yt_dlp/extractor/pokemon.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     extract_attributes,
   5     int_or_none,
   6     js_to_json,
   7     merge_dicts,
   8 )
   9
  10
  11 class PokemonIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/(?:[^/]+/)+(?P<display_id>[^/?#&]+))'
  13     _TESTS = [{
  14         'url': 'https://www.pokemon.com/us/pokemon-episodes/20_30-the-ol-raise-and-switch/',
  15         'md5': '2fe8eaec69768b25ef898cda9c43062e',
  16         'info_dict': {
  17             'id': 'afe22e30f01c41f49d4f1d9eab5cd9a4',
  18             'ext': 'mp4',
  19             'title': 'The Ol’ Raise and Switch!',
  20             'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
  21         },
  22         'add_id': ['LimelightMedia'],
  23     }, {
  24         # no data-video-title
  25         'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
  26         'info_dict': {
  27             'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
  28             'ext': 'mp4',
  29             'title': "Pokémon : L'ascension de Darkrai",
  30             'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
  31         },
  32         'add_id': ['LimelightMedia'],
  33         'params': {
  34             'skip_download': True,
  35         },
  36     }, {
  37         'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id, display_id = self._match_valid_url(url).groups()
  49         webpage = self._download_webpage(url, video_id or display_id)
  50         video_data = extract_attributes(self._search_regex(
  51             r'(<[^>]+data-video-id="{}"[^>]*>)'.format(video_id if video_id else '[a-z0-9]{32}'),
  52             webpage, 'video data element'))
  53         video_id = video_data['data-video-id']
  54         title = video_data.get('data-video-title') or self._html_search_meta(
  55             'pkm-title', webpage, ' title', default=None) or self._search_regex(
  56             r'<h1[^>]+\bclass=["\']us-title[^>]+>([^<]+)', webpage, 'title')
  57         return {
  58             '_type': 'url_transparent',
  59             'id': video_id,
  60             'url': f'limelight:media:{video_id}',
  61             'title': title,
  62             'description': video_data.get('data-video-summary'),
  63             'thumbnail': video_data.get('data-video-poster'),
  64             'series': 'Pokémon',
  65             'season_number': int_or_none(video_data.get('data-video-season')),
  66             'episode': title,
  67             'episode_number': int_or_none(video_data.get('data-video-episode')),
  68             'ie_key': 'LimelightMedia',
  69         }
  70
  71
  72 class PokemonWatchIE(InfoExtractor):
  73     _VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
  74     _API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
  75     _TESTS = [{
  76         'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
  77         'md5': '62833938a31e61ab49ada92f524c42ff',
  78         'info_dict': {
  79             'id': '8309a40969894a8e8d5bc1311e9c5667',
  80             'ext': 'mp4',
  81             'title': 'Lillier and the Staff!',
  82             'description': 'md5:338841b8c21b283d24bdc9b568849f04',
  83         },
  84     }, {
  85         'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
  86         'only_matching': True,
  87     }, {
  88         'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
  89         'only_matching': True,
  90     }]
  91
  92     def _extract_media(self, channel_array, video_id):
  93         for channel in channel_array:
  94             for media in channel.get('media'):
  95                 if media.get('id') == video_id:
  96                     return media
  97         return None
  98
  99     def _real_extract(self, url):
 100         video_id = self._match_id(url)
 101
 102         info = {
 103             '_type': 'url',
 104             'id': video_id,
 105             'url': f'limelight:media:{video_id}',
 106             'ie_key': 'LimelightMedia',
 107         }
 108
 109         # API call can be avoided entirely if we are listing formats
 110         if self.get_param('listformats', False):
 111             return info
 112
 113         webpage = self._download_webpage(url, video_id)
 114         build_vars = self._parse_json(self._search_regex(
 115             r'(?s)buildVars\s*=\s*({.*?})', webpage, 'build vars'),
 116             video_id, transform_source=js_to_json)
 117         region = build_vars.get('region')
 118         channel_array = self._download_json(self._API_URL.format(region), video_id)
 119         video_data = self._extract_media(channel_array, video_id)
 120
 121         if video_data is None:
 122             raise ExtractorError(
 123                 f'Video {video_id} does not exist', expected=True)
 124
 125         info['_type'] = 'url_transparent'
 126         images = video_data.get('images')
 127
 128         return merge_dicts(info, {
 129             'title': video_data.get('title'),
 130             'description': video_data.get('description'),
 131             'thumbnail': images.get('medium') or images.get('small'),
 132             'series': 'Pokémon',
 133             'season_number': int_or_none(video_data.get('season')),
 134             'episode': video_data.get('title'),
 135             'episode_number': int_or_none(video_data.get('episode')),
 136         })