Pricing

$0.30 / 1,000 page converteds

Go to Apify Store

Website to Markdown for LLMs

Try for free

Crawl a site and export clean Markdown with token counts and chunks, ready for RAG.

Pricing

$0.30 / 1,000 page converteds

Rating

0.0

(0)

Developer

Ken Agland

Actor stats

Bookmarked

Total users

Monthly active users

a day ago

Last modified

What it does

Crawls pages starting from your URLs, staying on the same domain by default.
Strips boilerplate (scripts, styles, nav, header, footer, sidebars) and keeps the main content.
Converts the main content to clean Markdown.
Estimates token count for each page.
Optionally splits each page into token-sized chunks for retrieval-augmented generation.

No API key needed.

Example input

{
  "startUrls": [
    "https://example.com"
  ],
  "maxPages": 10,
  "maxDepth": 2,
  "sameDomainOnly": true,
  "includeChunks": true,
  "chunkSizeTokens": 800
}

Input

Field	Type	Default	Description
`startUrls`	array of strings	(required)	URLs to start crawling from.
`maxPages`	integer	10	Stop after this many pages in total.
`maxDepth`	integer	2	Link hops to follow from a start URL. Start URLs are depth 0.
`sameDomainOnly`	boolean	true	Only follow links on the same domain as their start URL.
`includeChunks`	boolean	false	Include the chunk array in each item.
`chunkSizeTokens`	integer	800	Target chunk size in estimated tokens.

Output

Each dataset item is one page:

{
  "url": "https://example.com/",
  "title": "Example Domain",
  "markdown": "# Example Domain\n\nThis domain is for use in illustrative examples...",
  "charCount": 210,
  "tokenEstimate": 53,
  "chunkCount": 1,
  "chunks": [
    "# Example Domain\n\nThis domain is for use in illustrative examples..."
  ]
}

The chunks field is present only when includeChunks is true.

Run summary (OUTPUT)

The run's default key-value store record OUTPUT holds an aggregate:

{
  "startUrls": [
    "https://example.com/"
  ],
  "pagesCrawled": 1,
  "totalChars": 210,
  "totalTokens": 53,
  "totalChunks": 1,
  "includeChunks": true,
  "chunkSizeTokens": 800,
  "maxPages": 10,
  "maxDepth": 2,
  "sameDomainOnly": true
}

How it works

The Actor fetches each page's HTML with plain fetch (retrying on 429 and 5xx with backoff, failing fast on other 4xx). It parses the HTML with cheerio, removes boilerplate, and picks the main content region. It converts that content to Markdown with turndown, falling back to a cheerio-based builder (headings, paragraphs, list items) if turndown cannot run. Tokens are estimated as characters divided by 4. Crawling uses an in-memory breadth-first queue with a small concurrency, staying on the same domain and honoring maxPages and maxDepth.

MIT licensed.

Website to Markdown for LLM & RAG — Crawl4AI URL to Clean

bikram07/web-to-markdown-crawl4ai

Convert any URL, sitemap, or whole website into clean, LLM-ready Markdown for RAG, vector databases, and AI agents. Hosted Crawl4AI in a real Chromium browser — renders JavaScript and SPAs, strips boilerplate, and exports JSON/CSV. Callable over MCP from Claude and Cursor.

Bikram

Website to Markdown for LLMs and RAG

rodrgds/website-to-markdown

Convert webpages into clean markdown for LLMs, RAG pipelines, AI datasets, archives, and content extraction. Simple pay-per-page pricing.

Rodrigo Dias

Website to Markdown – Clean LLM & RAG Content Extractor

dataquarry/website-to-markdown

Convert any public web page to clean, LLM-ready Markdown with metadata — by URL, a list of URLs, or a whole-site crawl. Strips nav/ads/boilerplate, keeps headings/lists/tables/code. Respects robots.txt. No API key.

Daniel Brenner

Website to Markdown - Clean LLM-Ready Content

ambitious_door/web-to-markdown

Convert any webpage into clean markdown stripped of navigation, ads, and boilerplate. Perfect for RAG pipelines, LLM context, and content extraction. Token counts included.

C. K.

Website to Markdown for LLM and RAG

jeweled_jockstrap/my-actor-3

Convert any URL to clean Markdown text for AI applications. Strips HTML extracts content. For LLM training RAG pipelines and vector databases. Free Firecrawl alternative.

Juan Triviño

Website To Markdown

smart_api/website-to-markdown

Convert any webpage into clean, LLM-ready Markdown in seconds — perfect for AI training data, RAG pipelines, and content archiving.

SmartApi

5.0

(1)

Website Content to Markdown for LLM Training

easyapi/website-content-to-markdown-for-llm-training

🚀 Transform web content into clean, LLM-ready Markdown! 📘 Scrape multiple pages, extract main content, and convert to Markdown format. Perfect for AI researchers, data scientists, and LLM developers. Fast, efficient, and customizable. Supercharge your AI training data today! 🌐📝🧠

EasyApi

325

5.0

(2)

Website to Markdown Crawler for LLM & RAG

logiover/website-text-markdown-crawler

Crawl any website to clean Markdown and plain text for LLM training and RAG. HTML to Markdown, no API or login. Export website text to CSV or JSON.

Logiover

RAG Website Crawler - Markdown Chunks for LLMs & MCP

themineworks/rag-crawler

Crawl any website into clean, pre-chunked Markdown with per-chunk token counts for RAG pipelines, vector DBs (Pinecone, Qdrant) and LLM context. MCP-native for Claude & ChatGPT. SPA support via Playwright. Pay only for pages that crawl. A Firecrawl alternative.

The Mine Works

Website to Markdown for RAG & LLMs

hereditary_model/website-to-markdown

Crawls a website and converts every page into clean Markdown, ready for RAG pipelines, vector databases, and LLM context. Pay per page converted.

Aaron Marxsen

Simple Website Scrapper (markdown format)

manojaditya64/simple-website-scrapper-markdown-format

A simple website scrapper that scrapes websites and converts it into markdown format which is easy to use with LLM. You can feed markdown data to LLM for easy analysis.