flickr 画像のメタデータをtxtファイルに抽出

前提・実現したいこと

flickrの画像のメタデータをtxtファイルに抽出したいのですが、エラーが出てしまいます

発生している問題・エラーメッセージ

Traceback (most recent call last):
  File "geo-1.py", line 53, in <module>
    pprint(photos)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 53, in pprint
    printer.pprint(object)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 139, in pprint
    self._format(object, self._stream, 0, 0, {}, 0)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 167, in _format
    p(self, object, stream, indent, allowance, context, level + 1)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 189, in _pprint_dict
    context, level)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 346, in _format_dict_items
    context, level)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 167, in _format
    p(self, object, stream, indent, allowance, context, level + 1)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 210, in _pprint_list
    context, level)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 389, in _format_items
    context, level)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 167, in _format
    p(self, object, stream, indent, allowance, context, level + 1)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 189, in _pprint_dict
    context, level)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 346, in _format_dict_items
    context, level)
  File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\pprint.
py", line 176, in _format
    stream.write(rep)
UnicodeEncodeError: 'cp932' codec can't encode character '\xe9' in position 15:
illegal multibyte sequence

該当のソースコード

python
1import os
2
3import time
4import traceback
5
6import flickrapi
7from urllib.request import urlretrieve
8
9import sys
10from retry import retry
11from pprint import pprint
12
13flickr_api_key = ""
14secret_key = ""
15
16keyword = sys.argv[1]
17
18
19@retry()
20def get_photos(url, filepath):
21    urlretrieve(url, filepath)
22    time.sleep(1)
23
24
25if __name__ == '__main__':
26
27    flicker = flickrapi.FlickrAPI(flickr_api_key, secret_key, format='parsed-json')
28    response = flicker.photos.search(
29        text=keyword,
30        media='photos',
31        sort='relevance',
32        safe_search=1,
33        has_geo=1,
34        extras='url_q,license,geo'
35    )
36    photos = response['photos']
37
38    try:
39        if not os.path.exists('./image-data/' + keyword):
40            os.mkdir('./image-data/' + keyword)
41
42        for photo in photos['photo']:
43            url_q = photo['url_q']
44            filepath = './image-data/' + keyword + '/' + photo['id'] + '.jpg'
45            get_photos(url_q, filepath)
46
47    except Exception as e:
48        traceback.print_exc()
49
50    photos = response['photos']
51    pprint(photos)

行動規範の内容に同意します

回答1件

ベストアンサー

API が返してくるのは json オブジェクトなので、.json ファイルとして保存しましょう。

python
1import os
2import traceback
3import time
4import sys
5import json
6from urllib.request import urlretrieve
7
8import flickrapi
9
10# API 設定
11flickr_api_key = ''
12secret_key = ''
13
14
15if __name__ == '__main__':
16    keyword = sys.argv[1]
17
18    flicker = flickrapi.FlickrAPI(
19        flickr_api_key, secret_key, format='parsed-json')
20
21    print('accessing... ')
22    response = flicker.photos.search(
23        text=keyword,
24        media='photos',
25        sort='relevance',
26        safe_search=1,
27        has_geo=1,
28        extras='url_q,license,geo')
29
30
31    photos = response['photos']
32    try:
33        out_dirpath = os.path.join('image_data', keyword)
34        os.makedirs(out_dirpath, exist_ok=True)
35
36        for photo in photos['photo']:
37            url = photo['url_q']
38            out_path = os.path.join(out_dirpath, photo['id'] + '.jpg')
39
40            print('getting image...', url)
41            urlretrieve(url, out_path)
42
43            time.sleep(1)
44
45    except Exception as e:
46        traceback.print_exc()
47
48    with open('photo_{}.json'.format(keyword), 'w') as f:
49        json.dump(photos, f, sort_keys=True, indent=4)