Website to Markdown — Clean Markdown for LLMs & RAG

from $44.00 / 1,000 pages converted (per 5)s

Go to Apify Store

Website to Markdown — Clean Markdown for LLMs & RAG

noniner/website-to-markdown

Try for free

Copy setup promptCopied

Turn any web page into clean, LLM/RAG-ready Markdown. Strips nav/ads/boilerplate, optional same-domain crawl and overlap-aware chunking for vector databases. Keyless and fast.

from $44.00 / 1,000 pages converted (per 5)s

README

Input

Pricing

API

Issues

Turn any web page into clean, LLM/RAG-ready Markdown. Point it at one URL or a whole docs site: it strips navigation, ads and boilerplate, keeps the main content, and returns tidy Markdown — optionally split into overlap-aware chunks ready to embed into a vector database.

Deterministic and keyless — no OpenAI key, no per-token cost. Fast, cheap, and built for people and AI agents (available over MCP).

A clean Firecrawl / Jina Reader alternative on Apify: pay-per-use, no subscription.

Boilerplate removal — drops nav, header, footer, aside, forms, scripts, ads and common menu/sidebar classes, then picks the richest

<main>/<article> container.

Clean Markdown — turndown + GFM, so tables, code blocks and lists survive intact (ATX headings, fenced code).

Same-domain crawl — set a crawl depth to walk a whole docs site; filter with include/exclude URL globs.

RAG chunking — optional: split each page into ~N-token chunks with overlap so vector-DB retrieval keeps context across chunk edges.

Token + word counts — every record carries a rough token estimate for budgeting.

Input

FieldTypeDefaultNotesstartUrlsstring[]—Seed URLs (required).maxPagesinteger50Hard cap 200. One charge per page converted.maxDepthinteger0Same-domain crawl depth. 0 = only the seeds.maxConcurrencyinteger5Pages fetched/converted in parallel.chunkForRagbooleanfalseEmit chunk records instead of page records.chunkSizeinteger512Target chunk size in tokens.chunkOverlapinteger50Token overlap between chunks (< chunkSize).includeUrlGlobsstring[]—Only follow matching links when crawling.excludeUrlGlobsstring[]—Never follow matching links (wins over include). Output

One dataset record per page (or per chunk when chunkForRag is on):

{

"url": "https://quotes.toscrape.com/",

"title": "Quotes to Scrape",

"markdown": "# Quotes to Scrape\n\n> "The world as we have created it..."\n...",

"wordCount": 412,

"tokenEstimate": 540

}

Chunk records add chunkIndex and drop wordCount.

A typical article arrives wrapped in nav bars, cookie banners, share widgets and footers. You get only the content:

In: one blog/docs URL (full HTML, ~180 KB of markup)

RAG best practices

Retrieval-augmented generation works best when your chunks keep their context.

1. Clean your source

Strip boilerplate before you embed — nav links and cookie banners poison retrieval.

Flip on chunkForRag and the same page comes back as embed-ready chunks with overlap and a token estimate per chunk — drop them straight into a vector DB.

Pay-per-event: $0.10 per 5 pages converted (≈ $0.02 / page). No subscription, no token fees — you only pay for pages actually converted.

One of 90+ no-code data tools — many chain directly into each other. Browse them all

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

Turn docs sites, help centers, blogs, and websites into clean markdown, text, or HTML for RAG, AI knowledge bases, and internal search. Crawl from start URLs or sitemaps and keep the crawl in scope.

Turn any website, documentation site or help centre into a retrieval-ready knowledge corpus for RAG and AI search. Clean Markdown plus chunks, change detection, deduplication, retrieval scoring, version awareness and a full corpus audit, in one run.

An Apify Actor that takes a URL as input and returns the content of the page in Markdown format.

Scrapes technical documentation sites (Docusaurus, GitBook, MkDocs, ReadTheDocs) and converts them to clean, structured Markdown for RAG pipelines, LLM training, and AI assistants. Automatically detects documentation framework and removes navigation elements.

SW

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.

Bulk convert any website URLs to clean Markdown for AI & LLMs. Universal scraper that removes ads, scripts, and clutter. Optimized for RAG, ChatGPT, Claude, and LangChain. Fast, async, and API-ready.

WT

Web to LLM Spanish — RAG-ready content extractor

fanciful_geode/web-to-llm-es

Crawls Spanish-language websites and extracts clean markdown content optimized for LLM RAG pipelines. Handles Spanish character encoding, removes boilerplate, and outputs structured chunks ready for embedding.

The /llms.txt Generator 🕸️📄 extracts website content to create an llms.txt file for AI apps 🤖✨ like LLM fine-tuning and indexing. Output is available 📥 in the Key-Value Store for easy download and integration into workflows. 🚀

sync-network/website-main-content-extractor

Extract the main content from any webpage — clean text without navigation, ads, footers, or boilerplate. Perfect for AI/LLM pipelines, RAG systems, content analysis, and data extraction. Returns title, description, author, publish date, and clean body text.