gctag.py 文件源码

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--url', metavar='URL', default=None, help='input the url')
    parser.add_argument('--output', metavar='OUTPUT', default='./wordcloud.jpg', help='input the output_file')
    parser.add_argument('--input', metavar='INPUT_FIEL', default=None, help='input the input_file')
    parser.add_argument('--model', metavar='INPUT_IMAGE_MODEL', default=None, help='input the input_image_model')
    parser.add_argument('--ttf', metavar='INPUT_TTF', default='./font/simhei.ttf', help='input the typeface')
    parser.add_argument('--width', metavar='INPUT_WIDTH', default=1800, type=int, help='input the image width')
    parser.add_argument('--height', metavar='INPUT_HEIGHT', default=1000, type=int, help='input the image height')
    parser.add_argument('--bg', metavar='INPUT_BACKGROUND_COLOR', default='black', help='input the image background_color')
    parser.add_argument('--margin', metavar='INPUT_MARGIN', default=5, type=int, help='input the image margin')
    parser.add_argument('--max_font_size', metavar='INPUT_max_font_size', default=60, type=int, help='input the max_font_size')
    args = parser.parse_args()

    url = args.url
    output_file = args.output
    input_file = args.input
    model_path = args.model
    typeface = args.ttf
    max_font_size=args.max_font_size
    width = args.width
    height = args.height
    background_color = args.bg
    margin = args.margin

    try:
        image_mask = np.array(PIL.Image.open(model_path))
    except:
        image_mask=None

    wordcloud = WordCloud(font_path=typeface, mask=image_mask, max_font_size=max_font_size,
                          background_color=background_color, margin=margin, width=width, height=height)
    try:
        txt_join = get_txt(input_file)
        wordcloud_ = wordcloud.generate(txt_join)
    except:
        html_text = get_html_text(url)
        wordcloud_ = wordcloud.generate(html_text)

    image = wordcloud_.to_image()
    image.save(output_file)