Firecrawl Batch Scraper: Clean Blog Posts to Google Docs (n8n)

Batch-scrape blog posts with Firecrawl, clean the text, and save it to Google Docs—automatically in n8n

This n8n workflow manually batch-scrapes a list of blog post URLs using Firecrawl, waits for the batch result, cleans the returned markdown into plain text, and writes the combined content into a new Google Doc.

What this workflow does

• Manual start in n8n: Runs when you manually execute the workflow.
• Create a Firecrawl batch scrape job: Submits a configured list of blog post URLs to Firecrawl for batch scraping.
• Poll until completion: Waits one minute, then repeatedly checks Firecrawl batch status until it reports completed or failed.
• Fail fast on errors: If Firecrawl returns a failed status, the workflow stops with an error message.
• Create a Google Doc: Once the scrape completes, it creates a new Google Doc titled with the Firecrawl batch ID.
• Clean and combine content: Cleans the scraped markdown by removing navigation/footer sections, links, images, and most markdown formatting while keeping titles and source URLs.
• Write cleaned text to Google Docs: Inserts the combined cleaned output into the newly created document.

Use cases

• Content repurposing: Turn a set of blog posts into a single cleaned document for internal review or drafting.
• Research workflows: Consolidate multiple sources into one Google Doc without manual copy/paste.
• Operations & SaaS support: Batch-gather documentation-style content for knowledge base creation.

Technical details

• Firecrawl integration: “Firecrawl batch scrape” and “batch status-check” steps (polling until completed/failed).
• Google Docs integration: OAuth2-based Google Docs create and update steps.
• n8n nodes used: if, code, wait, google docs, sticky note, stop and error.
• Setup requirements: Add Firecrawl API credentials and Google Docs OAuth2 credentials, then replace the placeholder URL list with your target blog post URLs.