flickrの画像情報抽出

前提・実現したいこと

flickrの画像のメタデータの抽出

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

tiitoi

2018/10/03 10:16

文字コードの問題だと思います。https://qiita.com/butada/items/33db39ced989c2ebf644

行動規範の内容に同意します

回答1件

ベストアンサー

以下のコードで特にエラーにはなりませんでした。

Python 3.6
Ubuntu 16.04

utf-8 でエンコードされた文字を Shiftjis に変換できないならば、print でなく、ファイルに保存してはどうでしょうか。

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