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
Each integration step this workflow runs, in order, what it is for, and the conditions and loops that decide when it runs.
- 1
ExtendExtract dataReads the whole PDF in one pass, following your guidance if given, and returns every value with a confidence and page number.
- 2
Google DocsAppend textAppends a section headed with the file name and date, holding the JSON and any values read below your confidence level.
How it works
What happens on each run, in plain English.
Give it one PDF, whether a form, a spec sheet, a statement of work or a scanned report, and run it whenever you want that document in a machine-readable shape. The whole file is read in a single pass, its own structure decides what the fields are unless you describe what it is and how to read it, and the result is appended to a Google Doc as JSON you can copy into whatever comes next.
Every run appends a new section to the Doc headed with the file name and the date, so it becomes a log of everything you have read and nothing in it 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 choose is listed by name and page under the JSON, so you know exactly what to check against the original. If nothing at all can be read from the file, the run stops and writes nothing.
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
