PDF, Word & PowerPoint to Text/Markdown [$3/1K 💰]

Pageshuck: PDF to Text & Markdown Extractor (PDF, Word, PowerPoint)

Turn any PDF, Word or PowerPoint file into clean text and Markdown, with tables kept

Pageshuck downloads your PDF, DOCX and PPTX files and returns clean, LLM-ready Markdown (headings, bullet lists and tables kept) and plain text in reading order, plus page count, word count and document metadata. It reads two-column papers in the right order, rejoins words split across lines, and can split the text into RAG chunks for embeddings. One row per document, or one row per page for citations. $3 per 1,000 documents, no start fee.

▶ Try it now with a prefilled input · $0.003 per document (100 PDFs = $0.30) · up to 500 pages per document by default · Apify's free plan includes $5 of credit a month

Built for: RAG and AI-agent pipelines that need documents as Markdown · analysts pulling text from reports, filings and research papers · legal, finance and compliance teams searching contracts and policies · developers who need a PDF-to-text API without running their own parser

Real output (real run on Apify, 10 Nov 2026: 5 links, 3 documents converted (23 pages) in 2.9 s, platform cost $0.0002; the other 2 links answered 403 and 404 and were not charged):

Document	Type	Pages	Words	Markdown (start)
IRS Form W-9 (fw9.pdf)	pdf	6	6,525	form header as a table: Form W-9 · Request for Taxpayer Identification Number and Certification · Give form to the requester…
BERT paper (arxiv.org/pdf/1810.04805, two columns)	pdf	16	10,654	## BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding · Abstract · We introduce a new language representation model…
calibre demo.docx	docx	3	1,650	Demonstration of DOCX support in calibre · This document demonstrates the ability of the calibre DOCX Input plugin…

{"urls": ["https://www.irs.gov/pub/irs-pdf/fw9.pdf", "https://arxiv.org/pdf/1810.04805"], "chunkSize": 1500}

What you get for each document

Field	What it is
url, type, status	The file, its type (pdf, docx, pptx) and ok, no-text or error.
markdown	Headings (#, ##), bullet lists and tables as GitHub Markdown; pages separated by <!-- page break -->.
text	Clean plain text in reading order (table cells separated by tabs).
pageCount, pagesExtracted, page	Total pages, pages read, and the page number in per-page mode.
words, characters	Size of the extracted text.
chunks	Text split into chunks of chunkSize characters at paragraph and sentence ends (optional).
metadata	Title, author, subject, keywords, creator app, producer, created and modified dates, PDF version.
needsOcr	true when a PDF has little or no text layer (a scan): run those pages through OCR.
sha256, fileSizeBytes, change	File fingerprint and size; new or changed in monitor mode.
error	Why a file failed (404, password-protected, not a document, too big).

Ready-made inputs

Job	Input
One PDF to Markdown	{"urls": ["https://example.com/report.pdf"]}
Research papers for RAG	{"urls": ["https://arxiv.org/pdf/1810.04805"], "formats": ["markdown"], "chunkSize": 1500}
Page-by-page with citations	{"urls": ["https://example.com/handbook.pdf"], "outputMode": "pages"}
Only the first pages	{"urls": ["https://example.com/annual-report.pdf"], "pageRange": "1-5"}
Word and PowerPoint	{"urls": ["https://example.com/contract.docx", "https://example.com/pitch.pptx"]}
Watch documents for changes	{"urls": ["https://example.com/terms.pdf"], "monitor": true}

Use cases

• RAG and AI agents: documents in, Markdown and chunks out, ready for a vector database or an LLM prompt.
• Search and archiving: make a folder of PDFs searchable by text, with metadata and page numbers.
• Document monitoring: run on a schedule with monitor mode and get only policies, price lists or filings that changed.
• Data extraction: tables come out as Markdown tables you can parse into rows.

Run it on a schedule

1. Put your document URLs in the input with "monitor": true and save it as a task.
2. Schedules → Create: daily (cron 0 7 * * *) or weekly.
3. Add an integration (email, Slack, webhook to Make/Zapier/n8n). Each run returns only new or changed documents; unchanged ones cost nothing.

Integrations

• API (curl):

  curl -X POST "https://api.apify.com/v2/acts/cybermax~pdf-to-text/run-sync-get-dataset-items?token=YOUR_TOKEN" \
    -H "Content-Type: application/json" -d '{"urls": ["https://www.irs.gov/pub/irs-pdf/fw9.pdf"]}'
  

• Python: ApifyClient(token).actor("cybermax/pdf-to-text").call(run_input={"urls": [...]})
• JavaScript: await new ApifyClient({ token }).actor('cybermax/pdf-to-text').call({ urls: [...] })
• Make, Zapier, n8n: use the Apify app or node, run cybermax/pdf-to-text, then map markdown or text into Google Docs, Notion, Airtable or your LLM step.
• AI agents (MCP): add it to the Apify MCP server: https://mcp.apify.com?actors=cybermax/pdf-to-text.

Why Pageshuck

	Pageshuck	Typical PDF text extractor on the Store
Formats	PDF, Word (DOCX) and PowerPoint (PPTX) in one Actor	Often PDF only
Markdown	Headings, lists and tables kept; two-column papers in reading order	Often plain text, columns mixed
Per-page rows	Yes, with page numbers	Sometimes
RAG chunks	Built in	Rare
Monitor mode	Only changed documents, unchanged = free	Rare
Price	$3 per 1,000 documents, no start fee	$3.45–$5 per 1,000 PDFs plus a $5 start fee per 1,000 runs (Store prices on 10 Nov 2026)

FAQ

Does it do OCR for scanned PDFs? Pageshuck reads the text layer, which most PDFs have. When a PDF is a scan, the row says needsOcr: true (and a fully scanned file is not charged). For images and scans, use Inkscry: Image to Text OCR.

How big can a file be? Up to 100 MB and 500 pages by default; raise maxFileSizeMb (300 MB max) and maxPages (5,000 max) for bigger documents. You pay the same per document.

What about password-protected PDFs? They are reported with an error and not charged.

Is it legal? Pageshuck converts files you link to. Use it on documents you own or are allowed to process; it collects nothing else.

Why not a free PDF library? You can; Pageshuck saves the hosting, the edge cases (columns, tables, hyphenation, broken metadata) and gives you an API, schedules and integrations for $0.003 a document.

Also from CyberMax

• Inkscry: Image to Text OCR · text from scans, screenshots and photos.
• Docsieve: Website to Markdown · whole websites as Markdown and llms.txt.
• Inkpluck: Article Extractor · clean article text from news pages and RSS.

Found this useful? A quick rating helps others find it.

© 2026 CyberMax. All rights reserved.