🌐 Wikipedia Topic Summary & Knowledge Graph Extractor

Extract clean structured Wikipedia article summaries, Wikidata descriptions, coordinates, high-resolution thumbnail images, and page revisions for AI RAG pipelines and educational applications.

---

🥊 Why This Actor Beats the Competition

Feature	🌐 Wikipedia Knowledge Extractor	HTML Web Scrapers	MediaWiki Action API
Speed	Sub-second response (< 500ms)	5–15 seconds (bloated DOM)	Complex nested XML/JSON
Pricing	Pay-Per-Result ($0.80 / 1k articles)	Costly compute hours	Rate-limited infrastructure
Clean Output	Pure clean text summary + description	Cluttered wiki tables & banners	Requires multiple API hops
Multi-Language	Supports all major Wikimedia editions	Fails on RTL & encoding	Inconsistent schema formats
AI / RAG Ready	Formatted for direct vector embedding	Unclean tags & scripts	High token overhead

---

🛠️ Step-by-Step: How to Use

Method 1: Apify Console (No-Code GUI)

1. Enter a list of topics or Wikipedia URLs (e.g. Artificial intelligence, Quantum computing, Sam Altman).
2. Select your desired language (default: en).
3. Click Start to run and export clean JSON or CSV.

Method 2: Python SDK

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run_input = {
    "topics": ["Artificial intelligence", "Albert Einstein"],
    "language": "en"
}

run = client.actor("litezero/wikipedia-structured-data-scraper").call(run_input=run_input)
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(f"{item['title']} ({item['description']}):\n{item['extract'][:120]}...\n")

Method 3: Node.js SDK

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('litezero/wikipedia-structured-data-scraper').call({
    topics: ['SpaceX', 'DeepMind'],
    language: 'en',
});

const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

Method 4: cURL / REST API

curl --request POST \
  --url "https://api.apify.com/v2/acts/litezero~wikipedia-structured-data-scraper/runs?token=YOUR_APIFY_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{"topics": ["Nvidia", "OpenAI"], "language": "en"}'

---

📥 Input Parameters

Parameter	Type	Default	Description
topics	Array	["Artificial intelligence", ...]	List of article topic names or Wikipedia URLs.
language	Select	"en"	Language edition (en, es, de, fr, ja, it, zh).
includeHtml	Boolean	false	Include HTML snippet of the extract.

---

📤 Sample Output JSON

{
  "title": "Artificial intelligence",
  "displayTitle": "Artificial intelligence",
  "pageId": 1164,
  "description": "Intelligence of machines or software",
  "extract": "Artificial intelligence (AI) is the intelligence of machines or software, as opposed to the intelligence of living beings, primarily of humans...",
  "thumbnailUrl": "https://upload.wikimedia.org/wikipedia/commons/thumb/0/04/ChatGPT_logo.svg/320px-ChatGPT_logo.svg.png",
  "originalImageUrl": "https://upload.wikimedia.org/wikipedia/commons/0/04/ChatGPT_logo.svg",
  "coordinates": null,
  "desktopUrl": "https://en.wikipedia.org/wiki/Artificial_intelligence",
  "mobileUrl": "https://en.m.wikipedia.org/wiki/Artificial_intelligence",
  "language": "en",
  "timestamp": "2026-10-01T12:00:00Z",
  "revision": "1249821894",
  "scrapedAt": "2026-10-02T16:45:00.000Z"
}

---

💡 Top Commercial Use Cases

1. Entity Resolution & Knowledge Graph Augmentation: Enrich internal databases with authoritative Wikipedia entity summaries and images.
2. AI RAG Context Ingestion: Provide fast, zero-latency background knowledge to LLM conversational agents.
3. Automated Content Curation: Generate instant biographical and conceptual summaries for educational apps and media platforms.