🔥 Firecrawl

Crawl and convert any website into LLM-ready markdown. Built by Mendable.ai and the firecrawl community. Includes powerful search/serp scraping, crawling, and data extraction capabilities.

This repository is in its early development stages. We are still merging custom modules in the mono repo. It's not completely yet ready for full self-host deployment, but you can already run it locally.

What is Firecrawl?

Firecrawl is an API service that takes a URL, crawls it, and converts it into clean markdown. We crawl all accessible subpages and give you clean markdown for each. No sitemap required.

Pst. hey, you, join our stargazers :)

How to use it?

We provide an easy to use API with our hosted version. You can find the playground and documentation here. You can also self host the backend if you'd like.

• API
• Python SDK
• Node SDK
• Langchain Integration 🦜🔗
• Llama Index Integration 🦙
• Langchain JS Integration 🦜🔗
• Want an SDK or Integration? Let us know by opening an issue.

To run locally, refer to guide here.

API Key

To use the API, you need to sign up on Firecrawl and get an API key.

Crawling

Used to crawl a URL and all accessible subpages. This submits a crawl job and returns a job ID to check the status of the crawl.

curl -X POST https://api.firecrawl.dev/v0/crawl \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "url": "https://mendable.ai"
    }'

Returns a jobId

{ "jobId": "1234-5678-9101" }

Check Crawl Job

Used to check the status of a crawl job and get its result.

curl -X GET https://api.firecrawl.dev/v0/crawl/status/1234-5678-9101 \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY'

{
  "status": "completed",
  "current": 22,
  "total": 22,
  "data": [
    {
      "content": "Raw Content ",
      "markdown": "# Markdown Content",
      "provider": "web-scraper",
      "metadata": {
        "title": "Mendable | AI for CX and Sales",
        "description": "AI for CX and Sales",
        "language": null,
        "sourceURL": "https://www.mendable.ai/"
      }
    }
  ]
}

Scraping

Used to scrape a URL and get its content.

curl -X POST https://api.firecrawl.dev/v0/scrape \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "url": "https://mendable.ai"
    }'

Response:

{
  "success": true,
  "data": {
    "content": "Raw Content ",
    "markdown": "# Markdown Content",
    "provider": "web-scraper",
    "metadata": {
      "title": "Mendable | AI for CX and Sales",
      "description": "AI for CX and Sales",
      "language": null,
      "sourceURL": "https://www.mendable.ai/"
    }
  }
}

Search (Beta)

Used to search the web, get the most relevant results, scrap each page and return the markdown.

curl -X POST https://api.firecrawl.dev/v0/search \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "query": "firecrawl",
      "pageOptions": {
        "fetchPageContent": true // false for a fast serp api
      }
    }'

{
  "success": true,
  "data": [
    {
      "url": "https://mendable.ai",
      "markdown": "# Markdown Content",
      "provider": "web-scraper",
      "metadata": {
        "title": "Mendable | AI for CX and Sales",
        "description": "AI for CX and Sales",
        "language": null,
        "sourceURL": "https://www.mendable.ai/"
      }
    }
  ]
}

Intelligent Extraction (Beta)

Used to extract structured data from scraped pages.

curl -X POST https://api.firecrawl.dev/v0/scrape \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "url": "https://www.mendable.ai/",
      "extractorOptions": {
        "mode": "llm-extraction",
        "extractionPrompt": "Based on the information on the page, extract the information from the schema. ",
        "extractionSchema": {
          "type": "object",
          "properties": {
            "company_mission": {
                      "type": "string"
            },
            "supports_sso": {
                      "type": "boolean"
            },
            "is_open_source": {
                      "type": "boolean"
            },
            "is_in_yc": {
                      "type": "boolean"
            }
          },
          "required": [
            "company_mission",
            "supports_sso",
            "is_open_source",
            "is_in_yc"
          ]
        }
      }
    }'

{
    "success": true,
    "data": {
      "content": "Raw Content",
      "metadata": {
        "title": "Mendable",
        "description": "Mendable allows you to easily build AI chat applications. Ingest, customize, then deploy with one line of code anywhere you want. Brought to you by SideGuide",
        "robots": "follow, index",
        "ogTitle": "Mendable",
        "ogDescription": "Mendable allows you to easily build AI chat applications. Ingest, customize, then deploy with one line of code anywhere you want. Brought to you by SideGuide",
        "ogUrl": "https://mendable.ai/",
        "ogImage": "https://mendable.ai/mendable_new_og1.png",
        "ogLocaleAlternate": [],
        "ogSiteName": "Mendable",
        "sourceURL": "https://mendable.ai/"
      },
      "llm_extraction": {
        "company_mission": "Train a secure AI on your technical resources that answers customer and employee questions so your team doesn't have to",
        "supports_sso": true,
        "is_open_source": false,
        "is_in_yc": true
      }
    }
}

