Google Colab Pdf OCR

Add OCR to your PDF books and documents easily using Google Colab , this will help you search text content or copy text form PDFs made from scanned images.

How to use:

1. Open the notebook in Google Colab

2. Set variables in the first Cell

   • make sure original_pdf matches the pdf's file name.
   • set correct lang_code (ara = Arabic, eng = English , jpn = Japanese, ..etc ) more codes here
   • (optional) you can set first and last pages to ocr only a range/ chapter ..etc

3. Upload the pdf or uncomment # !wget in the second cell and set the correct url. wget will make sure to set the correct name to the PDF when downloaded .

4. DONE ! Run all cells Runtime > Run all or run them cell by cell without skipping .

Features

• Easy setup.
• Basic Error checking .
• Shows Progress.

Credit:

Google Colab Tesseract