DIY_Book_Scanner_Workflow/tesseract_ocr.py

# import libraries
from PIL import Image
import pytesseract
import time

i = 1

while True:
    try:
        img = Image.open("bounding_box/input%i.jpg"%i)
        print(img)
        pdf = pytesseract.image_to_pdf_or_hocr(img, lang="eng", extension='pdf')
        time.sleep(1)
        file = open(("ocred/page%i.pdf"%i), "w+b")
        file.write(bytearray(pdf))
        file.close()
        i+=1
        print(i)

    except:
        print("All pages must be ready!")
        break