PURCHASE_ORDER_OCR
Purchase order OCR for PO numbers, line items, and approvals
Convert purchase order PDFs into structured data for AP matching, procurement review, and downstream finance workflows.
{
"document_type": "purchase_order",
"po_number": "PO-88421",
"supplier_name": "Northstar Supply Co.",
"buyer": "Aiman Operations LLC",
"order_date": "2026-04-28",
"line_count": 14,
"subtotal": 4820.0,
"total_amount": 5205.6
}
FIELD_SCHEMA
Fields built for PO matching
The parser extracts the PO fields teams need before invoice matching: supplier, buyer, ship-to details, item rows, quantities, and totals.
PO identity
Supplier and buyer
Line items
Handles purchase orders that slow AP matching
PO tables split across pages with repeated headers
Item descriptions wrapped across multiple table rows
Ship-to and bill-to addresses printed in separate blocks
Discounts, freight, and tax rows mixed with ordered items
From PO upload to match-ready data
Upload a purchase order PDF, scan, or image
Extract PO header fields, addresses, line items, and totals
Review ambiguous item rows before export
Export clean PO data to Excel, CSV, JSON, or your API flow
RELATED_PARSERS
FAQ
Common questions
Can PDF2TEXT extract purchase order line items?
Yes. It extracts PO header fields and line-item tables so teams can review quantities, prices, and totals.
Can I match purchase orders to invoices?
Yes. Export PO numbers, vendors, item rows, and totals to support invoice matching and approval workflows.
Does PO OCR work with scanned purchase orders?
Yes. Upload scanned purchase orders or image files, then review the extracted fields before export.
Turn purchase orders into structured data
Convert purchase order PDFs into structured data for AP matching, procurement review, and downstream finance workflows.