Turn PDF documents into clean JSON/CSV with an API

Parse PDF invoices, receipts, and statements into structured JSON/CSV automatically. Pass the extracted text to DocStruct — free tier, developer-first, no credit card.

Try live demo View docs

PDFs hide your data

Invoices, receipts, and statements arrive as PDFs, and getting the data out means either manual retyping or expensive OCR. DocStruct takes the PDF's text (however you extract it — many tools and libraries do that part) and turns it into structured JSON or CSV: line items, totals, dates, vendor, and more.

Parse-then-extract is the winning combo

Use your existing PDF-to-text step, then call DocStruct to understand the content. It handles invoices, receipts, bank statements, and contracts automatically (type "auto" detects the kind) and returns clean, consistent fields.

Sample output

{
  "ok": true,
  "data": { ... }
}

Developer-first, free to start

One POST request to /v1/extract. CORS-enabled, JSON or CSV, 20 free calls a day. Pay-as-you-grow plans for production volume.

Quick start

POST https://docstruct.marwannaili-23-07.workers.dev/v1/extract
Content-Type: application/json

{"text": "<paste invoice/statement/receipt/contract text>", "type": "auto", "output": "json"}
→ {"ok": true, "data": { ... structured fields ... }}