Extract Tables from PDF

Drop a PDF with tables, get spreadsheet-ready output back. Columns and rows are reconstructed, not flattened into prose.

What it does

LensCopy extracts tables from PDFs into markdown tables and spreadsheet files (XLSX). It uses AI-powered OCR to detect table boundaries, reconstruct columns and rows, and preserve header alignment. The output works for invoice tables, financial reports, academic papers, and scanned documents. The free tier handles 10 pages and no signup is required for the first try.

Extract tables from a PDF

  1. Open LensCopy. Visit lenscopy.com in your browser. No installation needed.
  2. Upload the PDF. Drag and drop the PDF onto the upload area. Multi-page PDFs are supported.
  3. Wait for processing. OCR runs and tables are reconstructed with column and row structure preserved.
  4. Export as XLSX or copy markdown. Use the Export button for an XLSX file ready for Excel or Google Sheets, or copy the markdown table to paste into Notion or docs.

FAQ: Extract Tables from PDF

How do I extract a table from a PDF to Excel?

Upload the PDF to LensCopy, wait for OCR processing, then export as XLSX. The output opens directly in Excel and Google Sheets with column and row structure preserved.

Can it extract tables from scanned PDFs?

Yes. Scanned and image-only PDFs go through the same OCR pipeline as digital PDFs. Table detection works on both.

What about tables that span multiple pages?

Multi-page tables are detected and merged where the column structure is consistent across page breaks. Pages with different layouts are kept separate.

Last reviewed 2026-05-03. Loading interactive page…