Download iamges with flickr API

flickr_image_download.py

"""
To utilize flickr API, you need to parse a config.json like bellow.

{
  "Key": "XXXX",
  "Secret": "XXXX",
  "Keywords": "XXXX",
  "Per_page": "XXXX",
}
"""
import argparse
import json
import os
import time
from logging import DEBUG, StreamHandler, getLogger
from urllib.request import urlretrieve

from flickrapi import FlickrAPI

WAIT_TIME = 1
SAVEDIR = "./photos"

logger = getLogger(__name__)
handler = StreamHandler()
handler.setLevel(DEBUG)
logger.setLevel(DEBUG)
logger.addHandler(handler)
logger.propagate = False


def get_photos_info(key: str, secret: str, perpage: int, keyword: str) -> list:
    """Get data photos using flickr api
    Flickr API: https://code.google.com/archive/p/flickrpy/
    """
    logger.debug('Search keyword: {}'.format(keyword))

    flickr = FlickrAPI(key, secret, format='parsed-json')
    result = flickr.photos.search(
        text=keyword,
        per_page=per_page,
        media='photos',
        sort='relevance',
        safe_search=1,
        extras='url_q, license')

    photos_info = result['photos']
    return photos_info


def download_photos(photos_info: dict, keyword: str) -> None:
    """Download and save photos with photos info via flickr api"""
    for i, photo_info in enumerate(photos_info['photo']):
        url_q = photo_info['url_q']
        filepath = SAVEDIR + '/{}_{}.jpg'.format(keyword.replace(' ', '_'), i)
        if os.path.exists(filepath):
            continue
        urlretrieve(url_q, filepath)
        time.sleep(WAIT_TIME)


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument(
        '--flickr_config',
        required=False,
        default='flickr_config.json')
    args = parser.parse_args()

    with open(args.flickr_config) as f:
        flickr_config = json.load(f)

    key = flickr_config['Key']
    secret = flickr_config['Secret']
    keywords = flickr_config['Keywords']
    per_page = flickr_config['Per_page']

    if not os.path.isdir(SAVEDIR):
        os.makedirs(SAVEDIR)

    for keyword in keywords:
        photos_info = get_photos_info(key, secret, per_page, keyword)
        download_photos(photos_info, keyword)