Simple python captcha reader using tesseract OCR

captcha.py

from PIL import Image
import sys

import pyocr
import pyocr.builders

tools = pyocr.get_available_tools()
if len(tools) == 0:
    print("No OCR tool found")
    sys.exit(1)
# The tools are returned in the recommended order of usage
tool = tools[0]
print("Will use tool '%s'" % (tool.get_name()))
# Ex: Will use tool 'libtesseract'


# https://github.com/ldong/captcha-decoder
from PIL import Image,ImageEnhance,ImageFilter
def iterate(im, iteration):
    if iteration == 0:
        return im.convert('1')
    
    im = im.filter(ImageFilter.MedianFilter())
    enhancer = ImageEnhance.Contrast(im)
    im = enhancer.enhance(2)
    
    return iterate(im, iteration-1)


import sys

txt = tool.image_to_string(
    iterate(Image.open(sys.argv[1]), 3),
    #lang='eng',
    builder=pyocr.builders.TextBuilder()
)

print()
print('---- OCR: ----')
print(txt)
print()