Structured Extraction

# Extract top HN stories with natural language prompt
curl -X POST https://api.webpeel.dev/v1/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://news.ycombinator.com",
    "prompt": "Extract the top 5 story titles and their point counts as a JSON array of objects with title and points fields.",
    "llmApiKey": "sk-..."
  }'

# Response:
# {
#   "success": true,
#   "data": [
#     { "title": "Llama 4 released", "points": 842 },
#     { "title": "Ask HN: Best tools for...", "points": 634 }
#   ]
# }

# No LLM key needed — heuristic extraction from article page
curl "https://api.webpeel.dev/v1/extract/auto?url=https://techcrunch.com/2025/01/15/example" \
  -H "Authorization: Bearer YOUR_API_KEY"

# Response:
# {
#   "url": "https://techcrunch.com/2025/01/15/example",
#   "pageType": "article",
#   "structured": {
#     "type": "article",
#     "title": "Example Article Title",
#     "author": "Jane Doe",
#     "publishedAt": "2025-01-15",
#     "description": "Article summary..."
#   }
# }

# Auto-extraction works on product pages too
curl "https://api.webpeel.dev/v1/extract/auto?url=https://www.amazon.com/dp/B0EXAMPLE" \
  -H "Authorization: Bearer YOUR_API_KEY"
# Returns: { pageType: "product", structured: { name, price, rating, reviewCount, ... } }

// Extract product info from an e-commerce page
const response = await fetch('https://api.webpeel.dev/v1/extract', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.WEBPEEL_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    url: 'https://shop.example.com/product/widget-pro',
    schema: {
      type: 'object',
      properties: {
        name:         { type: 'string', description: 'Product name' },
        price:        { type: 'number', description: 'Price in USD' },
        currency:     { type: 'string', description: 'Currency code (USD, EUR, etc.)' },
        availability: { type: 'string', enum: ['in_stock', 'out_of_stock', 'limited'] },
        rating:       { type: 'number', description: 'Average customer rating (0-5)' },
        reviewCount:  { type: 'integer', description: 'Number of reviews' },
        images:       { type: 'array', items: { type: 'string' }, description: 'Image URLs' },
        features:     { type: 'array', items: { type: 'string' }, description: 'Key features list' },
      },
      required: ['name', 'price'],
    },
    llmApiKey: process.env.OPENAI_API_KEY,
    model: 'gpt-4o-mini',
  }),
});

const { data, metadata } = await response.json();
console.log(data);
// {
//   name: 'Widget Pro 3000',
//   price: 49.99,
//   currency: 'USD',
//   availability: 'in_stock',
//   rating: 4.7,
//   reviewCount: 1842,
//   images: ['https://...jpg'],
//   features: ['Wireless charging', 'Waterproof', '2-year warranty']
// }
console.log(`Model: ${metadata.model}, tokens: ${metadata.tokensUsed}, ${metadata.elapsed}ms`);

import requests, os

# Extract product info from any e-commerce page
response = requests.post(
    'https://api.webpeel.dev/v1/extract',
    headers={
        'Authorization': f'Bearer {os.environ["WEBPEEL_API_KEY"]}',
        'Content-Type': 'application/json',
    },
    json={
        'url': 'https://shop.example.com/product/widget-pro',
        'schema': {
            'type': 'object',
            'properties': {
                'name':         {'type': 'string'},
                'price':        {'type': 'number'},
                'currency':     {'type': 'string'},
                'availability': {'type': 'string', 'enum': ['in_stock', 'out_of_stock', 'limited']},
                'rating':       {'type': 'number'},
                'reviewCount':  {'type': 'integer'},
                'features':     {'type': 'array', 'items': {'type': 'string'}},
            },
        },
        'llmApiKey': os.environ['OPENAI_API_KEY'],
        'model': 'gpt-4o-mini',
    },
)

result = response.json()
product = result['data']
meta = result['metadata']

print(f"{product['name']} — ${product['price']} ({product['availability']})")
print(f"Rating: {product.get('rating', 'N/A')} ({product.get('reviewCount', 0)} reviews)")
print(f"Tokens used: {meta['tokensUsed']}, elapsed: {meta['elapsed']}ms")

import requests, os

# Extract company info from a company homepage
response = requests.post(
    'https://api.webpeel.dev/v1/extract',
    headers={
        'Authorization': f'Bearer {os.environ["WEBPEEL_API_KEY"]}',
        'Content-Type': 'application/json',
    },
    json={
        'url': 'https://stripe.com',
        'schema': {
            'type': 'object',
            'properties': {
                'name':        {'type': 'string', 'description': 'Company name'},
                'tagline':     {'type': 'string', 'description': 'Main tagline or value proposition'},
                'description': {'type': 'string', 'description': 'What the company does'},
                'products':    {'type': 'array', 'items': {'type': 'string'}, 'description': 'Main products/services'},
                'targetAudience': {'type': 'string', 'description': 'Who the product is for'},
            },
        },
        'llmApiKey': os.environ['OPENAI_API_KEY'],
    },
)

data = response.json()['data']
print(f"Company: {data['name']}")
print(f"Tagline: {data.get('tagline', 'N/A')}")
print(f"Products: {', '.join(data.get('products', []))}")