{"id":86973,"title":"/extract by Firecrawl - Get structured website data with just a prompt","tagline":" Turn entire websites into structured data with AI","body":"Hey everyone! We’re Eric, Caleb, and Nick from Firecrawl (S22). Today, we’re launching **/extract** — an endpoint that turns entire websites into structured data with a prompt.\n\n**TL;DR**\n\nWith Firecrawls' new /extract endpoint, any website can be turned into structured data with a simple API call and prompt. We handle the complexity so you can focus on building your company.\\\n\\\n**The Problem.**\n\nIf you need to pull data from websites - maybe to enrich your CRM, track competitors, or onboard users - you're stuck with:\n\n1. Manually researching and copy-pasting from multiple sources \\\\\n2. Building and maintaining scrapers that break at the slightest site change\n3. Stitching together scraping services and complex LLM pipelines with limited context windows\\\n   \\\n   Each approach wastes the engineering time you could spend shipping a product. :\n\n## **Our Solution:**\n\n/extract is an API that turns a prompt into structured web data.\n\n![uploaded image](/media/?type=post\u0026id=86973\u0026key=user_uploads/1045172/62c44a11-9011-4ae0-82ac-8151a9c57c1b)\n\nHere's how to use it: \n\n1. **Give us URLs + Prompt**\\\n   Write what data you want, and point us at websites. Use wildcards like [example.com/\\*](http://example.com/\\*) to scan entire sites.\n2. **We Find Relevant Content**\\\n   Our crawler finds and ranks the pages that matter, automatically.\n3. **AI Extracts Data**\\\n   Intelligent agents split, search and parallelize the work, handling sites of any size.\n4. **Get Clean JSON**\\\n   Receive structured data ready to use - no post-processing needed.\n5. **Integrate anywhere via API**\\\n   With our API, you can use firecrawl anywhere, whether its in your applications or no-code tools like Zapier\n\n## **Why It Works**\n\n* **Handle Any Website:** Built on proven scraping infrastructure that just works\n* **Natural Language Input:** Describe what you want in plain English - we figure out the schema\n* **No Size Limits:** Process massive sites by automatically splitting the work\n* **Use It Anywhere:** Full API + ready-made integrations for Python, Node, and Zapier\n\n## **Limitations - (and the road ahead)**\n\nLet's be honest - while /extract is pretty awesome at grabbing web data, it's not perfect yet. Here's what we're still working on:\n\n1. Big sites are tricky - It can't (yet!) grab every single product on Amazon in one go\n2. Complex searches need work - Things like \"find all posts posted after 2024\" aren't quite there\n3. Sometimes, it's a bit quirky - Results can vary between runs, though it usually gets what you need\n\nBut here's the exciting part: we're seeing the future of web scraping take shape. \n\n## **Get Started**\n\n1. **Try the Open Beta**\n   * For a limited time, get **500,000 free** tokens to get you started\n   * Explore the [www.firecrawl.dev/playground?mode=extract](http://www.firecrawl.dev/playground?mode=extract) \n   * Read the docs =\u003e \u003chttps://docs.firecrawl.dev/features/extract\u003e\n2. **Join Our Community**\n   * Star us on [www.github.com/mendableai/firecrawl](http://www.github.com/mendableai/firecrawl) - we're open-source!\n   * Share your use cases and feedback.\n\nReady to turn web data into your competitive advantage? Get started in less than 5 minutes.\n\nGet your API key at [www.firecrawl.dev/app](http://www.firecrawl.dev/app)\n\n— Eric, Caleb, and Nick at Firecrawl 🔥","slug":"Mcn-extract-by-firecrawl-get-structured-website-data-with-just-a-prompt","created_at":"2025-01-20T16:54:10.692Z","updated_at":"2026-07-22T00:04:18.073Z","total_vote_count":14,"url":"https://www.ycombinator.com/launches/Mcn-extract-by-firecrawl-get-structured-website-data-with-just-a-prompt","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":27152,"name":"Firecrawl","slug":"firecrawl","url":"https://www.firecrawl.dev","logo":"https://bookface-images.s3.amazonaws.com/small_logos/fe35a47d1e4dd7a3c1a7dcbea86c08b5ef2d67e6.png","batch":"Summer 2022","industry":"B2B","tags":["Developer Tools","Open Source","AI"],"search_path":"https://bookface.ycombinator.com/company/27152"}}