Convert a bank statement PDF to a clean CSV
ProofRows extracts transactions from text-based or scanned bank-statement PDFs, lets you review every row against the source page, validates the math, and exports a clean CSV that imports into QuickBooks, Xero, or any spreadsheet.
What the tool does
A bookkeeper uploads a client’s bank statement as a PDF, opens the file in ProofRows, and gets back a CSV with the right columns, signs, and dates. The bookkeeper reviews every row before anything ships — the file never goes straight to a ledger without a human sign-off.
- Extracts date, description, vendor, amount, debit/credit, and balance from each transaction line.
- Renders the source PDF side-by-side with the extracted table so the bookkeeper can verify any row against the printed page.
- Surfaces a confidence score on every row; rows under 90% are flagged for review.
- Reconciles to the printed beginning and ending balance before allowing export.
- Exports the cleaned rows as a CSV that imports cleanly into QuickBooks Online, Xero, or a spreadsheet.
Why generic PDF converters fail
We benchmarked the same statement against five off-the-shelf PDF-to-CSV converters before we built ProofRows. The pattern was consistent — the converters dump rows, but the rows aren’t trustworthy.
Converters that guess on sign lose every reversed transaction. The CSV imports to QuickBooks with negative deposits.
Generic converters ignore the running balance. A small per-row rounding error becomes a $1,200 mismatch by the end of the month.
A deposit that crosses two pages is split in two, or dropped, or merged with the next transaction. The total ends up off by one.
Long merchant names, multi-line descriptions, and unicode characters are stripped, truncated, or replaced with placeholders.
There is no way to know if the CSV reconciles. You re-import it to the accounting system, run reconciliation, and chase the variance by hand.
AMAZON.COM*RT4N9 PMT goes straight into your books. Categorisation becomes a separate, manual, error-prone step.
The ProofRows workflow
Six steps from a messy PDF to a clean CSV. Each step exists because a real bookkeeper got burned without it.
- 01Upload
Drag one or more PDFs into the uploader. Multi-month, multi-bank, mixed quality.
- 02Extract
Every transaction parsed with dates, amounts, descriptions, vendor, and balances.
- 03Review
PDF and table side-by-side. Click a row, the source line highlights in the PDF.
- 04Validate
Beginning + Σ credits − Σ debits = ending. Math has to add up before export is allowed.
- 05Flag
Duplicates, low-confidence rows, missing fields surface as work items you can resolve in bulk.
- 06Export
CSV, XLSX, QuickBooks-ready CSV, or Xero-ready CSV. Choose signed amount or two columns.
CSV export for accounting workflows
Three CSV profiles ship today, all RFC-4180 compliant. Pick the one that matches where the file is going.
Date, Description, Vendor, Category, Amount, Balance. Optional Status and Confidence columns. Best for Excel, Numbers, or any tool that isn't QuickBooks or Xero.
Strips to Date, Description, Amount (signed) or Date, Description, Credit, Debit. Accepts the QBO Banking → Upload from file wizard without remapping.
Date, Amount, Payee, Description, Reference. Matches the column order Xero's bank-import wizard expects.
Full field-by-field reference: CSV format documentation.
For bookkeepers and accountants
ProofRows is built around the workflows you actually run — catch-ups, new-client onboarding, and historical reconstruction from PDFs.
Three to twelve months of bank statements from a single client. Drop the PDFs in, get a clean file back in a fraction of the time it would take to retype.
Reconstructing the year a client is missing before an extension deadline. The 30-day window before April 15 doesn't leave room for retyping.
Mid-year, a new client arrives with 3–6 months of statements in their inbox. Bring them in before QBO sync, not after.
When the previous bookkeeper left the books untidy, the bank export is long gone, and you're rebuilding from PDFs. The math has to add up; the audit log has to be there.
Quick reviews of historical activity for due diligence, forensic reconstruction, or pre-acquisition cleanup. PDFs in, reviewed transactions out.
Standardise the cleanup across your client base. Same CSV shape, same review surface, same balance check.
Current limitations (read these)
Honest is faster than a marketing claim. ProofRows today is a focused, review-first workspace — it is not a fully automated bookkeeping system.
- Text and scanned PDFs are supported today. OCR reads image-only statements, then low-confidence rows stay in review until a person confirms or excludes them.
- CSV, XLSX, QuickBooks-ready CSV, and Xero-ready CSV ship today. Direct QuickBooks Online push and direct Xero push are on the roadmap; the export file is the wire today.
- We do not claim SOC 2, HIPAA, ISO 27001, PCI-DSS, FedRAMP, or ‘bank-level’ security. The security page is the honest list of what we do and don’t have.
- ProofRows is not a replacement for bookkeeping software. It is a statement-cleanup workspace that prepares transaction data for import into the tools you already use.
Read the full Terms of Service for the complete picture.
Try it on your messiest statement
150 free pages, no credit card. The first statement is the one that takes the most time when you’re doing it by hand — start there.
Frequently asked questions
- Can ProofRows convert bank statement PDFs to CSV?
- Yes. ProofRows extracts transactions from bank-statement PDFs — text-based or scanned — and lets bookkeepers review, edit, validate, and export the results as CSV. The QuickBooks-ready and Xero-ready CSV profiles import cleanly into those tools through their native bank-import wizards.
- Does ProofRows work with scanned bank statements?
- Yes. Scanned and image-only statements are read with built-in OCR, then parsed into transactions the same way as text PDFs. Low-confidence rows from rough scans are flagged for review, and every statement still has to pass the balance check before export.
- Can I import ProofRows exports into QuickBooks?
- ProofRows exports QuickBooks-ready CSV (for the Banking → Upload from file wizard) and .qbo Web Connect files that QuickBooks Online and Desktop import natively. A direct QuickBooks Online API push is on the roadmap and should not be described as live yet. ProofRows is not affiliated with or endorsed by Intuit.
- Can I import ProofRows exports into Xero?
- ProofRows exports a Xero-ready CSV that supports Xero's bank-import workflow (Accounting → Bank accounts → Import a statement). A direct Xero API push is on the roadmap. ProofRows is not affiliated with or endorsed by Xero.
- Does ProofRows export to Excel (XLSX)?
- Yes — XLSX export is supported today. CSV files produced by ProofRows also open cleanly in Microsoft Excel, Apple Numbers, and Google Sheets.
- Is ProofRows a replacement for bookkeeping software?
- No. ProofRows is a statement-cleanup workspace. It prepares transaction data for import or reconciliation in accounting tools like QuickBooks Online or Xero. It is not a ledger of record.
- Who is ProofRows built for?
- ProofRows is built for solo bookkeepers, small bookkeeping firms, accountants, tax preparers, QuickBooks ProAdvisors, cleanup bookkeeping specialists, and fractional CFOs who receive bank statements as PDFs.
- How long do you keep my client's bank statements?
- Source PDFs are auto-deleted after the per-client retention window (default 30 days, configurable). The extracted transactions and export-log audit trail stay for the life of the account. Account deletion cascades and removes every row, file, and auth artifact in a single transaction.
- Do you train AI models on my client's bank statements?
- No. We do not train models on customer data. The extraction provider we use is contracted not to train on API requests, and our application does not write statement text back to the database from the model — the only path through is a strict schema validation.
- How accurate is the extraction?
- Confidence scores are surfaced per row so the bookkeeper can see which transactions the model is less sure about. The validation page enforces a beginning + Σ credits − Σ debits = ending balance check before any export. We do not claim 'perfect AI extraction' — every export is human-reviewed.
More questions? Contact support or read the full FAQ.