yt_dlp/extractor/dropout.py

   1 import functools
   2
   3 from .common import InfoExtractor
   4 from .vimeo import VHXEmbedIE
   5 from ..utils import (
   6     ExtractorError,
   7     OnDemandPagedList,
   8     clean_html,
   9     extract_attributes,
  10     get_element_by_class,
  11     get_element_by_id,
  12     get_elements_html_by_class,
  13     int_or_none,
  14     traverse_obj,
  15     unified_strdate,
  16     urlencode_postdata,
  17 )
  18
  19
  20 class DropoutIE(InfoExtractor):
  21     _LOGIN_URL = 'https://www.dropout.tv/login'
  22     _NETRC_MACHINE = 'dropout'
  23
  24     _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
  25     _TESTS = [
  26         {
  27             'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
  28             'note': 'Episode in a series',
  29             'md5': '5e000fdfd8d8fa46ff40456f1c2af04a',
  30             'info_dict': {
  31                 'id': '738153',
  32                 'display_id': 'yes-or-no',
  33                 'ext': 'mp4',
  34                 'title': 'Yes or No',
  35                 'description': 'Ally, Brennan, and Zac are asked a simple question, but is there a correct answer?',
  36                 'release_date': '20200508',
  37                 'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/351e3f24-c4a3-459a-8b79-dc80f1e5b7fd.jpg',
  38                 'series': 'Game Changer',
  39                 'season_number': 2,
  40                 'season': 'Season 2',
  41                 'episode_number': 6,
  42                 'episode': 'Yes or No',
  43                 'duration': 1180,
  44                 'uploader_id': 'user80538407',
  45                 'uploader_url': 'https://vimeo.com/user80538407',
  46                 'uploader': 'OTT Videos',
  47             },
  48             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
  49         },
  50         {
  51             'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1/videos/episode-1',
  52             'note': 'Episode in a series (missing release_date)',
  53             'md5': '712caf7c191f1c47c8f1879520c2fa5c',
  54             'info_dict': {
  55                 'id': '320562',
  56                 'display_id': 'episode-1',
  57                 'ext': 'mp4',
  58                 'title': 'The Beginning Begins',
  59                 'description': 'The cast introduces their PCs, including a neurotic elf, a goblin PI, and a corn-worshipping cleric.',
  60                 'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/4421ed0d-f630-4c88-9004-5251b2b8adfa.jpg',
  61                 'series': 'Dimension 20: Fantasy High',
  62                 'season_number': 1,
  63                 'season': 'Season 1',
  64                 'episode_number': 1,
  65                 'episode': 'The Beginning Begins',
  66                 'duration': 6838,
  67                 'uploader_id': 'user80538407',
  68                 'uploader_url': 'https://vimeo.com/user80538407',
  69                 'uploader': 'OTT Videos',
  70             },
  71             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
  72         },
  73         {
  74             'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
  75             'note': 'Episode not in a series',
  76             'md5': 'c30fa18999c5880d156339f13c953a26',
  77             'info_dict': {
  78                 'id': '1915774',
  79                 'display_id': 'misfits-magic-holiday-special',
  80                 'ext': 'mp4',
  81                 'title': 'Misfits & Magic Holiday Special',
  82                 'description': 'The magical misfits spend Christmas break at Gowpenny, with an unwelcome visitor.',
  83                 'release_date': '20211215',
  84                 'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/d91ea8a6-b250-42ed-907e-b30fb1c65176-8e24b8e5.jpg',
  85                 'duration': 11698,
  86                 'uploader_id': 'user80538407',
  87                 'uploader_url': 'https://vimeo.com/user80538407',
  88                 'uploader': 'OTT Videos',
  89             },
  90             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
  91         },
  92     ]
  93
  94     def _get_authenticity_token(self, display_id):
  95         signin_page = self._download_webpage(
  96             self._LOGIN_URL, display_id, note='Getting authenticity token')
  97         return self._html_search_regex(
  98             r'name=["\']authenticity_token["\'] value=["\'](.+?)["\']',
  99             signin_page, 'authenticity_token')
 100
 101     def _login(self, display_id):
 102         username, password = self._get_login_info()
 103         if not username:
 104             return True
 105
 106         response = self._download_webpage(
 107             self._LOGIN_URL, display_id, note='Logging in', fatal=False,
 108             data=urlencode_postdata({
 109                 'email': username,
 110                 'password': password,
 111                 'authenticity_token': self._get_authenticity_token(display_id),
