Scrape images from the Google Images

scrape-image.py

# pip install icrawler
from icrawler.builtin import GoogleImageCrawler
import argparse

if __name__=='__main__':

    parser = argparse.ArgumentParser(description='Scrape some images.')
    parser.add_argument('keywords', metavar = 'KEYWORDS', nargs = '+',
        help='keywords to download images for')
    parser.add_argument('-n', '--max-num', type = int, default = 10,
        help = 'Maximum number of images to download for each keyword')
    parser.add_argument('-W', '--min-width', type=int, default=200,
        help = 'Minimum width of images in pixels')
    parser.add_argument('-H', '--min-height', type=int, default=200,
        help = 'Minimum height of images in pixels')
    parser.add_argument('-d', '--directory', default='images',
            help = 'Directory in which to store images')

    args = parser.parse_args()

    for keyword in args.keywords:
        google_crawler = GoogleImageCrawler(
            parser_threads=2,
            downloader_threads=4,
            storage={'root_dir': '{}/{}'.format(args.directory, keyword)}

        )
        google_crawler.crawl(
            keyword=keyword,
            max_num=args.max_num,
            min_size=(args.min_width, args.min_height)
        )