Extract structured tables from PDF files in seconds.
Supports PDFs, scanned invoices, bank statements, financial reports, government forms, and academic papers. Powered by OCR and deep table structure recognition — no manual cleanup needed.
Drop your file here
or · paste image ⌘V
PDF, PNG, JPEG, BMP, TIFF, WEBP · max 200 MB
Processing
document.pdf
Export
Something went wrong
Built for accuracy and speed — turn messy documents into clean, structured data.
Structure-Aware OCR
Detects rows, columns, and merged cells — not just raw text — so tables come out clean, not scrambled.
Multi-Format Input
Works with PDFs, scanned invoices, bank statements, and photos — PNG, JPEG, BMP, TIFF, and WEBP all supported.
Fast Processing
A step-by-step pipeline — upload, OCR, table detection, cell reconstruction — completes in seconds, not minutes.
Export Anywhere
Download results as JSON, CSV, Excel, HTML, or Markdown — whatever fits your workflow.
Multi-Table Support
Documents with several tables are automatically split and navigable, page by page and table by table.
Searchable Results
Instantly search across extracted table data, plus view raw JSON, metadata, and stats side by side.