Overview
Phinite’s Firecrawl integration lets assistants scrape web pages into clean markdown, extract data, and run batch crawls for analysis.
What this integration enables
- Scrape webpage content to markdown
- Extract structured data with selectors
- Crawl multiple pages and monitor changes
- Batch processing and content filtering
- Screenshots and PDF generation
Required credentials
Setup steps
Create Firecrawl account
Sign up at Firecrawl, verify email, and log in.
Generate API key
Dashboard → API Keys → Create key with appropriate permissions. Copy it.
Configure in Phinite
Workspace → Integrations → Firecrawl → + Add Configuration. Paste API key, name the connection, select assistants, and save.
Respect robots.txt and the target website’s terms of service. Large crawl jobs may take time.
- Scrape URL
- Crawl Domain
- Extract Structured Data
- Monitor Page Changes
- Convert to Markdown
- Extract Images
- Get Page Metadata
- Custom CSS Selectors
- Batch Processing
- Content Filtering
- Screenshot Capture
- PDF Generation
- Text Extraction
- Link Analysis
- SEO Data Extraction
Documentation & resources
- Docs:
https://docs.firecrawl.dev/
- API Reference:
https://docs.firecrawl.dev/api-reference
