Introducing /extract - Get web data with a prompt

January 20, 2025

•

Eric Ciarla imageEric Ciarla

Introducing /extract: Get structured web data with just a prompt

The era of writing web scrapers is over

Today we’re releasing /extract - write a prompt, get structured data from any website. No scrapers. No pipelines. Just results.

Getting web data is hard

If you’ve ever needed structured data from websites—whether to enrich your CRM, monitor competitors, or power various applications—you’re probably familiar with the frustrating options available today:

  • Manually researching and copy-pasting data from multiple sources, consuming countless hours
  • Writing and maintaining fragile web scrapers that break at the slightest site change
  • Using scraping services and building complex LLM pipelines with limited context windows that force you to break down data manually

Fortunately, with our /extract endpoint, you can leave these cumbersome approaches in the past and focus on what matters - getting the data you need.

What You Can Build With /extract

Companies are already using /extract to:

  • Enrich thousands of CRM leads with company data
  • Automate KYB processes with structured business information
  • Track competitor prices and feature changes in real-time
  • Build targeted prospecting lists at scale

Here’s how it works:

  1. Write a prompt describing the data you need
  2. Point us at any website (use wildcards like example.com/*)
  3. Get back clean, structured JSON

No more broken scrapers. No more complex pipelines. Just the data you need to build.

Current Limitations

While /extract handles most web data needs effectively, there are some edge cases we’re actively improving:

  1. Scale Limitations: Very large sites (think Amazon’s entire catalog) require breaking requests into smaller chunks
  2. Advanced Filtering: Complex queries like time-based filtering are still in development
  3. Consistency: Multiple runs may return slightly different results as we refine our extraction model

We’re actively working on these areas. Our goal is to make web data as accessible as an API - and we’re getting closer every day.

Get Started

  1. Try it Now

    • Get 500,000 free tokens in our playground
    • See examples and experiment with different prompts
    • No credit card required
  2. Build Something Real

Ready to turn web data into your competitive advantage? Get started in less than 5 minutes.

— Caleb, Eric, Nick and the Firecrawl team 🔥

Ready to Build?

Start scraping web data for your AI apps today.
No credit card needed.

About the Author

Eric Ciarla image
Eric Ciarla@ericciarla

Eric Ciarla is the Chief Operating Officer (COO) of Firecrawl and leads marketing. He also worked on Mendable.ai and sold it to companies like Snapchat, Coinbase, and MongoDB. Previously worked at Ford and Fracta as a Data Scientist. Eric also co-founded SideGuide, a tool for learning code within VS Code with 50,000 users.

More articles by Eric Ciarla