yt_dlp/extractor/animelab.py

   1 from .common import InfoExtractor
   2
   3 from ..utils import (
   4     ExtractorError,
   5     urlencode_postdata,
   6     int_or_none,
   7     str_or_none,
   8     determine_ext,
   9 )
  10
  11 from ..compat import compat_HTTPError
  12
  13
  14 class AnimeLabBaseIE(InfoExtractor):
  15     _LOGIN_URL = 'https://www.animelab.com/login'
  16     _NETRC_MACHINE = 'animelab'
  17     _LOGGED_IN = False
  18
  19     def _is_logged_in(self, login_page=None):
  20         if not self._LOGGED_IN:
  21             if not login_page:
  22                 login_page = self._download_webpage(self._LOGIN_URL, None, 'Downloading login page')
  23             AnimeLabBaseIE._LOGGED_IN = 'Sign In' not in login_page
  24         return self._LOGGED_IN
  25
  26     def _perform_login(self, username, password):
  27         if self._is_logged_in():
  28             return
  29
  30         login_form = {
  31             'email': username,
  32             'password': password,
  33         }
  34
  35         try:
  36             response = self._download_webpage(
  37                 self._LOGIN_URL, None, 'Logging in', 'Wrong login info',
  38                 data=urlencode_postdata(login_form),
  39                 headers={'Content-Type': 'application/x-www-form-urlencoded'})
  40         except ExtractorError as e:
  41             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
  42                 raise ExtractorError('Unable to log in (wrong credentials?)', expected=True)
  43             raise
  44
  45         if not self._is_logged_in(response):
  46             raise ExtractorError('Unable to login (cannot verify if logged in)')
  47
  48     def _real_initialize(self):
  49         if not self._is_logged_in():
  50             self.raise_login_required('Login is required to access any AnimeLab content')
  51
  52
  53 class AnimeLabIE(AnimeLabBaseIE):
  54     _VALID_URL = r'https?://(?:www\.)?animelab\.com/player/(?P<id>[^/]+)'
  55
  56     _TEST = {
  57         'url': 'https://www.animelab.com/player/fullmetal-alchemist-brotherhood-episode-42',
  58         'md5': '05bde4b91a5d1ff46ef5b94df05b0f7f',
  59         'info_dict': {
  60             'id': '383',
  61             'ext': 'mp4',
  62             'display_id': 'fullmetal-alchemist-brotherhood-episode-42',
  63             'title': 'Fullmetal Alchemist: Brotherhood - Episode 42 - Signs of a Counteroffensive',
  64             'description': 'md5:103eb61dd0a56d3dfc5dbf748e5e83f4',
  65             'series': 'Fullmetal Alchemist: Brotherhood',
  66             'episode': 'Signs of a Counteroffensive',
  67             'episode_number': 42,
  68             'duration': 1469,
  69             'season': 'Season 1',
  70             'season_number': 1,
  71             'season_id': '38',
  72         },
  73         'params': {
  74             # Ensure the same video is downloaded whether the user is premium or not
  75             'format': '[format_id=21711_yeshardsubbed_ja-JP][height=480]',
  76         },
  77     }
  78
  79     def _real_extract(self, url):
  80         display_id = self._match_id(url)
  81
  82         # unfortunately we can get different URLs for the same formats
  83         # e.g. if we are using a "free" account so no dubs available
  84         # (so _remove_duplicate_formats is not effective)
  85         # so we use a dictionary as a workaround
  86         formats = {}
  87         for language_option_url in ('https://www.animelab.com/player/%s/subtitles',
  88                                     'https://www.animelab.com/player/%s/dubbed'):
  89             actual_url = language_option_url % display_id
  90             webpage = self._download_webpage(actual_url, display_id, 'Downloading URL ' + actual_url)
  91
  92             video_collection = self._parse_json(self._search_regex(r'new\s+?AnimeLabApp\.VideoCollection\s*?\((.*?)\);', webpage, 'AnimeLab VideoCollection'), display_id)
  93             position = int_or_none(self._search_regex(r'playlistPosition\s*?=\s*?(\d+)', webpage, 'Playlist Position'))
  94
  95             raw_data = video_collection[position]['videoEntry']
  96
  97             video_id = str_or_none(raw_data['id'])
  98
  99             # create a title from many sources (while grabbing other info)
 100             # TODO use more fallback sources to get some of these
 101             series = raw_data.get('showTitle')
 102             video_type = raw_data.get('videoEntryType', {}).get('name')
 103             episode_number = raw_data.get('episodeNumber')
 104             episode_name = raw_data.get('name')
 105
 106             title_parts = (series, video_type, episode_number, episode_name)
 107             if None not in title_parts:
 108                 title = '%s - %s %s - %s' % title_parts
 109             else:
 110                 title = episode_name
 111
 112             description = raw_data.get('synopsis') or self._og_search_description(webpage, default=None)
 113
 114             duration = int_or_none(raw_data.get('duration'))
 115
 116             thumbnail_data = raw_data.get('images', [])
 117             thumbnails = []
 118             for thumbnail in thumbnail_data:
 119                 for instance in thumbnail['imageInstances']:
 120                     image_data = instance.get('imageInfo', {})
 121                     thumbnails.append({
 122                         'id': str_or_none(image_data.get('id')),
 123                         'url': image_data.get('fullPath'),
 124                         'width': image_data.get('width'),
 125                         'height': image_data.get('height'),
 126                     })
 127
 128             season_data = raw_data.get('season', {}) or {}
 129             season = str_or_none(season_data.get('name'))
 130             season_number = int_or_none(season_data.get('seasonNumber'))
 131             season_id = str_or_none(season_data.get('id'))
 132
 133             for video_data in raw_data['videoList']:
 134                 current_video_list = {}
 135                 current_video_list['language'] = video_data.get('language', {}).get('languageCode')
 136
 137                 is_hardsubbed = video_data.get('hardSubbed')
 138
 139                 for video_instance in video_data['videoInstances']:
 140                     httpurl = video_instance.get('httpUrl')
 141                     url = httpurl if httpurl else video_instance.get('rtmpUrl')
 142                     if url is None:
 143                         # this video format is unavailable to the user (not premium etc.)
