Agent skill
firecrawl-scraper
Extract property data from real estate listing URLs using Firecrawl AI. Use when scraping Zillow, Redfin, Realtor.com, or any property listing site. Returns structured data ready for video generation.
Stars
163
Forks
31
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/firecrawl-scraper
SKILL.md
Firecrawl Property Extraction
Overview
Firecrawl transforms any real estate listing URL into structured JSON data for video generation. It handles JavaScript rendering, anti-bot measures, and image extraction automatically.
Quick Start
typescript
import Firecrawl from '@mendable/firecrawl-js';
import { z } from 'zod';
const firecrawl = new Firecrawl({
apiKey: process.env.FIRECRAWL_API_KEY
});
const result = await firecrawl.extract({
urls: [listingUrl],
prompt: 'Extract property details for video generation',
schema: PropertySchema
});
Supported Sites
| Site | URL Pattern | Data Quality |
|---|---|---|
| Zillow | zillow.com/homedetails/* | Excellent |
| Redfin | redfin.com//home/ | Excellent |
| Realtor.com | realtor.com/realestateandhomes-detail/* | Excellent |
| Trulia | trulia.com/home/* | Good |
| Homes.com | homes.com/property/* | Good |
| MLS Sites | Varies by region | Good |
| Broker Sites | Any | Variable |
Property Schema
See rules/property-extraction.md for complete schema.
typescript
const PropertySchema = z.object({
address: z.string(),
city: z.string(),
state: z.string(),
zipCode: z.string(),
price: z.number(),
bedrooms: z.number(),
bathrooms: z.number(),
sqft: z.number(),
lotSize: z.string().optional(),
yearBuilt: z.number().optional(),
propertyType: z.string(),
description: z.string(),
features: z.array(z.string()),
images: z.array(z.string()),
agent: z.object({
name: z.string(),
phone: z.string().optional(),
brokerage: z.string().optional(),
}).optional(),
});
Advanced Extraction
Competitor Analysis
typescript
const CompetitorSchema = z.object({
listings: z.array(z.object({
address: z.string(),
price: z.number(),
daysOnMarket: z.number(),
pricePerSqft: z.number(),
})),
marketTrends: z.object({
medianPrice: z.number(),
averageDaysOnMarket: z.number(),
inventoryCount: z.number(),
}),
});
Market Data
Best Practices
- Rate Limiting: Max 10 requests/minute on standard plan
- Error Handling: Always wrap in try/catch
- Image Quality: Request high-res images when available
- Caching: Cache results for 24 hours to save credits
- Validation: Always validate extracted data with Zod
API Integration
Next.js Route Handler
typescript
// /app/api/scrape/route.ts
export async function POST(request: Request) {
const { url } = await request.json();
const firecrawl = new Firecrawl({
apiKey: process.env.FIRECRAWL_API_KEY!
});
const result = await firecrawl.extract({
urls: [url],
prompt: 'Extract property listing data',
schema: PropertySchema,
});
return Response.json({
success: true,
data: result.data
});
}
Credit Usage
| Operation | Credits |
|---|---|
| /scrape (single page) | 1 |
| /crawl (per page) | 1 |
| /extract (AI) | Tokens-based |
| /map (URL discovery) | 1 per 100 URLs |
Error Handling
typescript
try {
const result = await firecrawl.extract({ ... });
} catch (error) {
if (error.statusCode === 429) {
// Rate limited - wait and retry
} else if (error.statusCode === 403) {
// Site blocked - try alternative approach
} else {
// Log and return fallback
}
}
Didn't find tool you were looking for?