Scrape Web Pages into Markdown with Firecrawl in Jinba Flow

Use FIRECRAWL_SCRAPE to crawl a web page and return its content as markdown using a Firecrawl API key.

The Firecrawl tool provides functionality for automating website crawling and data collection.

• FIRECRAWL_SCRAPE
  • Scrape web pages and extract data
  • Supports various output formats (markdown, HTML, JSON, links, screenshot)
  • Selective content extraction with includeTags (use only when specific elements are requested)
  • Content filtering with excludeTags
  • Customizable crawling parameters

Connect with a Firecrawl API key

If you do not have an API key, you can still run Firecrawl tools by using Jinba API credit. If you’d like to use your own API key, you can obtain one from the official Firecrawl website and follow the developer documentation.

Note: Treat API keys as sensitive information and never commit them to public repositories.

Scrape a web page

- id: scrape
  tool: FIRECRAWL_SCRAPE
  config:
    - name: token
      value: "{{secrets.FIRECRAWL_API_KEY}}"
  input:
    - name: url
      value: https://news.ycombinator.com
    - name: formats
      value: '["markdown","html","links"]'
    - name: includeTags
      value: '[".title a",".score",".age"]'
    - name: excludeTags
      value: '[".comment"]'
    - name: waitFor
      value: "1000"