Faut-il créer votre propre ScanToExcel ?

Build a document-to-spreadsheet converter inspired by ScanToExcel.
Use exactly this stack: Next.js 15 + TypeScript.
Primary job: the user uploads a photo or a PDF page containing a table, and gets back a downloadable .xlsx whose cells match the document.
Start from an empty folder and create the complete working project.
Send the image to one vision-capable model and ask for the table as structured rows and columns, not as prose.
Write the result with a spreadsheet library so numbers arrive as numbers and dates as dates, not as text.
Show the extracted table in the browser for review and let the user fix cells before downloading - never hand over a file the user has not seen.
Handle multi-page PDFs by processing pages in order and dropping a repeated header row when the same header appears on a later page.
Single-user and private by default; delete uploads once the download is produced, and say so in the UI.
Put every secret in .env and provide .env.example.
Include clear empty, loading, validation, success and failure states, and show the model's confidence when it reports one.
Accessible keyboard navigation, labels, focus states and sensible contrast.
Deliberately exclude these paid-product advantages: a native mobile capture app, tuned handwriting recognition, batch processing of very long documents.
State plainly in the README that handwriting and low-quality photos are where this build degrades.
Write unit tests for the row-parsing logic and one end-to-end smoke test that converts a sample image to a valid .xlsx.
Create a README with setup, architecture, per-page cost estimate and limitations.
Run the tests and build before finishing, then fix what fails.