1. Install Tesseract
2. Install requirements.txt: $ pip install -r requirements.txt

Download One Piece

Warning this is a large zip file ~4GB

Remember to set your tesseract path in main.py line 9

For example:

pytesseract.pytesseract.tesseract_cmd = '/usr/local/Cellar/tesseract/5.1.0/bin/tesseract'

Text is extracted to <filename>.txt

For example img2.png will output to img2.txt

Example execution:

$ python main.py --file img2.png

Make sure the One_Piece folder is in the root directory of this project. This will output all the .txt files in each folder per manga panel.

$ bash automate_extraction.sh