从网上抓取图像

# load logo data from logo.txt which include image http paths.

import sys
import os
import argparse
import time

from urllib.request import urlretrieve

def parse_arguments(argv):
    parser = argparse.ArgumentParser()
    parser.add_argument('--file_path', type=str, help='the txt file path', default='/opt/xxx/data/img_path.txt')
    parser.add_argument('--save_path', type=str, help='save path', default='/opt/xxx/data/test')

    return parser.parse_args(argv)


def main(args):
    with open(args.file_path, 'r', encoding='utf-8') as f:
        idx = 0
        for line in f.readlines():
            img_path = line.strip('\n')
            if img_path:
                print(img_path)
                for i in range(10):
                    try:
                        urlretrieve(img_path, os.path.join(args.save_path, '2021-07-27_'+ str(idx) + '.jpg'))
                    except Exception as e:
                        if i >= 9:
                            print('load faild')
                        else:
                            time.sleep(0.5)
                    else: 
                        time.sleep(0.1)
                        break
                idx = idx + 1


if __name__ == '__main__':
    main(parse_arguments(sys.argv[1:]))

参考资料
Python Requests 频繁请求网站时返回“[Errno 104] Connection reset by peer”错误的解决方法