2 from __future__ import unicode_literals
6 from .common import InfoExtractor
13 class PokemonIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/[^/]+/\d+_\d+-(?P<display_id>[^/?#]+))'
16 'url': 'http://www.pokemon.com/us/pokemon-episodes/19_01-from-a-to-z/?play=true',
17 'md5': '9fb209ae3a569aac25de0f5afc4ee08f',
19 'id': 'd0436c00c3ce4071ac6cee8130ac54a1',
21 'title': 'From A to Z!',
22 'description': 'Bonnie makes a new friend, Ash runs into an old friend, and a terrifying premonition begins to unfold!',
23 'timestamp': 1460478136,
24 'upload_date': '20160412',
26 'add_id': ['LimelightMedia']
28 'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
29 'only_matching': True,
31 'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
32 'only_matching': True,
34 'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
35 'only_matching': True,
38 def _real_extract(self, url):
39 video_id, display_id = re.match(self._VALID_URL, url).groups()
40 webpage = self._download_webpage(url, video_id or display_id)
41 video_data = extract_attributes(self._search_regex(
42 r'(<[^>]+data-video-id="%s"[^>]*>)' % (video_id if video_id else '[a-z0-9]{32}'),
43 webpage, 'video data element'))
44 video_id = video_data['data-video-id']
45 title = video_data['data-video-title']
47 '_type': 'url_transparent',
49 'url': 'limelight:media:%s' % video_id,
51 'description': video_data.get('data-video-summary'),
52 'thumbnail': video_data.get('data-video-poster'),
54 'season_number': int_or_none(video_data.get('data-video-season')),
56 'episode_number': int_or_none(video_data.get('data-video-episode')),
57 'ie_key': 'LimelightMedia',