Skip to content

How to copy text from a scanned PDF

Quick answer

A scanned PDF is a picture of text, so there is nothing to select. Run it through DO101 PDF OCR: it reads each page with optical character recognition, gives you the text to copy or download as a .txt file, and shows a confidence score so you know how much to trust it. It supports 17 languages and runs on your device.

Open the PDF OCR — free

Step by step

  1. 1Open PDF OCR and choose the scanned PDF.
  2. 2Pick the language the document is written in.
  3. 3Start recognition. The first run downloads the OCR engine, which your browser then keeps.
  4. 4Check the confidence score, then copy the text or download it.

How to tell a scan from a normal PDF

Try to select a word. If the cursor drags a blue box over the whole page instead of highlighting text, the PDF is an image. Phone scanning apps, office photocopiers and old archive documents all produce these.

Getting accurate results

OCR is only as good as the image. A straight, flat, high-contrast scan comes out very well; a crooked phone photo of a faded receipt comes out poorly. If the score is below 70%, DO101 warns you — rescanning in better light usually does more than any setting.

Choose the right language. Recognition uses a language model, and reading French with the English model misses accents and common words.

Limits

Up to 20 pages per run, to keep the browser responsive — split a longer document first. The first run downloads the engine and language model, about 12 to 15 MB, from a public CDN; your PDF itself is never uploaded.

Frequently asked questions

Can I get a Word document instead of plain text?

Copy the OCR text into Word, or, for a PDF that already has a text layer, use PDF to Word directly.

Does it work on photos, not PDFs?

Yes — use Image to Text for a JPG or PNG. It uses the same engine.

Which languages are supported?

Seventeen, including English, Spanish, French, German, Portuguese, Italian, Japanese and Chinese. The full list is in the language picker.

The tool for the job

PDF OCRRuns in your browser

Read the text out of a scanned PDF.