Turning a bank statement PDF into a spreadsheet with a vision model

Larry — Tue, 20 Oct 2026 14:16:33 +0000

Bank statement PDFs are deceptively hard to parse. You'd think it's a
table, but:

A single transaction "description" frequently wraps across several lines, so you can't just split on newlines.
Debits and credits flip sign depending on the bank.
Scanned statements have no text layer at all.

So I didn't try to parse the PDF structure directly. Instead:

Render each page to an image with mupdf compiled to WASM.
Send the image to a vision model with a strict JSON schema:

{"bankName": ..., "accountNumber": ..., "summary": [...],
"transactions": [{"date": "...", "description": "...",
"amount": 0}]}

Ask for negative amounts on debits and positive on credits.
Stream rows back over SSE so the UI fills in live.
Reassemble and export (xlsx, CSV, and plain-text OFX/QBO/QIF for QuickBooks and Xero).

The things that actually moved the needle on accuracy:

Separate prompts: a "header + summary + transactions" prompt for page one, a transactions-only prompt for later pages.
Telling the model "return only JSON, no markdown".
Explicit sign conventions instead of relying on the model's guess.
Generating a deterministic FITID for QBO/OFC so re-imports don't duplicate entries.

It's live and free at statementexcelconverter.com. The parts that
still need work: hand-annotated adjustments (paper statements with
notes), and non-Latin statement layouts.

Happy to share more detail or the prompt structure if useful.

DEV Community: Larry

Turning a bank statement PDF into a spreadsheet with a vision model