Setup & Installation
openclaw skills install @codylrn804/crawl4ai
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install crawl4ai
What This Skill Does
Crawl4ai is a Python web scraping framework that combines browser automation with AI-assisted parsing to extract structured data from websites. It handles JavaScript-rendered pages, injects custom JS, and outputs clean markdown, HTML, or structured JSON.
Handles JavaScript-rendered content natively without requiring a separate browser driver setup, unlike BeautifulSoup or Scrapy alone.
When to use it
- Scraping product prices and names from an e-commerce site
- Extracting article titles from a news or blog page
- Pulling form data from a page that loads via JavaScript
- Cleaning and converting messy HTML into readable markdown
- Batch scraping multiple URLs in a single session
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Extract all product names and prices from this e-commerce URL
AGENT
- 1Instantiate AsyncWebCrawler with headless browser mode
- 2Run crawler on the URL with javascript=true and a custom js_code selector targeting product elements
- 3Receive extracted_content with structured name/price fields
- 4Filter and normalize the returned array into a clean list
OUTPUT
JSON array of objects each containing product name and price