Code for post "Transforming manga pages for lazy western readers"

transforming-manga-pages-for-lazy-western-readers-script-1.py

import easyocr

def extract_text_from_manga(base_image):
    reader = easyocr.Reader(['en'])
    if isinstance(base_image, Image.Image):
        base_image = np.array(base_image)

    results = reader.readtext(base_image, detail=1)
    extracted_data = []
    for result in results:
        data = {
            "text": result[1],
            "location": [int(point) for point in result[0][0]],
            "width": int(result[0][2][0] - result[0][0][0]),
            "height": int(result[0][2][1] - result[0][0][1])
        }
        extracted_data.append(data)
    return json.dumps(extracted_data, ensure_ascii=False)