All APIs & tools Nº 020

API · n8n node

Article Extractor to Clean Text and Markdown

Any URL or PDF link to clean article text and Markdown with title, author, date and language. Honest status on every page.

Who it's for LLM/RAG and vector-database pipelines, read-later apps, newsletter digests, research and SEO content audits

See it work

A real example from the listing: what you send, and what comes back. No live call, no key, no cost.

In

GET /v1/extract?url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FOpen_data&output=markdown&max_chars=500

Out

{
  "url": "https://en.wikipedia.org/wiki/Open_data",
  "status": "ok",
  "title": "Open data - Wikipedia",
  "language": "en",
  "published_at": "2006-10-30T00:00:00",
  "content_markdown": "**Open data** are data that are openly accessible, exploitable, editable and shareable by anyone for any purpose. …",
  "word_count": 6345,
  "warnings": [
    "content_truncated"
  ]
}

Pricing

  • BASIC $0 · 100/mo · 1 req/s
  • PRO $9.99 · 5,000
  • ULTRA $29.99 · 25,000
  • MEGA $79 · 100,000
  • overage $0.002/req
  • The plans are the same on RapidAPI and api.market (BASIC is called FREE there). BASIC has a hard limit; paid plans are soft limits with overage.
  • Prices in US dollars, as on the store. Fuentio's own plans are in euros.

Get it

Open on RapidAPI (opens in a new tab) ↗api.market: in reviewn8n node on npm (opens in a new tab) ↗

Install the n8n node

npm install n8n-nodes-compasslab-article-extractor

Or in n8n: Settings → Community nodes, then the package name.