yt_dlp/extractor/dropout.py

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