Using Python SDK

Installing Python SDK

pip install firecrawl-py

Crawl a website

from firecrawl import FirecrawlApp

app = FirecrawlApp(api_key="YOUR_API_KEY")

crawl_result = app.crawl_url('mendable.ai', {'crawlerOptions': {'excludes': ['blog/*']}})

# Get the markdown
for result in crawl_result:
    print(result['markdown'])

Scraping a URL

To scrape a single URL, use the scrape_url method. It takes the URL as a parameter and returns the scraped data as a dictionary.

url = 'https://example.com'
scraped_data = app.scrape_url(url)

Extracting structured data from a URL

With LLM extraction, you can easily extract structured data from any URL. We support pydanti schemas to make it easier for you too. Here is how you to use it:

class ArticleSchema(BaseModel):
    title: str
    points: int 
    by: str
    commentsURL: str

class TopArticlesSchema(BaseModel):
    top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")

data = app.scrape_url('https://news.ycombinator.com', {
    'extractorOptions': {
        'extractionSchema': TopArticlesSchema.model_json_schema(),
        'mode': 'llm-extraction'
    },
    'pageOptions':{
        'onlyMainContent': True
    }
})
print(data["llm_extraction"])

Search for a query

Performs a web search, retrieve the top results, extract data from each page, and returns their markdown.

query = 'What is Mendable?'
search_result = app.search(query)

Using the Node SDK

Installation

To install the Firecrawl Node SDK, you can use npm:

npm install @mendable/firecrawl-js

Usage

1. Get an API key from firecrawl.dev
2. Set the API key as an environment variable named FIRECRAWL_API_KEY or pass it as a parameter to the FirecrawlApp class.

Scraping a URL

To scrape a single URL with error handling, use the scrapeUrl method. It takes the URL as a parameter and returns the scraped data as a dictionary.

try {
  const url = 'https://example.com';
  const scrapedData = await app.scrapeUrl(url);
  console.log(scrapedData);

} catch (error) {
  console.error(
    'Error occurred while scraping:',
    error.message
  );
}

Crawling a Website

To crawl a website with error handling, use the crawlUrl method. It takes the starting URL and optional parameters as arguments. The params argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.

const crawlUrl = 'https://example.com';
const params = {
  crawlerOptions: {
    excludes: ['blog/'],
    includes: [], // leave empty for all pages
    limit: 1000,
  },
  pageOptions: {
    onlyMainContent: true
  }
};
const waitUntilDone = true;
const timeout = 5;
const crawlResult = await app.crawlUrl(
  crawlUrl,
  params,
  waitUntilDone,
  timeout
);

Checking Crawl Status

To check the status of a crawl job with error handling, use the checkCrawlStatus method. It takes the job ID as a parameter and returns the current status of the crawl job.

const status = await app.checkCrawlStatus(jobId);
console.log(status);

Extracting structured data from a URL

With LLM extraction, you can easily extract structured data from any URL. We support zod schema to make it easier for you too. Here is how you to use it:

import FirecrawlApp from "@mendable/firecrawl-js";
import { z } from "zod";

const app = new FirecrawlApp({
  apiKey: "fc-YOUR_API_KEY",
});

// Define schema to extract contents into
const schema = z.object({
  top: z
    .array(
      z.object({
        title: z.string(),
        points: z.number(),
        by: z.string(),
        commentsURL: z.string(),
      })
    )
    .length(5)
    .describe("Top 5 stories on Hacker News"),
});

const scrapeResult = await app.scrapeUrl("https://news.ycombinator.com", {
  extractorOptions: { extractionSchema: schema },
});

console.log(scrapeResult.data["llm_extraction"]);

Search for a query

With the search method, you can search for a query in a search engine and get the top results along with the page content for each result. The method takes the query as a parameter and returns the search results.

const query = 'what is mendable?';
const searchResults = await app.search(query, {
  pageOptions: {
    fetchPageContent: true // Fetch the page content for each search result
  }
});

Contributing

We love contributions! Please read our contributing guide before submitting a pull request.

It is the sole responsibility of the end users to respect websites' policies when scraping, searching and crawling with Firecrawl. Users are advised to adhere to the applicable privacy policies and terms of use of the websites prior to initiating any scraping activities. By default, Firecrawl respects the directives specified in the websites' robots.txt files when crawling. By utilizing Firecrawl, you expressly agree to comply with these conditions.