Web Page to Markdown for LLM & RAG - Clean Article Text

Turn any web page into clean Markdown ready for ChatGPT, Claude, RAG pipelines and AI agents. Only the main content is kept (the article, the documentation page, the blog post): menus, cookie banners, ads, sidebars and footers are removed. Tables become Markdown tables, links are made absolute, and the text can be split into chunks for embeddings.

• Reader View quality. The main content is found with Mozilla Readability, the engine behind Firefox Reader View.
• Clean Markdown. Headings, lists, code blocks, tables (GitHub style) and links. Images are optional.
• Ready for RAG. Set chunkSize to get chunks that respect paragraph boundaries, alongside the full Markdown.
• Fast and cheap. One HTTP request per page, no browser: $1 per 1,000 pages.
• No result, no charge. Invalid URLs, pages that return an error, non-HTML files and internal addresses are not billed.

What can I use it for?

• RAG and chatbots: feed documentation, help-center articles or blog posts to a vector database.
• AI agents: give an agent the readable text of any page through the Apify MCP server (see below), at a fraction of the tokens of raw HTML.
• Content monitoring and research: archive articles as Markdown, summarize them, or compare versions.
• Migrations: move pages from an old website or CMS to Markdown files (Docusaurus, Hugo, Astro, Notion import).

Tip: to convert a whole website, get its URLs with Sitemap URL Extractor and pass them here. For PDF, Word, Excel or PowerPoint files, use PDF, Word, Excel & PowerPoint to Markdown.

Input

{
    "urls": ["https://en.wikipedia.org/wiki/Markdown", "https://blog.apify.com/what-is-web-scraping/"],
    "mainContentOnly": true,
    "keepLinks": true,
    "keepImages": false,
    "chunkSize": 1000
}

Output

One row per page. Example from a real run (Markdown and chunks shortened):

{
    "url": "https://en.wikipedia.org/wiki/Markdown",
    "finalUrl": "https://en.wikipedia.org/wiki/Markdown",
    "status": 200,
    "title": "Markdown",
    "description": "From Wikipedia, the free encyclopedia",
    "siteName": null,
    "lang": "en",
    "publishedTime": null,
    "usedMainContent": true,
    "wordCount": 6829,
    "markdown": "From Wikipedia, the free encyclopedia\n\n| Markdown |\n| --- |\n|  |\n| [Filename extensions](https://en.wikipedia.org/wiki/Filename_extension \"Filename extension\") | `.md`, `.markdown`...",
    "chunks": [{ "index": 0, "text": "From Wikipedia, the free encyclopedia ..." }],
    "error": null
}

Field	Meaning
title, description, siteName, lang, publishedTime	Page metadata (Open Graph and HTML tags)
usedMainContent	true when the main content was found; false means the whole page body was converted
markdown	The page as Markdown
chunks	Only when chunkSize > 0: pieces of at most chunkSize characters, split on paragraphs
wordCount	Words in the Markdown

Pricing

$0.001 per page converted ($1 per 1,000 pages) plus Apify's small run-start fee. No subscription, lower prices on higher Apify plans. Invalid URLs, pages returning an error, non-HTML files and internal addresses are free.

How it works, and its limits

Each page is fetched once over HTTP (redirects followed, at most 4 requests per second per site), and its scripts are never executed. Pages that build their text with JavaScript after loading (some single-page apps) may come out nearly empty: check wordCount.

Author names are not extracted as a separate field.

Use it from AI agents (MCP)

Add web-page-to-markdown to the Apify MCP server in your MCP client (Claude, Cursor, VS Code...).

Integrations

Apify API, schedules, webhooks, Make, Zapier, n8n, LangChain and LlamaIndex (Apify dataset loaders). Export as JSON, CSV, Excel or HTML.

Related tools

Same developer, same pay-per-result pricing, outputs that chain together:

• PDF, Word, Excel & PowerPoint to Markdown for RAG: PDF, Word, Excel and PowerPoint files to clean Markdown for LLMs.
• RSS & Atom Feed Reader: RSS and Atom feeds of any website as JSON.
• Sitemap URL Extractor: every URL of a website from its sitemaps.

FAQ

Can it log in or get past paywalls? No. Only public pages are read.

Something wrong or missing? Open an issue on the Issues tab.