from PIL import Image
import pytesseract
import re
from loguru import logger

'''
下载语言包
wget https://github.com/tesseract-ocr/tessdata/raw/main/chi_sim.traineddata
mkdir tessdata
mv chi_sim.traineddata tessdata
export TESSDATA_PREFIX=tessdata
'''

logger.add('huanbu.log', rotation='100 KB', level='DEBUG', compression='tar.gz')
logger.debug("That's it, beautiful and simple logging!")
def format_number(number, width):
    return f'{number:0{width}}'


def extract_text(image_path):
    image = Image.open(image_path)
    text = pytesseract.image_to_string(image, lang='chi_sim')
    text_without_spaces = re.sub(r'\s', '', text)
    return text_without_spaces


if __name__ == "__main__":
    imgpath='./huanbu/'
    for num in range(1, 331):
        fnum = format_number(num, 3)
        img = f'{imgpath}{fnum}.png'

        extracted_text = extract_text(img)
        print(extracted_text)
        logger.info(extracted_text)