Batch Scrape URLs from Sheets to Docs with Firecrawl

This n8n workflow streamlines batch web scraping by reading a list of URLs from a Google Sheets template, validating and filtering them to process only new or unhandled entries. It then loops through each URL, leverages Firecrawl's API to extract and convert page content into clean markdown format, and automatically generates a dedicated Google Doc for every scraped page in your Google Drive.

Ideal for AI chatbot developers building knowledge bases, content managers migrating websites, or data analysts performing competitive research, this workflow saves hours of manual copying and formatting. It includes progress tracking by updating the original spreadsheet with completion status and links to new Docs, plus a final notification summarizing the batch results.

Key benefits include efficient handling of dozens or hundreds of pages without rate limits issues via sequential processing, structured markdown output perfect for AI ingestion or documentation, and seamless Google ecosystem integration. Setup requires Firecrawl API key, Google credentials, and a simple Sheets template—making it accessible yet powerful for scaling content extraction tasks.