Convert PDF, Word & Excel URLs to Markdown + RAG Chunks

What it does: turns public document links into clean Markdown and ready-to-embed RAG chunks, by Print & Plan UK. You give it: a list of document URLs (PDF, DOCX, PPTX, XLSX, HTML, CSV, EPUB), plus optional chunk size and overlap. You get: one dataset item per document with the full Markdown, chunks that keep their heading path and PDF page number, and token estimates. Cost per run: $0.004 per document (first 10 pages included) plus $0.0003 per extra page, so 100 ten-page PDFs cost $0.40; failed downloads are free. Example inputs: https://arxiv.org/pdf/1706.03762, https://en.wikipedia.org/wiki/Markdown, https://calibre-ebook.com/downloads/demos/demo.docx.

Why use it?

• One Actor for every format: PDF, DOCX, PPTX, XLSX/XLS, HTML, CSV, JSON, XML, TXT. Most Store alternatives handle PDF only.
• RAG-ready chunks: paragraph-aware chunks with configurable size and overlap. Each chunk keeps its heading path (e.g. Lists > Multi-level Lists) and its PDF page number, so you can cite sources.
• Good PDF text: uses PDFium, which keeps word spacing on LaTeX and academic PDFs that trip up other extractors.
• Token estimates for every document and chunk, so you can plan LLM costs.
• Fair pricing: you pay per converted document. Failed downloads and conversions are free.

How to use

1. Paste one or more document URLs into Document URLs.
2. Optionally adjust chunk size and overlap (defaults: 2,000 characters, roughly 500 tokens, with 200 characters of overlap).
3. Click Start. Each document becomes one dataset item. Export as JSON, CSV or Excel, or use the API, Make, Zapier, n8n or LangChain.

Input example

{
  "urls": [
    "https://arxiv.org/pdf/1706.03762",
    "https://calibre-ebook.com/downloads/demos/demo.docx",
    "https://filesamples.com/samples/document/xlsx/sample1.xlsx"
  ],
  "includeMarkdown": true,
  "includeChunks": true,
  "chunkSize": 2000,
  "chunkOverlap": 200
}

Output example (trimmed)

{
  "url": "https://arxiv.org/pdf/1706.03762",
  "httpStatus": 200,
  "fileType": "pdf",
  "sizeBytes": 2215244,
  "pageCount": 15,
  "charCount": 39862,
  "approxTokens": 9966,
  "markdown": "<!-- page 1 -->\nProvided proper attribution is provided, Google hereby grants permission to …",
  "chunkCount": 27,
  "chunks": [
    {"index": 0, "page": 1, "headingPath": "", "charCount": 1740, "approxTokens": 435, "text": "Provided proper attribution is provided, …"}
  ]
}

A DOCX document produces a headingPath for each chunk, for example "Lists > Multi-level Lists". Spreadsheets become Markdown tables, one section per sheet.

Pricing (pay per event)

Event	Price
Document converted (includes the first 10 pages)	$0.004
Each extra page after 10 (PDF/PPTX)	$0.0003

Examples: a 15-page PDF costs $0.0055. 1,000 short DOCX or HTML files cost $4. Downloads that fail, files that are too large, and unsupported files are not charged. Set a maximum cost per run in the run options and the Actor stops cleanly at that limit.

FAQ

Does it OCR scanned PDFs? No. Image-only PDFs return little or no text, and the item has a warning field. OCR may be added later.

What's the file size limit? 50 MB by default (maxFileSizeMb, up to 200).

Can it read private files? Only URLs the Actor can download anonymously. It never logs in. For files on Google Drive, Dropbox and similar services, use a public direct-download link. Private network addresses are blocked.

Is the output good for embeddings? Yes. Chunks split on paragraph and line boundaries, start their overlap on a word boundary, and never exceed chunkSize.

Legal

Only convert documents you have the right to process. The Actor fetches each URL once, exactly as a browser download would, and does not bypass logins or paywalls.

Built with the Apify SDK for Python, Microsoft MarkItDown (MIT) and PDFium (pypdfium2, Apache-2.0/BSD).

More tools from this developer

• Bulk Domain Intel (RDAP): domain age, expiry, registrar, DNS and an SPF/DMARC/DKIM grade.
• Website Tech Stack Detector: CMS, ecommerce, analytics and CDN, with evidence for each detection.
• Wayback Machine Change Tracker: capture history and a text diff between archived versions.
• Broken Link & Redirect Chain Auditor: broken links, redirect chains, mixed content and noindex pages.