cut.py

from os import makedirs
import os.path
from glob import glob
from functions import *
from constants import *

image_files = glob(os.path.join(CAPTCHA_FOLDER, '*.png'))

for image_file in image_files:
    print('Now doing file:', image_file)
    answer = os.path.basename(image_file).split('_')[0]
    image = cv2.imread(image_file)
    processed = process_image(image)
    contours = get_contours(processed)
    if not len(contours):
        print('[!] Could not extract contours')
        continue
    letters = get_letters(processed, contours)
    if len(letters) != NR_CHARACTERS:
        print('[!] Could not extract desired amount of characters')
        continue
    if any([l.shape[0] < 10 or l.shape[1] < 10 for l in letters]):
        print('[!] Some of the extracted characters are too small')
        continue
    for i, mask in enumerate(letters):
        letter = answer[i]
        outfile = '{}_{}.png'.format(answer, i)
        outpath = os.path.join(LETTERS_FOLDER, letter)
        if not os.path.exists(outpath):
            makedirs(outpath)
        print('[i] Saving', letter, 'as', outfile)
        cv2.imwrite(os.path.join(outpath, outfile), mask)