Turn a multi-page scan into readable text
Turns a scanned PDF into text you can search, copy and edit, written into a Google Doc page by page.
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.
- 1iLovePDFOcr pdfRecognises the text on the scanned PDF in the language you name, giving it a real text layer to read from.
- 2ExtendParse documentReads only the pages asked for out of the searchable PDF, one page at a time, keeping paragraphs and tables in order.
- 3Google DocsAppend textAppends each page's text under its heading, and an [INCOMPLETE] note if any page is missing or left for a later run.
- 4Google DocsInsert headingAdds a heading with the file name and date for the scan, and a 'Page' heading above each page's text.
For each
page- 5Google DocsInsert heading
- 6Google DocsAppend text
- 5
How it works
What happens on each run, in plain English.
Give it one scanned PDF and the Google Doc it should go into, and run it. The text on each page is recognised in the language you name and added to your Doc in reading order: a heading with the file name and date, then each page under its own 'Page' heading. Paragraphs keep their breaks, and a table comes through row by row with its cells split by a vertical bar.
It is a transcript, not a summary: the words written are the words recognised, and a page where nothing could be read is counted rather than filled in. Nothing already in the Doc is changed, so one Doc can hold many scans. A long scan is done in parts, 40 pages at a time by default; if any page is skipped, fails to write or is left for a later run, an [INCOMPLETE] note at the end says so and which page to start from next, so a half-read scan is never mistaken for a whole one.
You need iLovePDF (which recognises the text), Extend (which lays it out) and Google Docs connected, the scan, a link to the Doc, and the language on the page; the wrong language is the usual reason a scan comes back as gibberish.
You may also be interested in
Pull every value out of a PDF and flag what to checkReads any PDF, lists every value it found in a Google Doc, and points out which ones to double-check against the original.
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 "Turn a multi-page scan into readable text" to your workspace, connect its apps, and make it yours.
Free plan, no credit card