Read a PDF into structured JSON
Reads one PDF in a single pass and appends everything it found to a Google Doc as JSON, with the low-confidence values listed.
Apps it connects
Authenticate each one once and the workflow is ready to run.
What it does
The integration steps this workflow runs, in the order it first runs them.
- 1ExtendExtract data
- 2Google DocsAppend text
How it works
Everything the template sets up, and what to fill in before the first run.
Some documents are worth reading into a machine-readable shape before you decide what to do with them - a form, a spec sheet, a statement of work, a scanned report. This reads the whole file in one pass, works out its own shape for it, and appends the result to a Google Doc as JSON you can copy into whatever comes next.
You do not have to name the fields. Leave 'readingGuidance' empty and the document's own structure decides them; fill it in - 'this is a delivery note, return dates as YYYY-MM-DD' - and the read follows that instead. This is why the output is JSON rather than a spreadsheet: a workflow cannot create columns for fields it has not been told about, but it can write the whole record out faithfully.
Every run appends a new section headed with the file name and the date, so the Doc becomes a log of everything you have read. Nothing in the Doc is ever overwritten.
Values are reported as they were read - nothing is completed, tidied up or filled in from elsewhere. Each value carries a confidence, and any that came back below the level you set in 'flagBelowConfidence' is listed by name and page under the JSON so you know exactly what to check. A value whose confidence was not reported at all is listed too.
Fill in 'sourceFile' and 'notebookDocument'. 'readingGuidance' and 'flagBelowConfidence' are optional.
You May Also Be Interested In
Turn a multi-page scan into readable textRuns OCR over a scanned PDF, then writes each page as clean text into a Google Doc you can search, quote and edit.
Summarise and index new documents in a Box folderChecks a Box folder hourly and gives each new PDF its own summary document and one row in your index sheet.Pull the contact details out of your notesReads a page of notes and adds a row for every name, email address and phone number actually written in it.
Summarise a batch of documents into one digestReads each Google Doc you list, summarises it with AI, and appends every summary to one digest document.
Start from a workflow that already works.
Add "Read a PDF into structured JSON" to your workspace, connect its apps, and make it yours. No credit card required.
Free plan available · No credit card required