yt_dlp/extractor/pokemon.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     extract_attributes,
   7     int_or_none,
   8     js_to_json,
   9     merge_dicts,
  10 )
  11
  12
  13 class PokemonIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/(?:[^/]+/)+(?P<display_id>[^/?#&]+))'
  15     _TESTS = [{
  16         'url': 'https://www.pokemon.com/us/pokemon-episodes/20_30-the-ol-raise-and-switch/',
  17         'md5': '2fe8eaec69768b25ef898cda9c43062e',
  18         'info_dict': {
  19             'id': 'afe22e30f01c41f49d4f1d9eab5cd9a4',
  20             'ext': 'mp4',
  21             'title': 'The Ol’ Raise and Switch!',
  22             'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
  23         },
  24         'add_id': ['LimelightMedia'],
  25     }, {
  26         # no data-video-title
  27         'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
  28         'info_dict': {
  29             'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
  30             'ext': 'mp4',
  31             'title': "Pokémon : L'ascension de Darkrai",
  32             'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
  33         },
  34         'add_id': ['LimelightMedia'],
  35         'params': {
  36             'skip_download': True,
  37         },
  38     }, {
  39         'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
  40         'only_matching': True,
  41     }, {
  42         'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
  43         'only_matching': True,
  44     }, {
  45         'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_extract(self, url):
  50         video_id, display_id = self._match_valid_url(url).groups()
  51         webpage = self._download_webpage(url, video_id or display_id)
  52         video_data = extract_attributes(self._search_regex(
  53             r'(<[^>]+data-video-id="%s"[^>]*>)' % (video_id if video_id else '[a-z0-9]{32}'),
  54             webpage, 'video data element'))
  55         video_id = video_data['data-video-id']
  56         title = video_data.get('data-video-title') or self._html_search_meta(
  57             'pkm-title', webpage, ' title', default=None) or self._search_regex(
  58             r'<h1[^>]+\bclass=["\']us-title[^>]+>([^<]+)', webpage, 'title')
  59         return {
  60             '_type': 'url_transparent',
  61             'id': video_id,
  62             'url': 'limelight:media:%s' % video_id,
  63             'title': title,
  64             'description': video_data.get('data-video-summary'),
  65             'thumbnail': video_data.get('data-video-poster'),
  66             'series': 'Pokémon',
  67             'season_number': int_or_none(video_data.get('data-video-season')),
  68             'episode': title,
  69             'episode_number': int_or_none(video_data.get('data-video-episode')),
  70             'ie_key': 'LimelightMedia',
  71         }
  72
  73
  74 class PokemonWatchIE(InfoExtractor):
  75     _VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
  76     _API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
  77     _TESTS = [{
  78         'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
  79         'md5': '62833938a31e61ab49ada92f524c42ff',
  80         'info_dict': {
  81             'id': '8309a40969894a8e8d5bc1311e9c5667',
  82             'ext': 'mp4',
  83             'title': 'Lillier and the Staff!',
  84             'description': 'md5:338841b8c21b283d24bdc9b568849f04',
  85         }
  86     }, {
  87         'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
  88         'only_matching': True
  89     }, {
  90         'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
  91         'only_matching': True
  92     }]
  93
  94     def _extract_media(self, channel_array, video_id):
  95         for channel in channel_array:
  96             for media in channel.get('media'):
  97                 if media.get('id') == video_id:
  98                     return media
  99         return None
 100
 101     def _real_extract(self, url):
 102         video_id = self._match_id(url)
 103
 104         info = {
 105             '_type': 'url',
 106             'id': video_id,
 107             'url': 'limelight:media:%s' % video_id,
 108             'ie_key': 'LimelightMedia',
 109         }
 110
 111         # API call can be avoided entirely if we are listing formats
 112         if self.get_param('listformats', False):
 113             return info
 114
 115         webpage = self._download_webpage(url, video_id)
 116         build_vars = self._parse_json(self._search_regex(
 117             r'(?s)buildVars\s*=\s*({.*?})', webpage, 'build vars'),
 118             video_id, transform_source=js_to_json)
 119         region = build_vars.get('region')
 120         channel_array = self._download_json(self._API_URL.format(region), video_id)
 121         video_data = self._extract_media(channel_array, video_id)
 122
 123         if video_data is None:
 124             raise ExtractorError(
 125                 'Video %s does not exist' % video_id, expected=True)
 126
 127         info['_type'] = 'url_transparent'
 128         images = video_data.get('images')
 129
 130         return merge_dicts(info, {
 131             'title': video_data.get('title'),
 132             'description': video_data.get('description'),
 133             'thumbnail': images.get('medium') or images.get('small'),
 134             'series': 'Pokémon',
 135             'season_number': int_or_none(video_data.get('season')),
 136             'episode': video_data.get('title'),
 137             'episode_number': int_or_none(video_data.get('episode')),
 138         })
 139
 140
 141 class PokemonSoundLibraryIE(InfoExtractor):
 142     _VALID_URL = r'https?://soundlibrary\.pokemon\.co\.jp'
 143
 144     _TESTS = [{
 145         'url': 'https://soundlibrary.pokemon.co.jp/',
 146         'info_dict': {
 147             'title': 'Pokémon Diamond and Pearl Sound Tracks',
 148         },
 149         'playlist_mincount': 149,
 150     }]
 151
 152     def _real_extract(self, url):
 153         musicbox_webpage = self._download_webpage(
 154             'https://soundlibrary.pokemon.co.jp/musicbox', None,
 155             'Downloading list of songs')
 156         song_titles = [x.group(1) for x in re.finditer(r'<span>([^>]+?)</span><br/>をてもち曲に加えます。', musicbox_webpage)]
 157         song_titles = song_titles[4::2]
 158
 159         # each songs don't have permalink; instead we return all songs at once
 160         song_entries = [{
 161             'id': f'pokemon-soundlibrary-{song_id}',
 162             'url': f'https://soundlibrary.pokemon.co.jp/api/assets/signing/sounds/wav/{song_id}.wav',
 163             # note: the server always serves MP3 files, despite its extension of the URL above
 164             'ext': 'mp3',
 165             'acodec': 'mp3',
 166             'vcodec': 'none',
 167             'title': song_title,
 168             'track': song_title,
 169             'artist': 'Nintendo / Creatures Inc. / GAME FREAK inc.',
 170             'uploader': 'Pokémon',
 171             'release_year': 2006,
 172             'release_date': '20060928',
 173             'track_number': song_id,
 174             'album': 'Pokémon Diamond and Pearl',
 175         } for song_id, song_title in enumerate(song_titles, 1)]
 176
 177         return self.playlist_result(song_entries, playlist_title='Pokémon Diamond and Pearl Sound Tracks')