PDF & Webpage to Markdown for AI / RAG avatar

PDF & Webpage to Markdown for AI / RAG

Pricing

from $0.99 / 1,000 converted pages

Go to Apify Store
PDF & Webpage to Markdown for AI / RAG

PDF & Webpage to Markdown for AI / RAG

Convert web pages and PDF files to clean, LLM-ready Markdown. Strips nav, ads and footers, keeps headings, lists and tables. Optional RAG chunking, links, word counts. Pay only for successful URLs.

Pricing

from $0.99 / 1,000 converted pages

Rating

0.0

(0)

Developer

Czech Data Tools

Czech Data Tools

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

12 days ago

Last modified

Categories

Features

Limited permissions

Share

Turn any list of web pages and PDF files into clean, LLM-ready Markdown in one run. Paste URLs, get back Markdown with headings, lists and tables preserved, plus title, word count, token estimate, links and (optionally) ready-made RAG chunks.

No browser, no proxies, no setup – fast and cheap HTTP conversion that works on articles, docs, blogs, knowledge bases, reports, papers and other PDF documents.

What it does

  • 🌐 HTML → Markdown – removes navigation, headers, footers, sidebars, cookie bars, ads and share widgets, keeps the main content (headings, lists, tables, code blocks, links).
  • 📄 PDF → Markdown – extracts the text layer, rebuilds paragraphs, detects headings by font size, fixes hyphenated line breaks and removes repeated page headers/footers and page numbers.
  • ✂️ Chunking for RAG – optional heading-aware chunks of ~N tokens with overlap, each carrying its nearest heading. Drop straight into a vector DB (Pinecone, Qdrant, Weaviate, pgvector…).
  • 🔗 Links – absolute URLs + anchor text from the main content.
  • 🔒 Privacy by default – e-mail addresses and international phone numbers are redacted (can be turned off).
  • 🤝 Polite – respects robots.txt, one request at a time per website with a pause between requests.
  • 💸 You only pay for successful conversions – failed, blocked or empty URLs are not charged. They are listed in the key-value store record FAILED_URLS.

Input

FieldDescription
startUrlsURLs of web pages and/or PDFs (type is detected automatically)
extractMainContentKeep only the main content (default true)
chunkSizeChunk size in tokens for RAG, 0 = off (default)
chunkOverlapOverlap between chunks in tokens (default 50)
includeLinksAdd the list of links (default true)
includeImagesKeep image references in Markdown (default false)
redactContactInfoRedact e-mails and phone numbers (default true)
respectRobotsTxtSkip URLs disallowed by robots.txt (default true)
maxPdfSizeMb, maxItems, maxConcurrency, requestDelayMs, timeoutSecsLimits and politeness settings

Example:

{
"startUrls": [
{ "url": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation" },
{ "url": "https://arxiv.org/pdf/2005.11401" }
],
"chunkSize": 500,
"chunkOverlap": 50
}

Output

One dataset item per successfully converted URL:

{
"url": "https://arxiv.org/pdf/2005.11401",
"finalUrl": "https://arxiv.org/pdf/2005.11401",
"status": 200,
"contentType": "pdf",
"title": "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks",
"pageCount": 19,
"wordCount": 10450,
"tokenEstimate": 16200,
"markdown": "# Retrieval-Augmented Generation ...",
"links": [{ "url": "https://github.com/...", "text": null }],
"linkCount": 12,
"chunks": [{ "index": 0, "heading": "Abstract", "text": "...", "tokens": 498 }],
"responseTimeMs": 1830,
"fetchedAt": "2026-11-09T17:00:00.000Z"
}

Download as JSON, JSONL, CSV or Excel, or read it via the Apify API, Python/JS client, Make, Zapier, n8n or LangChain / LlamaIndex Apify loaders.

Pricing

Pay per event: $0.99 per 1,000 converted URLs + a tiny $0.003 start fee per run. Failed URLs are free.

Limitations

  • Pages that render their content only with JavaScript (single-page apps) may return little text – the actor does not run a browser.
  • Scanned PDFs without a text layer are skipped (no OCR).
  • Pages behind a login or paywall are not supported.

Use cases

  • Feed websites and PDF documentation into a RAG chatbot or vector database
  • Build LLM fine-tuning / evaluation corpora
  • Convert reports, papers and manuals to Markdown for Obsidian/Notion
  • Monitor content of pages for changes (combine with Apify schedules)

Questions or feature requests? Open an issue on the Actor's Issues tab.