Gaming & Esports News Intelligence Pipeline

This Actor is a specialized scraper and analyzer for gaming and esports news. It takes RSS feeds from major outlets, extracts article content, and uses an LLM to generate structured intelligence like summaries, sentiment, and tags. You don't need to provide or manage any external API keys.

Overview

Instead of just fetching headlines and links from RSS feeds, this tool processes the full article content. It scrapes directly from the source URL. If direct scraping fails, it automatically falls back to extracting snippets via the Brave Search API. The extracted text is then sent through a Large Language Model to produce a structured analysis. This turns raw news into a clean dataset suitable for dashboards, feeds, or analysis.

Key Features

• No API Key Management: The Actor handles all necessary API calls (LLM via OpenRouter, search via Brave). You pay per successful analysis event, which covers these costs.
• AI-Powered Structuring: Each article is analyzed to generate:
  • A concise, two-sentence summary.
  • A "Hype" sentiment rating (e.g., High Hype, Moderate Interest).
  • A thematic category (e.g., Esports Results, Game Review).
  • A list of key entities like specific games, teams, or studios.
• Resilient Content Extraction: Uses a "scrape-first" engine with automatic fallback to paid search extraction to maximize success rate.
• Structured JSON Output: Delivers clean, consistent data ready for integration.

How to Use

The Actor is designed for a simple, plug-and-play workflow:

1. Configure Input: In the Actor input, select a predefined news source (like ign-articles or esportsinsider) or choose all to aggregate from major outlets. You can also provide a custom RSS feed URL.
2. Set Limits: Define the maxArticles to analyze to control the scope and cost of the run.
3. Run: Start the Actor. It will sequentially fetch the RSS feed, extract content for each article, and run the AI analysis.
4. Test Mode: You can enable Run Test Mode in the input settings. This generates dummy output data, allowing you to test your downstream integrations without incurring any usage costs.

Input & Output

Input Configuration

The input requires no authentication keys. Key parameters are:
* newsSource: Dropdown selection of preset gaming sites or a custom RSS URL.
* maxArticles: Integer to limit the number of articles processed.
* region / time: Optional parameters used if the fallback search method is triggered.

Output Data

Results are stored in the Apify default dataset, exportable as JSON, CSV, etc. The output for each article includes:

{
  "title": "Article Headline",
  "aiSummary": "A dense two-sentence summary.",
  "sentiment": "High Hype",
  "category": "New Release",
  "keyEntities": ["Game Name", "Studio Name"],
  "sourceFeed": "IGN",
  "extractionMethod": "direct" // or "search_fallback"
}

Pricing

Costs are based on a Pay-per-event model:
* Usage Cost: A small fee is charged per successful AI analysis event. You are not charged for articles that fail to be processed.
* Platform Cost: Standard Apify platform compute fees apply for the duration of the Actor run.

This model covers the underlying costs of the LLM and Search APIs that the Actor uses on your behalf.