firecrawl-interact

Scrape the page first with firecrawl scrape, then run firecrawl interact with a --prompt describing the action, such as clicking a button or filling a field. The scrape ID is saved automatically so subsequent interact calls target the same session.

Use the --profile flag on the initial scrape to persist cookies and localStorage, then interact to complete the login form. Later scrapes with the same profile reconnect to the authenticated session, and --no-save-changes allows read-only reconnects.

Use interact only as a last resort after scrape fails because content is behind JavaScript interaction, such as pagination, infinite scroll, or multi-step flows. Never use it for web searches; use the search command instead.

Yes, pass --code with --language set to bash, python, or node to execute precise commands in the session. Use either --prompt or --code per call, and set --timeout up to 300 seconds for longer operations.

Interact requires a scrape ID from a previous firecrawl scrape call, so you must scrape the page first. The ID is saved automatically, but you can target a specific scrape with --scrape-id when working with multiple pages in parallel.