Article Text Extractor: RSS and URLs to Clean Markdown for RAG

Turn news articles and blog posts into clean Markdown or plain text, from a list of URLs or straight from RSS and Atom feeds, ready to feed a RAG pipeline, a search index or an LLM. It follows robots.txt and keeps headings, lists and tables.

What you get

Field	Meaning
url	The article address
title	Article title
date	Publication date when the page gives one
sitename	Site name
language	Detected language when available
word_count	Words in the extracted text
text	Clean text or Markdown (headings, lists, tables)

Real example (13 Oct 2026, text shortened):

{"url": "https://www.iana.org/help/example-domains", "title": "Example Domains", "date": "2026-09-27", "sitename": "iana.org", "language": null, "word_count": 118, "text": "# Example Domains\n\nA number of domains such as `example.com` and `example.org` are maintained for documentation purposes..."}

Authors' names are deliberately not extracted.

How to use it in 3 steps

1. Add article URLs (up to 100) and/or RSS or Atom feed URLs (up to 10). From each feed the latest maxPerFeed entries (1 to 50) are extracted too.
2. Set format to markdown (best for RAG and LLMs) or txt.
3. Run it and read the clean text from the dataset.

Pricing

$3 per 1,000 articles ($0.003 each). Example: a feed of 50 posts = $0.15. Blocked, empty or failed pages are free.

Integrations

• Apify API and clients: start the Actor from any language with the Apify API (or the JavaScript and Python clients) and read the dataset when the run ends.
• Make, n8n and Zapier: use the official Apify modules, pick kadro/article-text-extractor, pass the input as JSON and map the dataset rows to your next step.
• Google Sheets: send the dataset to a sheet with the Apify integration or export it as CSV or Excel from the Console.
• MCP (Claude, Cursor and other AI agents): add the Apify MCP server https://mcp.apify.com/?actors=kadro/article-text-extractor and ask, for example: "Take the latest 20 posts from this blog's RSS feed and give me each one as Markdown."

FAQ

There are free article extractors. Why use this one? This Actor expands RSS and Atom feeds for you, outputs Markdown that keeps headings, lists and tables, respects robots.txt with a clear user agent, and only charges for articles that actually produced text.

Does it run JavaScript? No. Pages that need JavaScript to show their content return no text and are free.

Which pages are skipped? Pages disallowed by robots.txt, non-public addresses, and pages without article text.

Can I reuse the text? Copyright belongs to each site. Use the text according to their terms.

Limitations

• No JavaScript rendering: single-page apps that render in the browser return nothing.
• Pages are fetched one per second, with a 5 MB limit per page; max 100 URLs and 10 feeds per run.
• Author names are deliberately not extracted.
• No chunking or embeddings yet: you get one Markdown text per article.
• Only public http(s) addresses are allowed.

Other Kadro tools

• Website to Markdown + llms.txt
• PDF Text Extractor
• Podcast Transcriber
• Bulk OCR

Credits and license

Uses the open-source trafilatura library (Apache-2.0). Clear user agent (KadroBot).

Found it useful? Please leave a review ⭐ — it helps a lot. Bugs or feature ideas: open an issue, I answer within 24 h.