Skip to main content
Article·npmjs.com
automationdata-pipelinesweb-developmentragllmfirecrawl-clifirecrawl

firecrawl-cli

Scrape and crawl websites directly from your terminal using Firecrawl-cli. Extract structured data for AI models, RAG systems, or data-driven projects, bypassing complex custom scripts for rapid data acquisition.

beginner5 min3 steps
The play
  1. Install Firecrawl CLI
    Install the Firecrawl command-line interface globally using npm.
  2. Crawl a Target URL
    Execute the `firecrawl crawl` command, specifying the URL, output file, and desired output mode (e.g., `markdown`).
  3. Access Extracted Data
    Open the generated output file (e.g., `firecrawl_data.json`) to view the structured content extracted from the website.
Starter code
firecrawl crawl --url https://www.firecrawl.dev/ --output firecrawl_data.json --mode markdown
Source
firecrawl-cli — Action Pack