Gå til hovedindhold

Firecrawl

Turn entire websites and portals into clean, LLM-ready Markdown

Firecrawl crawls, handles JavaScript rendering, bypasses anti-bot barriers, and outputs clean Markdown structured for AI agent ingestion.

Kom hurtigt i gang

scrape.ts

Kom i gang med Firecrawl i dit projekt.

import FirecrawlApp from '@mendable/firecrawl-js'

const app = new FirecrawlApp({ apiKey: process.env.FIRECRAWL_API_KEY })

// Scrape a Danish public webpage into clean LLM markdown
const scrapeResult = await app.scrapeUrl('https://www.borger.dk', {
  formats: ['markdown'],
})

console.log(scrapeResult.markdown)

Om Firecrawl

Firecrawl (by Mendable) solves the messy reality of the web for AI agents. It handles headless browser rendering, proxy rotation, cookie banners, dynamic SPAs, and PDF downloads, returning pristine Markdown tailored for RAG pipelines and context windows.

DK

Danske data- og produkt-guides

Hvordan udviklere og agenter bruger Firecrawl til at tilgå dansk digital infrastruktur.

Extract Borger.dk Welfare & Pension Guides into Vector RAG

Crawl the official citizen portal Borger.dk to convert public administrative guidelines into clean Markdown for a Danish citizen advisory agent.

from firecrawl import FirecrawlApp app = FirecrawlApp(api_key="fc-xxx") content = app.scrape_url("https://www.borger.dk/pension-og-efterloen", params={"formats": ["markdown"]})

Extract Danish E-Commerce Prices & Catalogs

Scrape dynamic Danish webshops without APIs to extract structured product specifications, Danish kroner (DKK) pricing, and availability.

Nøglefunktioner

Crawls entire domains with intelligent link discovery
Transforms complex HTML tables and layouts into clean Markdown
Built-in structured JSON extraction via LLM schemas
Bypasses Cloudflare, cookie banners, and dynamic JS hydration
Official Python and TypeScript SDKs