Drop a PDF with tables here
or click to browse — PDF only, up to 25 MB
Up to 15 pages — scanned tables work too — password-protected PDFs not supported
What PDF to Excel does
ℹ️ Need the prose instead of the tables? PDF to Word converts the whole document.
Plenty of data arrives locked inside a PDF — bank statements, financial reports, price lists, exported dashboards, research tables. Copy-pasting them into a spreadsheet by hand is slow and error-prone, and a plain copy usually loses the row-and-column structure. PDF to Excel reads the tables with AI and rebuilds them as a real spreadsheet you can sort, filter, and sum.
It works on scanned tables too. The same AI vision behind our OCR tool reads pixels, not just text layers, so a photographed or scanned table still extracts into a grid. If your document is a stack of invoices or receipts rather than free-form tables, the Invoice & Receipt Scanner is purpose-built for that and validates totals as it goes.
Upload a PDF. The document is sent to Anthropic's Claude API, which reads each page, locates the tables, and reconstructs each one as a set of columns and rows. Every detected table becomes its own sheet, so a multi-table report lands as a multi-sheet workbook.
You preview the tables on screen, switch between sheets, then download a ready-to-open .xlsx file. Your document is held in memory only, forwarded to Anthropic for processing, and never written to our disk.
Finding and rebuilding tables means analyzing each page as an image, which is much heavier than reading a text layer. PDF to Excel is capped at 15 pages per document to keep it fast and free. If your file is longer, use Split PDF to break it into smaller parts and run each part through PDF to Excel — both tools are free and run back to back.
Best results: clean digital PDFs and sharp scans with clearly ruled tables — statements, ledgers, price lists, exported reports. Straightforward grids with a single header row come through faithfully.
Best-effort: merged cells, nested or multi-row headers, and tables that wrap across pages. The AI does its best, but expect to tidy header rows or re-join split cells in the resulting .xlsx. Faint scans and skewed phone photos also lower accuracy.
Whatever the input, treat the output as a strong first draft: proofread the numbers before relying on them for anything important.
PDF to Word converts a whole document — paragraphs, headings, and layout — into an editable Word file. PDF to Excel targets the tables specifically: it finds tabular data in your PDF and rebuilds it as spreadsheet rows and columns you can sort, filter, and sum. If you mostly need prose, use PDF to Word; if you need the numbers in a grid, use PDF to Excel.
Yes. PDF to Excel reads tables with the same AI vision used by our OCR tool, so a scanned or photographed table — with no selectable text layer — still extracts into a spreadsheet. Accuracy is highest on clean, sharp scans; faint or skewed pages reduce it. Always proofread the result.
Each page is analyzed by the AI to find and reconstruct tables, which is heavier than reading a plain text layer. The 15-page cap keeps each job fast and keeps the tool free. For longer files, use Split PDF to break the document into smaller parts and run each part through PDF to Excel.
Merged cells, nested headers, and multi-row headers are handled on a best-effort basis. Simple grids extract faithfully; complex layouts may flatten merged cells or split a nested header across columns. Open the .xlsx and tidy the header rows if needed — the underlying data is preserved.
For AI-processing details and Anthropic's API retention terms, see our Privacy page.
Free, no signup. Extract tables from a PDF into a ready-to-open Excel workbook.