Pricing

Pay per usage

News Article & RSS Crawler — Clean Text for RAG

Fetch news from RSS feeds and Google News search, then extract clean article text and metadata. Perfect for RAG pipelines, newsletters, trend monitoring, and AI agents. Use via Apify Console/API or connect as an MCP server for Claude, Cursor, and other AI agents.

Pricing

Pay per usage

Rating

0.0

(0)

Developer

Aaron Hampton

Actor stats

Bookmarked

Total users

Monthly active users

a day ago

Last modified

News Article & RSS Crawler

Fetch news from RSS/Atom feeds and Google News search, then extract clean article text with metadata. Works as a normal Apify Actor or as an MCP server for Claude, Cursor, and other AI agents.

Features

Google News search via Google's public RSS endpoint
Direct RSS/Atom feeds — any standard feed
Clean article extraction — strips nav, ads, footers, and boilerplate, returning readable body text
MCP Server — search_news, fetch_feed, get_article_text tools
Pay-per-event pricing — first 20 articles free per run/tool call

MCP Tools

Tool	Description
`search_news(query, maxResults?, includeFullText?, geo?)`	Search Google News and extract articles
`fetch_feed(feedUrls, maxItems?, includeFullText?)`	Fetch articles from RSS/Atom feeds
`get_article_text(url)`	Extract clean text from a single article URL

Normal Mode Input

{
    "query": "artificial intelligence",
    "maxArticles": 20,
    "includeFullText": true,
    "geo": "US"
}

Or pass direct feeds instead of a query:

{
    "feedUrls": ["https://feeds.bbci.co.uk/news/rss.xml"],
    "maxArticles": 10,
    "includeFullText": true
}

Output

{
    "query": "artificial intelligence",
    "feedUrls": [],
    "totalResults": 20,
    "errors": [],
    "articles": [
        {
            "title": "AI Agents Reach New Milestone",
            "url": "https://example.com/ai-agents",
            "resolvedUrl": "https://example.com/ai-agents",
            "source": "Example Source",
            "publishedAt": "2026-07-04T12:00:00.000Z",
            "summary": "...",
            "text": "Clean, extracted article body text...",
            "wordCount": 842,
            "fetchedAt": "2026-07-04T19:00:00.000Z"
        }
    ],
    "fetchedAt": "2026-07-04T19:00:00.000Z"
}

Pricing (Pay-Per-Event)

Event	Price	Description
Actor start	$0.00005	Billed once per run
Article fetched	$0.005	Per article successfully extracted (first 20 free per run/tool call)
MCP tool call	$0.005	Per MCP tool invocation

Technical Approach

The Actor uses got-scraping with optional Apify proxy rotation for HTTP requests. RSS/Atom XML is parsed with fast-xml-parser. Article text is extracted with a Cheerio heuristic that removes scripts, navigation, sidebars, ads, and footers, then picks the richest <article>, <main>, or content-class container.

Development

npm install        # Install dependencies
npm run build      # Compile TypeScript
npm test           # Run tests
npm run start:dev  # Run locally (development mode)

License

ISC

News & Article Extractor

automation-lab/news-article-extractor

Auto-discover news/blog articles and extract clean text plus Markdown for LLM/RAG corpora. Uses RSS, sitemaps, and Readability; outputs metadata, counts, and token estimates.

Stas Persiianenko

AI News Content Scraper

ilborso/ai-news-content-crawler

This Apify actor get back all plain text news for your Agentic AI. Keep update your AI Agent with latest news!

Fabio Borsotti

5.0

(1)

Google News Scraper Comprehensive

scrapeio/google-news-scraper

Enter a keyword and collect up to 2,000 deduplicated Google News articles—headlines, publisher URLs, dates, sources, and snippets—from the public RSS layer. Excel‑ready CSV (UTF‑8 BOM, quoted fields) plus JSON. Perfect for brand monitoring, PR measurement, and news datasets. No Google Cloud API key.

Shop Intel

5.0

(4)

Article/News Extractor

tropical_prune/article-news-extractor

CAPABILITIES: extract_article, extract_metadata, detect_language, clean_text, batch_urls. INPUT: URLs (single or array) of articles/news pages. OUTPUT: structured JSON with title, author, date, content, language, word_count. FORMATS: json, markdown, text. PRICING: PPE $0.001/article.

Bado

5.0

(1)

Google News Scraper — Headlines, Sources, URLs

scrapeify/google-news-scraper

Turn any Google News query into a deduplicated dataset of up to 2,000 articles: titles, sources, dates, RSS links, resolved publisher URLs, clean snippets. Multiple RSS time-window passes for depth beyond single-feed limits. Excel-ready CSV. No API key. Not affiliated with Google.

Scrapeify

📰 Google News Scraper - Real Publisher URLs

renzomacar/google-news-scraper

Renzo Madueno

Global News Archive API - Rise of the Phoenix

thescrapelab/Apify-The-Rise-of-the-Phoenix

Search archived global news articles by country, publisher, and date. Export clean article text and metadata for media monitoring, PR research, market intelligence, RAG, and LLM workflows.

Inus Grobler

5.0

(1)

📰 AI News Intelligence Feed — Real-Time News for AI Agents

inexhaustible_glass/ai-news-intelligence-feed

Real-time, structured, LLM-ready news for AI agents & RAG. Google News (aggregates Reuters, AP, BBC, Bloomberg & 1000s of publishers) + topics + BBC. Decodes Google's redirects to REAL publisher URLs; optional clean full text, sentiment & de-dup. No API key. MCP tool for ChatGPT/Claude.

Hitman studio

📰 Extract Google News Articles — AI & RAG Ready

muhammadafzal/google-news-scraper

Extract Google News articles by keyword, topic, or URL with full-text extraction for AI/RAG pipelines. Get headlines, sources, snippets, images, authors, and clean article text in structured JSON. Export scraped data, run the scraper via API, or integrate with other tools.

Muhammad Afzal

Google News Scraper & RSS URL Extractor

taroyamada/google-news-scraper

Google News scraper that queries the public RSS feed for fresh news headlines and article URLs. Localized scoping, dedupe across queries, and deterministic article URL extraction for downstream NLP.

naoki anzai

$RSS \ XML Scraper & Smart Sitemap avatar$

RSS \ XML Scraper & Smart Sitemap

saregaa/rss-xml-scraper

Scrape any sitemap or RSS feed and extract full article text, titles, and images. Supports nested sitemaps, Atom feeds, proxy rotation, and browser fingerprint spoofing to bypass blocks. Perfect for news monitoring, SEO audits, and AI dataset collection.