yt_dlp/extractor/dropout.py

   1 from .common import InfoExtractor
   2 from .vimeo import VHXEmbedIE
   3 from ..utils import (
   4     ExtractorError,
   5     clean_html,
   6     get_element_by_class,
   7     get_element_by_id,
   8     get_elements_by_class,
   9     int_or_none,
  10     join_nonempty,
  11     unified_strdate,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class DropoutIE(InfoExtractor):
  17     _LOGIN_URL = 'https://www.dropout.tv/login'
  18     _NETRC_MACHINE = 'dropout'
  19
  20     _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
  21     _TESTS = [
  22         {
  23             'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
  24             'note': 'Episode in a series',
  25             'md5': '5e000fdfd8d8fa46ff40456f1c2af04a',
  26             'info_dict': {
  27                 'id': '738153',
  28                 'display_id': 'yes-or-no',
  29                 'ext': 'mp4',
  30                 'title': 'Yes or No',
  31                 'description': 'Ally, Brennan, and Zac are asked a simple question, but is there a correct answer?',
  32                 'release_date': '20200508',
  33                 'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/351e3f24-c4a3-459a-8b79-dc80f1e5b7fd.jpg',
  34                 'series': 'Game Changer',
  35                 'season_number': 2,
  36                 'season': 'Season 2',
  37                 'episode_number': 6,
  38                 'episode': 'Yes or No',
  39                 'duration': 1180,
  40                 'uploader_id': 'user80538407',
  41                 'uploader_url': 'https://vimeo.com/user80538407',
  42                 'uploader': 'OTT Videos'
  43             },
  44             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
  45         },
  46         {
  47             'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1/videos/episode-1',
  48             'note': 'Episode in a series (missing release_date)',
  49             'md5': '712caf7c191f1c47c8f1879520c2fa5c',
  50             'info_dict': {
  51                 'id': '320562',
  52                 'display_id': 'episode-1',
  53                 'ext': 'mp4',
  54                 'title': 'The Beginning Begins',
  55                 'description': 'The cast introduces their PCs, including a neurotic elf, a goblin PI, and a corn-worshipping cleric.',
  56                 'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/4421ed0d-f630-4c88-9004-5251b2b8adfa.jpg',
  57                 'series': 'Dimension 20: Fantasy High',
  58                 'season_number': 1,
  59                 'season': 'Season 1',
  60                 'episode_number': 1,
  61                 'episode': 'The Beginning Begins',
  62                 'duration': 6838,
  63                 'uploader_id': 'user80538407',
  64                 'uploader_url': 'https://vimeo.com/user80538407',
  65                 'uploader': 'OTT Videos'
  66             },
  67             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
  68         },
  69         {
  70             'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
  71             'note': 'Episode not in a series',
  72             'md5': 'c30fa18999c5880d156339f13c953a26',
  73             'info_dict': {
  74                 'id': '1915774',
  75                 'display_id': 'misfits-magic-holiday-special',
  76                 'ext': 'mp4',
  77                 'title': 'Misfits & Magic Holiday Special',
  78                 'description': 'The magical misfits spend Christmas break at Gowpenny, with an unwelcome visitor.',
  79                 'release_date': '20211215',
  80                 'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/d91ea8a6-b250-42ed-907e-b30fb1c65176-8e24b8e5.jpg',
  81                 'duration': 11698,
  82                 'uploader_id': 'user80538407',
  83                 'uploader_url': 'https://vimeo.com/user80538407',
  84                 'uploader': 'OTT Videos'
  85             },
  86             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
  87         }
  88     ]
  89
  90     def _get_authenticity_token(self, display_id):
  91         signin_page = self._download_webpage(
  92             self._LOGIN_URL, display_id, note='Getting authenticity token')
  93         return self._html_search_regex(
  94             r'name=["\']authenticity_token["\'] value=["\'](.+?)["\']',
  95             signin_page, 'authenticity_token')
  96
  97     def _login(self, display_id):
  98         username, password = self._get_login_info()
  99         if not username:
 100             return True
 101
 102         response = self._download_webpage(
 103             self._LOGIN_URL, display_id, note='Logging in', fatal=False,
 104             data=urlencode_postdata({
 105                 'email': username,
 106                 'password': password,
 107                 'authenticity_token': self._get_authenticity_token(display_id),
 108                 'utf8': True
 109             }))
 110
 111         user_has_subscription = self._search_regex(
 112             r'user_has_subscription:\s*["\'](.+?)["\']', response, 'subscription status', default='none')
