1 from __future__ import unicode_literals
5 from .common import InfoExtractor
8 class NhkVodIE(InfoExtractor):
9 _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)'
10 # Content available only for a limited period of time. Visit
11 # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
14 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
15 'md5': '256a1be14f48d960a7e61e2532d95ec3',
19 'title': "Dining with the Chef - Chef Saito's Family recipe: MENCHI-KATSU",
20 'description': 'md5:5aee4a9f9d81c26281862382103b0ea5',
21 'timestamp': 1565965194,
22 'upload_date': '20190816',
25 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
26 'only_matching': True,
28 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/plugin-20190404-1/',
29 'only_matching': True,
31 'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
32 'only_matching': True,
34 _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json'
36 def _real_extract(self, url):
37 lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
38 if episode_id.isdigit():
39 episode_id = episode_id[:4] + '-' + episode_id[4:]
41 is_video = m_type == 'video'
42 episode = self._download_json(
43 self._API_URL_TEMPLATE % (
44 'v' if is_video else 'r',
45 'clip' if episode_id[:4] == '9999' else 'esd',
46 episode_id, lang, '/all' if is_video else ''),
47 episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0]
48 title = episode.get('sub_title_clean') or episode['sub_title']
50 def get_clean_field(key):
51 return episode.get(key + '_clean') or episode.get(key)
53 series = get_clean_field('title')
56 for s, w, h in [('', 640, 360), ('_l', 1280, 720)]:
57 img_path = episode.get('image' + s)
64 'url': 'https://www3.nhk.or.jp' + img_path,
68 'id': episode_id + '-' + lang,
69 'title': '%s - %s' % (series, title) if series and title else title,
70 'description': get_clean_field('description'),
71 'thumbnails': thumbnails,
77 '_type': 'url_transparent',
79 'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + episode['vod_id'],
82 audio = episode['audio']
83 audio_path = audio['audio']
84 info['formats'] = self._extract_m3u8_formats(
85 'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
86 episode_id, 'm4a', m3u8_id='hls', fatal=False)
87 for proto in ('rtmpt', 'rtmp'):
88 info['formats'].append({
91 'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path),
94 for f in info['formats']: