Tables from scanned PDFs to Excel

A scan is a picture of a page, so there is no text to copy and converters that only read a PDF's text give you nothing. Aoken Extract reads the tables on the page itself and gives you each one as an Excel or CSV file.

What it reads

• Scanned PDFs from an office scanner or a scanning app.
• Phone photos of a printed table, as JPG, PNG or WebP.
• Mixed files, where some pages are scans and some are digital. A table that continues on the next page stays one table, with the header once.

Not sure which kind of PDF you have? Check it free in your browser before you pay for anything.

How it handles a hard-to-read page

• Unclear readings are flagged. When a figure is smudged or cut off, you still get its most likely reading, with a short note in the preview so you know which cell to check.
• Totals are checked. A row labelled Total must equal the sum of the amounts above it, to the cent. When the page has a Total row, a misread amount above it makes this check fail.
• Odd cells are highlighted: text in a column of amounts, and rows with the wrong number of cells.

Amounts come out as numbers without currency signs or thousands separators, so SUM works straight away. Text is copied as written, in any language. Nothing is translated.

Limits and cost

• PDF, JPG, PNG or WebP, up to 100 pages and 5 MB per file.
• $0.06 to $0.10 per page, from page packs that never expire. A page that fails to convert costs nothing. See pricing.
• Your files and results are deleted within 24 hours and never used to train AI models. Privacy policy.

Working with a particular document? See bank statements and invoices.