WebExtrator Інтелектуальний API для витягування даних

Authorization: Bearer YOUR_API_KEY
Content-Type:  application/json

{
  "success": true,
  "task_id": "550e8400-e29b-41d4-a716-446655440000",
  "trace_id": "550e8400-e29b-41d4-a716-446655440001",
  "started_at": 1777717800.123,
  "finished_at": 1777717802.535,
  "elapsed": 2.412,
  "data": {
    "kind": "extract",
    "url": "https://en.wikipedia.org/wiki/Diffbot",
    "finalUrl": "https://en.wikipedia.org/wiki/Diffbot",
    "contentType": "article",
    "title": "Diffbot",
    "description": "Американська компанія з машинного навчання та управління знаннями",
    "byline": "Учасники проектів Wikimedia",
    "language": "en",
    "siteName": "Wikipedia",
    "publishedAt": "2007-08-08T05:47:27Z",
    "images": ["https://en.wikipedia.org/static/images/icons/enwiki-25.svg"],
    "links": ["https://en.wikipedia.org/wiki/Machine_learning"],
    "markdown": "# Diffbot\n\nDiffbot is a developer of machine learning ...",
    "text": "Diffbot is a developer of machine learning algorithms ...",
    "structured": {
      "schemaOrg": { "primary": { /* типізовані сутності */ }, "breadcrumbs": [], "all": [] },
      "openGraph": { "title": "...", "description": "...", "image": "...", "type": "..." },
      "jsonLd": [ /* оригінальний JSON-LD */ ]
    },
    "rawSignals": {
      "hasJsonLd": true,
      "title": "Diffbot - Wikipedia",
      "metaDescription": null,
      "pageStatus": 200,
      "textLength": 11473
    },
    "elapsedMs": 2412
  }
}

{
  "success": true,
  "task_id": "550e8400-...",
  "trace_id": "6ba7b810-...",
  "started_at": 1777717800.123
}

curl -X POST https://api.acedata.cloud/webextrator/extract \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://en.wikipedia.org/wiki/Diffbot",
    "expected_type": "article"
  }'

{
  "kind": "article",
  "subtype": "Article",
  "headline": "Американська компанія з машинного навчання та управління знаннями",
  "datePublished": "2007-08-08T05:47:27Z",
  "dateModified": "2025-07-10T20:42:45Z",
  "author": { "name": "Учасники проектів Вікіпедії", "type": "Organization" },
  "publisher": { "name": "Фонд Вікімедіа, Inc." }
}

curl -X POST https://api.acedata.cloud/webextrator/extract \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.bestbuy.com/product/apple-airpods-pro-2nd-generation-white/JJ8ZH6TPSW",
    "expected_type": "product"
  }'

{
  "kind": "product",
  "name": "Apple - Відновлені відмінні - AirPods Pro (2-го покоління) - Білий",
  "sku": "10845412",
  "model": "MQD83AM/A",
  "color": "Білий",
  "brand": "Apple",
  "offer": { "price": 159.99, "currency": "USD", "availability": "https://schema.org/InStock", "seller": "Best Buy" },
  "rating": { "value": 4.4, "count": 8 }
}

curl -X POST https://api.acedata.cloud/webextrator/extract \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.allrecipes.com/recipe/16354/easy-meatloaf/"
  }'

{
  "kind": "recipe",
  "name": "Легкий м'ясний хліб",
  "cookTime": "PT60M",
  "totalTime": "PT75M",
  "recipeYield": "8 / 1 (9x5-дюймовий) м'ясний хліб",
  "ingredients": ["1 1/2 фунта яловичини", "..."],
  "instructions": [{ "text": "Розігрійте духовку до 350°F ..." }, "..."],
  "rating": { "value": 4.7, "count": 9348 }
}

curl -X POST https://api.acedata.cloud/webextrator/extract \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://news.ycombinator.com/item?id=37000000",
    "enable_llm": true
  }'

{
  "kind": "discussion",
  "title": "Показати HN: Новий спосіб витягувати веб-сторінки",
  "author": "alice",
  "points": 173,
  "commentCount": 42,
  "body": "Привіт HN, ми створили самостійно хостовану альтернативу API аналізу Diffbot ..."
}

curl -X POST https://api.acedata.cloud/webextrator/extract \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.amazon.com/dp/B0BSHF7WHW",
    "expected_type": "product",
    "enable_llm": true
  }'

{
  "kind": "product",
  "name": "Apple 2023 MacBook Pro M2 Pro 14-дюймовий",
  "brand": "Apple",
  "price": 1799,
  "currency": "USD",
  "bullets": ["Чіп Apple M2 Pro з 10-ядерним ЦП", "..."],
  "specifications": [{ "name": "Розмір дисплея", "value": "14.2 дюйма" }, "..."]
}

import os, requests

API_KEY = os.environ["ACEDATA_API_KEY"]

resp = requests.post(
    "https://api.acedata.cloud/webextrator/extract",
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "url": "https://en.wikipedia.org/wiki/Diffbot",
        "expected_type": "article",
    },
    timeout=120,
)
resp.raise_for_status()
data = resp.json()["data"]

primary = (data.get("structured") or {}).get("schemaOrg", {}).get("primary")
print("contentType:", data["contentType"])
print("title:      ", data["title"])
print("byline:     ", data.get("byline"))
print("publishedAt:", data.get("publishedAt"))
if primary and primary["kind"] == "article":
    print("headline:    ", primary["headline"])
    print("dateModified:", primary.get("dateModified"))

const apiKey = process.env.ACEDATA_API_KEY;

const res = await fetch('https://api.acedata.cloud/webextrator/extract', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${apiKey}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    url: 'https://www.allrecipes.com/recipe/16354/easy-meatloaf/',
  }),
});
const { data } = await res.json();
const recipe = data?.structured?.schemaOrg?.primary;
console.log(recipe.name, recipe.cookTime, recipe.ingredients.length, 'інгредієнтів');