extract_structured

curl -X POST https://crawlforge.dev/api/v1/tools/extract_structured \
  -H "X-API-Key: cf_test_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/product/123",
    "schema": {
      "type": "object",
      "properties": {
        "title": { "type": "string" },
        "price": { "type": "number" },
        "in_stock": { "type": "boolean" }
      },
      "required": ["title", "price"]
    },
    "prompt": "Extract the product name, price in USD, and availability",
    "llmConfig": { "provider": "openai", "apiKey": "sk-..." }
  }'

// npm install crawlforge-sdk
import { CrawlForge } from 'crawlforge-sdk';

const client = new CrawlForge({ apiKey: process.env.CRAWLFORGE_API_KEY });

const result = await client.extractStructured({
  url: 'https://example.com/product/123',
  schema: {
    type: 'object',
    properties: {
      title: { type: 'string' },
      price: { type: 'number' },
    },
    required: ['title'],
  },
  selectorHints: {
    title: 'h1.product-title',
    price: '.price-value',
  },
  fallbackToSelectors: true,
});

// result.data is untyped in crawlforge-sdk 0.1 — its shape is the Response Example below.
const { data: product } = result.data as { data: { title: string; price: number } };
console.log(product.title, product.price);

# pip install crawlforge
from crawlforge import CrawlForge

client = CrawlForge()  # reads CRAWLFORGE_API_KEY

result = client.extract_structured(
    url='https://example.com/article/42',
    schema={
        'type': 'object',
        'properties': {
            'headline': {'type': 'string'},
            'author': {'type': 'string'},
            'published_at': {'type': 'string'},
            'tags': {'type': 'array'},
        },
        'required': ['headline'],
    },
    prompt='Extract headline, author, publish date (ISO 8601), and tags',
)

# result.data is a plain dict — its shape is the Response Example below.
print(result.data['data'])