News to Markdown

Convert news and announcements into RAG-ready Markdown chunks. Built for PR, comms, media-monitoring teams and AI agents.

📊 Sample Output

url	title	chunkIndex	totalChunks	markdown
https://www.apify.com/change-log	Changelog	0	1	Sep 3, 2026 ## Create an Actor with a Git repo in a few clicks New Co…

Real rows from run 7azUcqmrGaAUJmxoT on build 0.0.4 (2026-09-25), unedited apart from masked emails/phones and shortened long text; fields the source does not publish are empty.

🔧 Input reference

Field	Type	Default	What it does
urls	array	["https://www.apify.com/change-log"]	Direct URLs of press releases / news articles to convert.
rssFeeds	array	[]	Feed URLs; latest items are fetched and converted.
maxPerFeed	integer	10	How many latest items to take from each feed.
chunkWords	integer	800	Approx words per Markdown chunk for RAG.

🧾 JSON sample record

One real record from run 7azUcqmrGaAUJmxoT (emails/phones masked, long text shortened):

{
  "url": "https://www.apify.com/change-log",
  "title": "Changelog",
  "chunkIndex": 0,
  "totalChunks": 1,
  "markdown": "Sep 3, 2026 ## Create an Actor with a Git repo in a few clicks New Console Actor When you create a new Actor in Apify Console or with the Apify CLI, you can now pick GitHub, GitLab, or Bitbucket, and Apify sets up the whole Git workflow for you. ### Why it matters * **Builds on your first push.** The build pipeline is configured for you. You push a commit, and Apify builds the Actor. * **Your own repository from day one.** From the start, you get pull requests, reviews, CI, and everything else you already do with Git. * **No manual wiring.** The old flow meant creating the repository yourself, adding the template code, and pasting the Git URL into the Actor's **Source** tab. Private repositories also needed the SSH URL and a deployment key. All of that now happens automatically. * **One flow in Apify Console and the Apify CLI.** Whether you start in the browser or the terminal, you end up in the same place: code in your repo, builds running on push. ### How it works * In Apify Console, click **Develop new**. The flow walks you through creating an Actor: + **What do you want to build?** A web scraper, an AI agent, an API and data pipeline, or browser automation. + **Which language do you prefer?** TypeScript, JavaScript, or Python. + **Here's your best match.** Templates matched to your answers, so you start from working code instead of browsing a template gallery. + **Where do you want to host your code?** This is the new part. * Pick Git and choose GitHub, GitLab, or Bitbucket. You authorize the provider through OAuth, select the account or organization the repository should live under, and Apify does the rest: creates the repository, pushes the Actor template code, and configures the build. The new repository is private. You can make it public later in your provider's settings. * The `apify create` command in the Apify CLI walks you through the same choices and gives the same result: a repository under your account with the template code pushed and builds configured. * If you don't want Git, Create without Git is still there: Clone locally or Host on Apify. ### Learn more The new feature is live for everyone, on every plan. Open actor.new , and see for yourself. Or get the latest version of the Apify CLI and run `apify create` in your terminal. Read more about the new flow in the blog post. Patrik Braborec Product Manager"
}

💰 Pricing

Event	Price (USD)	When it is charged
Actor Start (apify-actor-start)	$0.005	Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).
Markdown chunk (document-record)	$0.04	Charged per Markdown chunk.

Pay-per-event: you pay only for what the run delivers. A run that delivers nothing bills no result events (only the actor-start event, when the actor defines one). Example: a run that delivers 100 results costs 100 × $0.04 = $4.00 plus the start fee.

🔗 Related Actors

More from the NexGenData Press releases & news family:

• EIN Presswire Press Releases Scraper — Media API
• GlobeNewswire Press Releases Scraper — Media API
• Google News Scraper — Breaking News Feed API
• PR Newswire Asia Press Releases — Media API
• PRWeb Press Releases Scraper — Media Monitoring API

2 more in this family on the NexGenData Store page.

⏰ Run this as a news corpus (recommended)

Every IP registry actor is a monitoring subscription, not a one-shot lookup. Schedule a weekly sweep and catch new filings as they land:

{
  "query": "company or keyword",
  "limit": 100
}

Weekly cron (0 8 * * 1) turns this into an always-on news corpus.

📊 What you get

Clean JSON, one record per chunk (full output has 6 fields):

• accession — Accession
• company — Company
• markdown — Markdown
• source_url — Source url
• chunk_index — Chunk index
• form — Form

Pricing: $0.04 per chunk (Pay-Per-Event) — about 25 chunks per $1.

🤖 Use with AI agents

Point Claude, the OpenAI Agents SDK, an n8n flow or any MCP-aware client at it and run news and announcements as RAG-ready chunks on demand.

Sample agent prompt:

Convert a news feed into Markdown chunks I can embed for retrieval.

Agentic payments (x402): Supports agentic payment via x402 — agents can call this actor with USDC, no API key required.

🔗 Related news & media actors

Full media-monitoring stack — monitor every major wire: PR Newswire, Business Wire, GlobeNewswire, PRWeb, EIN Presswire, Brand Mention Monitor

News agent front door: News MCP

---

Data from public news, press-wire and media sources.