dreammarket.py 文件源码

def process_captcha(self, image):
        """
        TODO: DOC
        """
        cv2_img = cv2.cvtColor(numpy.array(image), cv2.COLOR_BGR2GRAY)

        # Find the threshold of the image so that we can identify contours.
        ret, thresh = cv2.threshold(
            cv2_img,
            127,
            255,
            cv2.ADAPTIVE_THRESH_GAUSSIAN_C
        )
        # Find the contours of the image
        _, contours, hierarchy = cv2.findContours(
            thresh,
            cv2.RETR_EXTERNAL,
            cv2.CHAIN_APPROX_SIMPLE
        )

        # Find the largest contour in the image with 4 points. This is the
        # rectangle that is required to crop to for the captcha.
        largest_contour = None
        for contour in contours:
            if (len(cv2.approxPolyDP(contour, 0.1*cv2.arcLength(contour, True), True)) == 4) and (2500 < cv2.contourArea(contour) < 4000):
                if isinstance(largest_contour, type(None)):
                    largest_contour = contour
                    continue
                if cv2.contourArea(contour) > cv2.contourArea(largest_contour):
                    largest_contour = contour
        # If we don't have a matching contour, don't try to crop and such
        if isinstance(largest_contour, type(None)):
            return None

        # If we do have a matching contour, build the rectangle
        crop_x, crop_y, crop_width, crop_height = cv2.boundingRect(
            largest_contour
        )
        # Crop down to the contour rectangle
        image = image.crop(
            (
                crop_x,
                crop_y,
                crop_x + crop_width,
                crop_y + crop_height
            )
        )
        return image