Extract tables from your scanned documents

Automatically extract printed text, handwriting, and other data from scanned documents that goes beyond simple optical character recognition (OCR) to extract data from tables.


We have the most advanced solution for extracting tables from images

Robust table extraction technology

We use artificial intelligence to "read" documents as a person would, to extract printed text and handwriting without configuration, training, or custom code.

PDF2Spreadsheet automatically detects a document’s layout and the key elements on the page, understands the data relationships in any embedded tables, and extracts everything with its context intact.

Tools you already use

We integrate with Microsoft Excel, Google Sheets, Comma-Separated Values or JSON files.

Load files from your computer, phone or import them on the web. Upload PDFs from your Box, Dropbox, Google drive or Microsoft OneDrive folder.


We support many languages: English, Spanish, German, Italian, Portuguese, and French. PDF2Spreadsheet will automatically detect and extract the information.

Start On Demand

No upfront cost nor setup required. Start extracting tables from PDF today.


Start with no upfront cost with our on-demand plan. We can scale at any transaction volume you need.

Share files with your colleguages by inviting them to your team.


OCR a handwritten table from a scanned document


Convert a bank statement to Excel


Import a grid from an image


Parse a product Catalog to CSV


Convert a utility statement to Excel


Simple Pricing

Start free. Upgrade whenever you want.

Pay as you go

$0 /mo

100 pages processed for $0.20 per page

1000 pages processed for $0.07 per page

5000 pages processed for $0.03 per page

Share files with your team in real-time

Automate your workflow with our API access

For businesses or individuals