Product Overview

Table Extraction from Documents, Row by Row and Column by Column

Totals, line items, and schedules sit inside tables, and a table copied out of a file usually arrives as a jumble of text. ExtractMails performs table extraction from documents by finding each grid, keeping its rows and columns intact, and returning the cells in order.

  • Grid Detection
  • Merged Cell Reading
  • Multi-Page Tables
  • Cell-Level Review
Capabilities

How Each Table Is Found, Read, and Rebuilt

Before table extraction from documents can return clean rows, ExtractMails must decide where a table starts, where it ends, and which cells belong together.

Desk with receipts, a calculator, and a spreadsheet on a laptop

Boundary Detection

Finds where a table begins and ends, even when text sits above and below it.

Column Alignment

Keeps each value under its own heading, including columns with no ruled lines.

Header Recognition

Treats the top row as column names and carries them into every record.

Merged Cell Handling

A heading spanning several columns is applied to each column it covers.

Subtotal Rows

Rows marked Subtotal or Total can be kept, labeled, or left out.

Smiling woman pointing to the side
Man uploading a PDF document on a laptop
How It Works

Point at the Table, Name the Columns, Collect the Rows

Running table extraction from documents on a regular basis comes down to one setup that later files reuse.

  1. 01

    Add the Document

    Upload a file or forward an email with the document attached.

  2. 02

    Outline the Table

    Draw a box around the table or name the heading above it.

  3. 03

    Name the Columns

    Confirm column names and mark the ones you want returned.

  4. 04

    Export the Rows

    Download the cells as a spreadsheet or send them to another system.

Table Anatomy

Not Every Table Looks Like a Grid

A tool built for table extraction from documents should recognize ruled grids, borderless columns, and tables that run across pages.

Ruled Grids

Cells outlined by lines are read cell by cell.

Borderless Columns

Tables held together only by spacing are split by where the text aligns.

Tables Across Pages

A table that continues on the next page is joined, and repeated headings are dropped.

Merged and Stacked Headers

Two-level headings, such as Quarter above Month, become one column name.

Tables Inside Tables

A small table nested in a cell is returned as its own list.

Accuracy Checks

How You Know a Row Landed in the Right Column

A shifted column can quietly corrupt a whole sheet, so ExtractMails gives you ways to catch it before the cells leave.

Colleagues comparing a printed purchase order with a spreadsheet

Column Count Check

Rows with more or fewer cells than the header are marked.

Total Comparison

Added-up line items are compared with the printed total.

Cell Beside Source

Select a cell to see the part of the page it was read from.

Doubtful Cell Marks

Values the reader is unsure about are highlighted for review.

Table Sources

Where the Tables Are Hiding

Teams use table extraction from documents wherever figures are stuck in a layout that a spreadsheet cannot read.

Logistics coordinator holding a clipboard with a shipping manifest

Invoice Line Items

Capture item, quantity, rate, and amount for every row.

Bank Statements

Return date, description, debit, and credit as separate columns.

Price Lists

Read product codes and prices from supplier catalogs.

Shipping Manifests

Collect consignment numbers, weights, and destinations from cargo lists.

Financial Reports

Pull period-by-period figures from statements and annual reports.

Lab and Test Results

Read result tables with units and reference ranges.

Why ExtractMails

Fewer Broken Columns, Less Cleanup

Reliable table extraction from documents saves the hours people spend straightening pasted text in a spreadsheet.

No Manual Realigning

Pasted tables rarely line up, and here they arrive already in columns.

Headings Travel With Rows

Every record carries its column names, even across page breaks.

One Layout, One Setup

Statements from the same bank reuse the saved outline.

Cells Stay Traceable

Each value can be checked against its place on the page.

Frequently Asked Questions

What Is Table Extraction From Documents?

It locates tables inside files, reads each cell, and returns the rows and columns as structured data instead of loose text.

Can It Read Tables Without Borders?

Yes, where the text lines up in clear columns. Results depend on file quality.

What Happens When a Table Spans Several Pages?

Pages are joined into one table, and repeated headings are removed so the rows stay continuous.

Can I Choose Which Columns Come Back?

Yes. Name the columns you need, and the rest are left out.

How Do I Catch Errors in a Row?

Check the marked cells beside the source page before export.

Where Can the Rows Be Sent?

To a spreadsheet download or supported systems through webhooks and APIs, depending on your setup.

Is It Only for PDFs?

Supported file types depend on your setup. Confirm yours during onboarding.

Get Started

Run One Messy Table Through First

Bring ExtractMails into your workflow for table extraction from documents. Upload one file with a difficult table, name the columns you need, and compare each row with the page.

Scroll to Top