Firecrawl Scraper

# .env file
FIRECRAWL_API_KEY=fc-your-api-key-here

# .env.local (for local development)
FIRECRAWL_API_KEY=fc-your-api-key-here

pip install firecrawl-py

import os
from firecrawl import FirecrawlApp

# Initialize client
app = FirecrawlApp(api_key=os.environ.get("FIRECRAWL_API_KEY"))

# Scrape a single page
result = app.scrape_url(
    url="https://example.com/article",
    params={
        "formats": ["markdown", "html"],
        "onlyMainContent": True
    }
)

# Access markdown content
markdown = result.get("markdown")
print(markdown)

import os
from firecrawl import FirecrawlApp

app = FirecrawlApp(api_key=os.environ.get("FIRECRAWL_API_KEY"))

# Start crawl
crawl_result = app.crawl_url(
    url="https://docs.example.com",
    params={
        "limit": 100,
        "scrapeOptions": {
            "formats": ["markdown"]
        }
    },
    poll_interval=5  # Check status every 5 seconds
)

# Process results
for page in crawl_result.get("data", []):
    url = page.get("url")
    markdown = page.get("markdown")
    print(f"Scraped: {url}")

import os
from firecrawl import FirecrawlApp

app = FirecrawlApp(api_key=os.environ.get("FIRECRAWL_API_KEY"))

# Define schema
schema = {
    "type": "object",
    "properties": {
        "company_name": {"type": "string"},
        "product_price": {"type": "number"},
        "availability": {"type": "string"}
    },
    "required": ["company_name", "product_price"]
}

# Extract data
result = app.extract(
    urls=["https://example.com/product"],
    params={
        "schema": schema,
        "systemPrompt": "Extract product information from the page"
    }
)

print(result)

npm install @mendable/firecrawl-js
# or
pnpm add @mendable/firecrawl-js
# or use the unscoped package:
npm install firecrawl

import FirecrawlApp from '@mendable/firecrawl-js';

// Initialize client
const app = new FirecrawlApp({
  apiKey: process.env.FIRECRAWL_API_KEY
});

// Scrape a single page
const result = await app.scrapeUrl('https://example.com/article', {
  formats: ['markdown', 'html'],
  onlyMainContent: true
});

// Access markdown content
const markdown = result.markdown;
console.log(markdown);

import FirecrawlApp from '@mendable/firecrawl-js';

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

// Start crawl
const crawlResult = await app.crawlUrl('https://docs.example.com', {
  limit: 100,
  scrapeOptions: {
    formats: ['markdown']
  }
});

// Process results
for (const page of crawlResult.data) {
  console.log(`Scraped: ${page.url}`);
  console.log(page.markdown);
}

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

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

// Define schema with Zod
const schema = z.object({
  company_name: z.string(),
  product_price: z.number(),
  availability: z.string()
});

// Extract data
const result = await app.extract({
  urls: ['https://example.com/product'],
  schema: schema,
  systemPrompt: 'Extract product information from the page'
});

console.log(result);

app = FirecrawlApp(api_key=os.environ.get("FIRECRAWL_API_KEY"))

docs = app.crawl_url(
    url="https://docs.myapi.com",
    params={
        "limit": 500,
        "scrapeOptions": {
            "formats": ["markdown"],
            "onlyMainContent": True
        },
        "allowedDomains": ["docs.myapi.com"]
    }
)

# Save to files
for page in docs.get("data", []):
    filename = page["url"].replace("https://", "").replace("/", "_") + ".md"
    with open(f"docs/{filename}", "w") as f:
        f.write(page["markdown"])

const schema = z.object({
  title: z.string(),
  price: z.number(),
  description: z.string(),
  images: z.array(z.string()),
  in_stock: z.boolean()
});

const products = await app.extract({
  urls: productUrls,
  schema: schema,
  systemPrompt: 'Extract all product details including price and availability'
});

article = app.scrape_url(
    url="https://news.com/article",
    params={
        "formats": ["markdown"],
        "onlyMainContent": True,
        "removeBase64Images": True
    }
)

# Get clean markdown
content = article.get("markdown")

from firecrawl import FirecrawlApp
from firecrawl.exceptions import FirecrawlException

app = FirecrawlApp(api_key=os.environ.get("FIRECRAWL_API_KEY"))

try:
    result = app.scrape_url("https://example.com")
except FirecrawlException as e:
    print(f"Firecrawl error: {e}")
except Exception as e:
    print(f"Unexpected error: {e}")

import FirecrawlApp from '@mendable/firecrawl-js';

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

try {
  const result = await app.scrapeUrl('https://example.com');
} catch (error) {
  if (error.response) {
    // API error
    console.error('API Error:', error.response.data);
  } else {
    // Network or other error
    console.error('Error:', error.message);
  }
}