 144                         continue
 145
 146                     current_format = current_video_list.copy()
 147
 148                     format_id_parts = []
 149
 150                     format_id_parts.append(str_or_none(video_instance.get('id')))
 151
 152                     if is_hardsubbed is not None:
 153                         if is_hardsubbed:
 154                             format_id_parts.append('yeshardsubbed')
 155                         else:
 156                             format_id_parts.append('nothardsubbed')
 157
 158                     format_id_parts.append(current_format['language'])
 159
 160                     format_id = '_'.join([x for x in format_id_parts if x is not None])
 161
 162                     ext = determine_ext(url)
 163                     if ext == 'm3u8':
 164                         for format_ in self._extract_m3u8_formats(
 165                                 url, video_id, m3u8_id=format_id, fatal=False):
 166                             formats[format_['format_id']] = format_
 167                         continue
 168                     elif ext == 'mpd':
 169                         for format_ in self._extract_mpd_formats(
 170                                 url, video_id, mpd_id=format_id, fatal=False):
 171                             formats[format_['format_id']] = format_
 172                         continue
 173
 174                     current_format['url'] = url
 175                     quality_data = video_instance.get('videoQuality')
 176                     if quality_data:
 177                         quality = quality_data.get('name') or quality_data.get('description')
 178                     else:
 179                         quality = None
 180
 181                     height = None
 182                     if quality:
 183                         height = int_or_none(self._search_regex(r'(\d+)p?$', quality, 'Video format height', default=None))
 184
 185                     if height is None:
 186                         self.report_warning('Could not get height of video')
 187                     else:
 188                         current_format['height'] = height
 189                     current_format['format_id'] = format_id
 190
 191                     formats[current_format['format_id']] = current_format
 192
 193         formats = list(formats.values())
 194         self._sort_formats(formats)
 195
 196         return {
 197             'id': video_id,
 198             'display_id': display_id,
 199             'title': title,
 200             'description': description,
 201             'series': series,
 202             'episode': episode_name,
 203             'episode_number': int_or_none(episode_number),
 204             'thumbnails': thumbnails,
 205             'duration': duration,
 206             'formats': formats,
 207             'season': season,
 208             'season_number': season_number,
 209             'season_id': season_id,
 210         }
 211
 212
 213 class AnimeLabShowsIE(AnimeLabBaseIE):
 214     _VALID_URL = r'https?://(?:www\.)?animelab\.com/shows/(?P<id>[^/]+)'
 215
 216     _TEST = {
 217         'url': 'https://www.animelab.com/shows/attack-on-titan',
 218         'info_dict': {
 219             'id': '45',
 220             'title': 'Attack on Titan',
 221             'description': 'md5:989d95a2677e9309368d5cf39ba91469',
 222         },
 223         'playlist_count': 59,
 224         'skip': 'All AnimeLab content requires authentication',
 225     }
 226
 227     def _real_extract(self, url):
 228         _BASE_URL = 'http://www.animelab.com'
 229         _SHOWS_API_URL = '/api/videoentries/show/videos/'
 230         display_id = self._match_id(url)
 231
 232         webpage = self._download_webpage(url, display_id, 'Downloading requested URL')
 233
 234         show_data_str = self._search_regex(r'({"id":.*}),\svideoEntry', webpage, 'AnimeLab show data')
 235         show_data = self._parse_json(show_data_str, display_id)
 236
 237         show_id = str_or_none(show_data.get('id'))
 238         title = show_data.get('name')
 239         description = show_data.get('shortSynopsis') or show_data.get('longSynopsis')
 240
 241         entries = []
 242         for season in show_data['seasons']:
 243             season_id = season['id']
 244             get_data = urlencode_postdata({
 245                 'seasonId': season_id,
 246                 'limit': 1000,
 247             })
 248             # despite using urlencode_postdata, we are sending a GET request
 249             target_url = _BASE_URL + _SHOWS_API_URL + show_id + "?" + get_data.decode('utf-8')
 250             response = self._download_webpage(
 251                 target_url,
 252                 None, 'Season id %s' % season_id)
 253
 254             season_data = self._parse_json(response, display_id)
 255
 256             for video_data in season_data['list']:
 257                 entries.append(self.url_result(
 258                     _BASE_URL + '/player/' + video_data['slug'], 'AnimeLab',
 259                     str_or_none(video_data.get('id')), video_data.get('name')
 260                 ))
 261
 262         return {
 263             '_type': 'playlist',
 264             'id': show_id,
 265             'title': title,
 266             'description': description,
 267             'entries': entries,
 268         }
 269
 270 # TODO implement myqueue