AI tool

Extract Tables from PDF

Pull every table out of a PDF as CSV or JSON. Uses PyMuPDF's table detector — fast and self-hosted, no Adobe call. Best on native (born-digital) PDFs from Excel, Word, Google Docs, or any source with visible table structure.

Scanned / image-only PDFs need OCR before tables can be detected. If your result is empty, run /tools/ocr first, then come back.

Drop a PDF here, or click to choose

Up to 50 MB

Output format

CSV

One file, all tables. Easy to open in Excel, Google Sheets, Numbers, or any data tool.

JSON

Structured. Each table has page, index, bbox, rows × cols. Good for piping into scripts.

Extract Tables from PDF

Related tools