URL to Markdown for RAG
Overview
URL to Markdown for RAG is a hosted Apify Actor that converts public pages, sitemaps and PDFs into Markdown with heading-aware chunks, token counts and metadata. It uses HTTP rather than a headless browser, so JavaScript-only content, login walls and heavily protected sites are outside its reliable scope. An Apify account is required and platform and usage charges apply. Check its current Pricing tab for the terms that apply to your plan.
Key Features
- Converts pages, sitemaps and PDFs to Markdown with heading-aware chunks
- Token counts, metadata and content hashes per page
- Honors robots.txt with include/exclude URL patterns
- Failed, blocked and empty pages are not charged
Best For
Developers building RAG pipelines who need web pages, sitemaps and PDFs as chunked Markdown.
Pros & Cons
Cons
- HTTP only, so JavaScript-rendered pages return empty content
- Login walls and heavily protected sites come back blocked
- Requires an Apify account and platform usage
Pulse Verdict
Editorial review by SEODataPulse · Editorial rating: 4/5 · Updated
This is an editorial assessment, not an average of customer ratings.
“A cheap, well-documented content-extraction Actor for static sites; not suited to JavaScript-heavy pages.”
Pricing
Pay per event: $1.20 per 1,000 pages on Free/Starter, lower on higher plans; Apify account required.
Pricing changes often — confirm current plans on the official site.