URL List to Markdown Bundle for LLMs avatar

URL List to Markdown Bundle for LLMs

Pricing

$5.00 / 1,000 results

Go to Apify Store
URL List to Markdown Bundle for LLMs

URL List to Markdown Bundle for LLMs

Paste a list of URLs (or a sitemap URL you own) and get clean Markdown per page plus one combined llms-full.txt file, ready for RAG pipelines and LLM context.

Pricing

$5.00 / 1,000 results

Rating

0.0

(0)

Developer

James Barnes

James Barnes

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

11 hours ago

Last modified

Categories

Share

Paste a list of URLs (or a sitemap URL) and get clean Markdown for each page, plus one combined llms-full.txt file ready for RAG pipelines and LLM context windows.

What it does

  • Fetches each page directly over HTTP (no browser, so JavaScript-rendered content is not executed).
  • Strips scripts, navigation, footers and other boilerplate, then converts headings, lists, links, tables, code blocks and images to Markdown.
  • Pushes one dataset item per page.
  • Saves all pages concatenated into llms-full.txt in the run's key-value store.
  • Identifies itself with a clear User-Agent and respects robots.txt by default.

Input

  • urls: list of page URLs.
  • sitemapUrl: optional sitemap (index files supported, two levels deep).
  • maxPages: 1-1000 (default 50).
  • mainContentOnly: prefer <main>/<article> (default true).
  • respectRobotsTxt: default true.
  • delaySeconds: pause between requests (default 1).

Output example

{
"url": "https://example.com/",
"finalUrl": "https://example.com/",
"title": "Example Domain",
"markdown": "# Example Domain\n\nThis domain is for use in illustrative examples...",
"wordCount": 28
}

Pricing

$0.005 per result (one dataset item per converted page). Skipped or failed pages are not charged.

Limits

  • Static HTML only; pages that require JavaScript to render content may come back empty.
  • Pages over 5 MB, non-HTML content and pages blocked by robots.txt are skipped.
  • Up to 1000 pages per run. Only fetch content you are allowed to use, and follow each site's terms.