n8n Workflow: Extract Business Directory Listings to Google Sheets

Automatically extract business directory listings into Google Sheets (daily)

This n8n workflow pulls business-directory listing URLs from Google Sheets, captures fully rendered pages with Snapshot Site, uses OpenAI (n8n Information Extractor) to extract structured business records, and writes the results back to your sheet—while logging any capture or extraction failures.

What this workflow does

• Runs daily at 12 PM using a scheduled trigger.
• Reads input URLs from the “Directory Sources” tab in your Google Sheets spreadsheet.
• Processes URLs one at a time to fetch data reliably and steadily.
• Captures fully rendered HTML for each directory page via Snapshot Site, routing API errors to an error-log flow.
• Cleans captured HTML by removing scripts/styles and trimming content before extraction.
• Extracts structured listings by sending the cleaned HTML to OpenAI through n8n’s Information Extractor, returning an array of business records.
• Writes to “Businesses” tab by splitting extracted businesses into rows and appending/updating while deduplicating by directoryUrl.
• Logs failures by appending capture/extraction errors to the “Extraction Errors” tab and continuing with remaining URLs.

Use cases

• Build and refresh a lead database from multiple business directory sources on a schedule.
• Maintain a clean Google Sheets CRM by deduplicating results using directoryUrl.
• Continuously audit directory pages by tracking errors in “Extraction Errors” for failed captures/extractions.

Technical details

• Snapshot Site: uses the community node n8n-nodes-snapshot-site and Snapshot Site credentials to fetch fully rendered HTML.
• OpenAI: configured via an OpenAI (Chat Model) credential used by n8n’s Information Extractor.
• Google Sheets: reads URLs and writes extracted businesses plus error logs to dedicated tabs.
• Workflow nodes include if, set, code, no op, split out, and sticky note.