Skip to content

No account required

Start a project

The .docx file.

The one document format that stores its tables as tables. That makes extraction far more reliable than from a PDF of the same report.
Really a
ZIP archive of XML parts
Tables
Stored as real structures, including merged cells
Prose
Discarded. Only the tables are read.
Embedded objects
Not read. An embedded workbook has to be sent as its own file.
Read here as
Extracted. The tables are lifted out and the rest of the document is dropped.
Status
Ready
Fidelity
Data extracted
Largest file
25 MB free, 250 MB once a project is bought

What it actually is

Tables are lifted out of the document; the prose around them is kept as context.

A .docx is a ZIP of XML, and its tables are stored as genuine table structures with rows, cells and merges. This is the key difference from a PDF. Nothing has to be inferred from the geometry, because the grid is written down.

Only the tables come out. Everything else in the document, the prose, the headings, the footnotes, is discarded on the way in, so a sentence reading "figures exclude the Northern region pending migration" does not arrive beside the numbers it qualifies.

The awkward case is a document whose numbers are in the sentences rather than in a table, which is common in board reports. Nothing outside a table is read, so those figures do not arrive at all, and a document written that way is the wrong file to be analysing.

Upload one

The analysis runs before there is anything to pay for.

You see what it found, and the evidence behind it, first.

No account needed to start. You only pay when you like what you see.

What goes wrong, and what is done about it

2 named failures, each with the repair.

Merged cells that were doing two jobs

A merged cell spanning three columns is often a group heading rather than a value, and flattening it repeats the heading into three data cells that then look like observations.

What is done: Merged spans are not read as spans. A merged cell is one cell, so the row holding it comes out narrower than the header above it, and a table built with group headings is better sent as the spreadsheet it came from.

Numbers that only exist in a sentence

Board and management reports frequently state the important figure in prose and put only supporting detail in the tables. Extracting tables alone gets everything except the thing the document was written to say.

What is done: Nothing outside a table is read, so that figure does not arrive at all. Where the headline number lives in prose, put it into a table, or send the spreadsheet it was calculated in, before uploading.

If you have the choice, send something else

If the tables in the document were pasted from a spreadsheet, send the spreadsheet as well. The document has the numbers; the workbook has the formulas that produced them.

Questions people ask

About this format, not about the product.

Is this better than uploading the PDF version?

Yes, meaningfully. The Word file stores table structure explicitly, while the PDF stores glyph positions from which the structure has to be inferred. Send the .docx where you have the choice.

What happens to images and charts in the document?

Neither is read. Only the document's tables come out; a chart is dropped along with everything else that is not one, whether it is native or pasted in as a picture.

Can it handle a document with twenty tables?

Yes. Each one becomes its own table, keyed by where it sits in the document. The analysis then runs on the largest of them: the rest are read and available, but no figure is computed across two tables.

Keep reading

The jobs people do with this file, and the formats beside it.