captcha.py

import Image
import ImageFilter

def read_captcha(image_path):
    def prepare_image(img):
        """Transform image to greyscale and blur it"""
        img = img.filter(ImageFilter.SMOOTH_MORE)
        img = img.filter(ImageFilter.SMOOTH_MORE)
        if 'L' != img.mode:
            img = img.convert('L')
        return img

    def remove_noise(img, pass_factor):
        for column in range(img.size[0]):
            for line in range(img.size[1]):
                value = remove_noise_by_pixel(img, column, line, pass_factor)
                img.putpixel((column, line), value)
        return img

    def remove_noise_by_pixel(img, column, line, pass_factor):
        if img.getpixel((column, line)) < pass_factor:
            return (0)
        return (255)



    input_image = image_path
    output_image = 'temp_output.png'
    pass_factor = 100


    img = Image.open(input_image)
    img = prepare_image(img)
    img = remove_noise(img, pass_factor)
    img.save(output_image)

    import pytesseract
    im = Image.open(output_image)
    im.load()

    import os
    os.remove(output_image)

    return pytesseract.image_to_string(im).lower()