Crawl4AI
Indkapsler Crawl4AI browser-scraperen til JS-tunge sider, batch-crawls og LLM-fri skemaudtrækning.
Testet · Virker
Hvad det gør
Leverer CLI (crwl) and Python SDK patterns for Crawl4AI, a Playwright-backed crawler that renders JavaScript-heavy pages and SPAs that plain HTTP fetches can't reach. Dækker clean markdown generation, LLM-free CSS/JSON schema extraction, concurrent multi-URL batch crawling, sitemap-driven URL discovery, and login/session handling. Udløses ved crawl4ai, crwl, scraping SPAs/JS-heavy sites, and schema-based extraction; explicitly defers to lighter tools (defuddle/fetch-web) for static HTML.
Testrapport
Kørte the skill's exact recommended command against a live JS-rendered test page: a naive curl+CSS-selector scrape returned zero quotes, while `crwl ... -c wait_until=networkidle` returned all ten quotes med authors and tags cleanly formatted in markdown.
Testet: 2026-07-14 · Claude Code 2.x (agent harness)
Installation
git clone https://github.com/brettdavies/crawl4ai-skill cd crawl4ai-skill mkdir -p ~/.claude/skills cp -r . ~/.claude/skills/crawl4ai
Kommandoer og eksempelprompter
/crawl4aiIndkapsler Crawl4AI browser-scraperen til JS-tunge sider, batch-crawls og LLM-fri skemaudtrækning.
Skills udløses af almindelige forespørgsler — ingen kommandoer at huske. Efter installationen aktiverer prompter som disse skillen (på engelsk):
Scrape this SPA's product listings, it's all client-rendered React.Crawl 500 URLs from this sitemap into clean markdown for me.Extract price and name from these product pages with a CSS schema.