/styles, trims the HTML, and sends the content to the OpenAI chat model (via the Information Extractor) to return a list of products with structured fields.
• It then splits extracted products into individual rows and appends or updates them in the “Products” tab, with deduplication by productUrl.

Use cases

• Maintain an always-current product catalog from category pages for internal ops or reporting.
• Extract competitor or partner catalog data into Google Sheets for analysis and enrichment.
• Automate recurring e-commerce scraping workflows without manually exporting data.

Technical details

• n8n nodes include: if, set, code, no op, split out, sticky note.
• Snapshot Site (community node: n8n-nodes-snapshot-site) for fully rendered HTML capture + API credentials.
• Google Sheets via OAuth2 to read/write: “Store Sources”, “Products”, and “Extraction Errors”.
• OpenAI chat model / GPT-4o to extract structured product fields from cleaned HTML.

Ready to install: connect Snapshot Site, Google Sheets, and your OpenAI API credential, then align your tab names to match your spreadsheet.