PDF to Markdown Converter

Extract clean, usable text from any PDF — research papers, contracts, reports, manuals — and output structured Markdown ready for LLMs, RAG pipelines, or document analysis.

No external APIs. No proprietary services. Built on open source.

Why Use This

Most PDFs are locked — the text is there, but buried in binary format that LLMs can't read. This Actor extracts the text, cleans it up, and returns it as Markdown you can immediately feed into any AI workflow.

$0.05 per PDF. No subscription, no monthly fee, no setup.

Use Cases

• RAG pipelines — Convert research papers, whitepapers, or documentation PDFs into text chunks before embedding
• Contract analysis — Extract legal document text for LLM review
• Report processing — Batch-process financial reports, audit documents, or regulatory filings
• Knowledge base ingestion — Convert PDF manuals and guides into searchable text
• Academic research — Process arXiv papers, theses, or journal articles at scale

Input

Parameter	Type	Required	Description
pdfUrl	string	✅	Direct URL to a machine-readable PDF file
includePageNumbers	boolean	❌	Insert --- Page N --- markers between pages (default: false)
maxPages	integer	❌	Limit pages processed. 0 = all pages (default: 0)

{
  "pdfUrl": "https://arxiv.org/pdf/2305.10601",
  "includePageNumbers": true,
  "maxPages": 20
}

Output

One item per PDF pushed to the dataset:

Field	Type	Description
pdfUrl	string	Source PDF URL
pageCount	integer	Number of pages processed
wordCount	integer	Total words extracted
markdown	string	Extracted text in Markdown format
disclaimer	string	Accuracy disclaimer

{
  "pdfUrl": "https://arxiv.org/pdf/2305.10601",
  "pageCount": 15,
  "wordCount": 8432,
  "markdown": "# Tree of Thoughts: Deliberate Problem Solving with Large Language Models\n\n## Abstract\n\nLanguage models are increasingly being deployed for general problem solving..."
}

Pricing

• $0.05 per PDF converted
• Charged only on successful conversion
• No charge for validation errors or failed runs

Quick Start

curl

curl -X POST https://api.apify.com/v2/acts/{ACTOR_ID}/runs \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "pdfUrl": "https://arxiv.org/pdf/2305.10601",
    "includePageNumbers": true,
    "maxPages": 20
  }'

JavaScript (Apify Client)

const { ApifyClient } = require('apify-client');

const client = new ApifyClient({ token: 'YOUR_API_TOKEN' });

const run = await client.actor('YOUR_ACTOR_ID').call({
  pdfUrl: 'https://arxiv.org/pdf/2305.10601',
  includePageNumbers: true,
});

const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].markdown);

Limitations

Limitation	Details
Scanned PDFs	Not supported — requires machine-readable text layers
Image-only PDFs	Will return minimal or empty text
Encrypted PDFs	Password-protected files cannot be parsed
Non-Latin scripts	Accuracy varies for Arabic, CJK, and other scripts
Complex layouts	Multi-column or heavily formatted PDFs may have extraction quirks

Always verify extracted text against the original for critical use cases.

Technology

• pdf-parse — MIT License — PDF text extraction
• Apify SDK — Apache 2.0 License — Actor runtime and dataset management

Disclaimer

This tool extracts text from PDF files using open source libraries. Accuracy depends on PDF structure and encoding. Results should be reviewed for critical use cases. Not a substitute for professional document review.

---

🔗 Related Actors by ntriqpro

Extend this actor with the ntriqpro intelligence network:

• blueprint-intelligence — AI blueprint analyzer for construction & architectural PDFs
• invoice-extraction-mcp — Structured extraction of line items from PDF invoices
• content-factory — Turn PDFs into quizzes, flashcards, slide decks, podcast scripts

⭐ Love it? Leave a Review

Your rating helps other professionals discover this actor. Rate it here.