 113         if user_has_subscription.lower() == 'true':
 114             return
 115         elif user_has_subscription.lower() == 'false':
 116             return 'Account is not subscribed'
 117         else:
 118             return 'Incorrect username/password'
 119
 120     def _real_extract(self, url):
 121         display_id = self._match_id(url)
 122
 123         webpage = None
 124         if self._get_cookies('https://www.dropout.tv').get('_session'):
 125             webpage = self._download_webpage(url, display_id)
 126         if not webpage or '<div id="watch-unauthorized"' in webpage:
 127             login_err = self._login(display_id)
 128             webpage = self._download_webpage(url, display_id)
 129             if login_err and '<div id="watch-unauthorized"' in webpage:
 130                 if login_err is True:
 131                     self.raise_login_required(method='any')
 132                 raise ExtractorError(login_err, expected=True)
 133
 134         embed_url = self._search_regex(r'embed_url:\s*["\'](.+?)["\']', webpage, 'embed url')
 135         thumbnail = self._og_search_thumbnail(webpage)
 136         watch_info = get_element_by_id('watch-info', webpage) or ''
 137
 138         title = clean_html(get_element_by_class('video-title', watch_info))
 139         season_episode = get_element_by_class(
 140             'site-font-secondary-color', get_element_by_class('text', watch_info))
 141         episode_number = int_or_none(self._search_regex(
 142             r'Episode (\d+)', season_episode or '', 'episode', default=None))
 143
 144         return {
 145             '_type': 'url_transparent',
 146             'ie_key': VHXEmbedIE.ie_key(),
 147             'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
 148             'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
 149             'display_id': display_id,
 150             'title': title,
 151             'description': self._html_search_meta('description', webpage, fatal=False),
 152             'thumbnail': thumbnail.split('?')[0] if thumbnail else None,  # Ignore crop/downscale
 153             'series': clean_html(get_element_by_class('series-title', watch_info)),
 154             'episode_number': episode_number,
 155             'episode': title if episode_number else None,
 156             'season_number': int_or_none(self._search_regex(
 157                 r'Season (\d+),', season_episode or '', 'season', default=None)),
 158             'release_date': unified_strdate(self._search_regex(
 159                 r'data-meta-field-name=["\']release_dates["\'] data-meta-field-value=["\'](.+?)["\']',
 160                 watch_info, 'release date', default=None)),
 161         }
 162
 163
 164 class DropoutSeasonIE(InfoExtractor):
 165     _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:[0-9]+/?$)'
 166     _TESTS = [
 167         {
 168             'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
 169             'note': 'Multi-season series with the season in the url',
 170             'playlist_count': 17,
 171             'info_dict': {
 172                 'id': 'dimension-20-fantasy-high-season-1',
 173                 'title': 'Dimension 20 Fantasy High - Season 1'
 174             }
 175         },
 176         {
 177             'url': 'https://www.dropout.tv/dimension-20-fantasy-high',
 178             'note': 'Multi-season series with the season not in the url',
 179             'playlist_count': 17,
 180             'info_dict': {
 181                 'id': 'dimension-20-fantasy-high-season-1',
 182                 'title': 'Dimension 20 Fantasy High - Season 1'
 183             }
 184         },
 185         {
 186             'url': 'https://www.dropout.tv/dimension-20-shriek-week',
 187             'note': 'Single-season series',
 188             'playlist_count': 4,
 189             'info_dict': {
 190                 'id': 'dimension-20-shriek-week-season-1',
 191                 'title': 'Dimension 20 Shriek Week - Season 1'
 192             }
 193         }
 194     ]
 195
 196     def _real_extract(self, url):
 197         season_id = self._match_id(url)
 198         season_title = season_id.replace('-', ' ').title()
 199         webpage = self._download_webpage(url, season_id)
 200
 201         entries = [
 202             self.url_result(
 203                 url=self._search_regex(r'<a href=["\'](.+?)["\'] class=["\']browse-item-link["\']',
 204                                        item, 'item_url'),
 205                 ie=DropoutIE.ie_key()
 206             ) for item in get_elements_by_class('js-collection-item', webpage)
 207         ]
 208
 209         seasons = (get_element_by_class('select-dropdown-wrapper', webpage) or '').strip().replace('\n', '')
 210         current_season = self._search_regex(r'<option[^>]+selected>([^<]+)</option>',
 211                                             seasons, 'current_season', default='').strip()
 212
 213         return {
 214             '_type': 'playlist',
 215             'id': join_nonempty(season_id, current_season.lower().replace(' ', '-')),
 216             'title': join_nonempty(season_title, current_season, delim=' - '),
 217             'entries': entries
 218         }