Web Page to Markdown Converter for LLMs

Convert any webpage into clean, structured Markdown optimized for LLMs and RAG pipelines. Stop wasting tokens on HTML boilerplate — get only the core content with metadata, ready for AI ingestion. Process hundreds of URLs in a single run with configurable concurrency.

Features

• Readability cleaning — strips ads, navigation, sidebars, and footers using Mozilla Readability
• Markdown formatting — converts article HTML to well-structured Markdown with ATX headings and fenced code blocks
• Bulk processing — convert hundreds of URLs in a single run
• Metadata extraction — captures page title, author byline, and excerpt alongside the Markdown content
• Redirect handling — follows HTTP redirects and reports the final URL
• Configurable concurrency — control parallel processing from 1 to 50 simultaneous requests
• Pay-per-event pricing — pay only for pages successfully converted

Input

Field	Type	Required	Default	Description
urls	array	Yes	—	List of webpage URLs to convert to Markdown
timeoutSeconds	integer	No	15	Maximum seconds to wait for each URL response
concurrency	integer	No	10	Number of URLs to process in parallel (1-50)

Input Example

{
  "urls": [
    "https://crawlee.dev",
    "https://docs.apify.com/academy/web-scraping-for-beginners"
  ],
  "timeoutSeconds": 15,
  "concurrency": 10
}

Output

Each URL produces one dataset item containing the converted Markdown and extracted metadata.

Key output fields:

• inputUrl (string) — the original URL provided
• finalUrl (string) — the URL after following redirects
• status (number) — HTTP status code
• pageTitle (string) — extracted article title
• markdown (string) — the full article content converted to Markdown
• excerpt (string) — short summary or description of the article
• byline (string) — author name if available
• error (string) — error message if conversion failed, otherwise null

Output Example

{
  "inputUrl": "https://crawlee.dev",
  "finalUrl": "https://crawlee.dev/",
  "status": 200,
  "pageTitle": "Crawlee - Build reliable crawlers. Fast.",
  "markdown": "# Crawlee\n\nBuild reliable crawlers. Fast.\n\nCrawlee is a web scraping and browser automation library...",
  "excerpt": "Crawlee is a web scraping and browser automation library for Node.js.",
  "byline": null,
  "error": null
}

Pricing

Event	Cost
Page Converted	Pay-per-event (see actor pricing page)

The actor respects the per-run max charge limit. Processing stops automatically when the spending cap is reached.

Use Cases

• RAG pipeline ingestion — convert documentation sites and knowledge bases into Markdown for vector database indexing
• LLM context preparation — clean web content for ChatGPT, Claude, or other LLM context windows without HTML noise
• Documentation migration — bulk-convert web pages to Markdown files for static site generators
• Content archiving — save readable article snapshots in a portable, version-control-friendly format
• AI training data — prepare clean text corpora from web sources for fine-tuning or evaluation

Related Actors

Actor	What it adds
Article Text Extractor for TTS & AI	Plain text output optimized for text-to-speech and summarization
PDF to Text Converter for AI & RAG	Extend your pipeline to extract text from PDF documents
YouTube Transcript Scraper for AI & RAG	Add video transcript extraction to your content pipeline