 112                 'utf8': True,
 113             }))
 114
 115         user_has_subscription = self._search_regex(
 116             r'user_has_subscription:\s*["\'](.+?)["\']', response, 'subscription status', default='none')
 117         if user_has_subscription.lower() == 'true':
 118             return
 119         elif user_has_subscription.lower() == 'false':
 120             return 'Account is not subscribed'
 121         else:
 122             return 'Incorrect username/password'
 123
 124     def _real_extract(self, url):
 125         display_id = self._match_id(url)
 126
 127         webpage = None
 128         if self._get_cookies('https://www.dropout.tv').get('_session'):
 129             webpage = self._download_webpage(url, display_id)
 130         if not webpage or '<div id="watch-unauthorized"' in webpage:
 131             login_err = self._login(display_id)
 132             webpage = self._download_webpage(url, display_id)
 133             if login_err and '<div id="watch-unauthorized"' in webpage:
 134                 if login_err is True:
 135                     self.raise_login_required(method='any')
 136                 raise ExtractorError(login_err, expected=True)
 137
 138         embed_url = self._search_regex(r'embed_url:\s*["\'](.+?)["\']', webpage, 'embed url')
 139         thumbnail = self._og_search_thumbnail(webpage)
 140         watch_info = get_element_by_id('watch-info', webpage) or ''
 141
 142         title = clean_html(get_element_by_class('video-title', watch_info))
 143         season_episode = get_element_by_class(
 144             'site-font-secondary-color', get_element_by_class('text', watch_info))
 145         episode_number = int_or_none(self._search_regex(
 146             r'Episode (\d+)', season_episode or '', 'episode', default=None))
 147
 148         return {
 149             '_type': 'url_transparent',
 150             'ie_key': VHXEmbedIE.ie_key(),
 151             'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
 152             'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
 153             'display_id': display_id,
 154             'title': title,
 155             'description': self._html_search_meta('description', webpage, fatal=False),
 156             'thumbnail': thumbnail.split('?')[0] if thumbnail else None,  # Ignore crop/downscale
 157             'series': clean_html(get_element_by_class('series-title', watch_info)),
 158             'episode_number': episode_number,
 159             'episode': title if episode_number else None,
 160             'season_number': int_or_none(self._search_regex(
 161                 r'Season (\d+),', season_episode or '', 'season', default=None)),
 162             'release_date': unified_strdate(self._search_regex(
 163                 r'data-meta-field-name=["\']release_dates["\'] data-meta-field-value=["\'](.+?)["\']',
 164                 watch_info, 'release date', default=None)),
 165         }
 166
 167
 168 class DropoutSeasonIE(InfoExtractor):
 169     _PAGE_SIZE = 24
 170     _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
 171     _TESTS = [
 172         {
 173             'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
 174             'note': 'Multi-season series with the season in the url',
 175             'playlist_count': 24,
 176             'info_dict': {
 177                 'id': 'dimension-20-fantasy-high-season-1',
 178                 'title': 'Dimension 20 Fantasy High - Season 1',
 179             },
 180         },
 181         {
 182             'url': 'https://www.dropout.tv/dimension-20-fantasy-high',
 183             'note': 'Multi-season series with the season not in the url',
 184             'playlist_count': 24,
 185             'info_dict': {
 186                 'id': 'dimension-20-fantasy-high-season-1',
 187                 'title': 'Dimension 20 Fantasy High - Season 1',
 188             },
 189         },
 190         {
 191             'url': 'https://www.dropout.tv/dimension-20-shriek-week',
 192             'note': 'Single-season series',
 193             'playlist_count': 4,
 194             'info_dict': {
 195                 'id': 'dimension-20-shriek-week-season-1',
 196                 'title': 'Dimension 20 Shriek Week - Season 1',
 197             },
 198         },
 199         {
 200             'url': 'https://www.dropout.tv/breaking-news-no-laugh-newsroom/season:3',
 201             'note': 'Multi-season series with season in the url that requires pagination',
 202             'playlist_count': 25,
 203             'info_dict': {
 204                 'id': 'breaking-news-no-laugh-newsroom-season-3',
 205                 'title': 'Breaking News No Laugh Newsroom - Season 3',
 206             },
 207         },
 208     ]
 209
 210     def _fetch_page(self, url, season_id, page):
 211         page += 1
 212         webpage = self._download_webpage(
 213             f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
 214         yield from [self.url_result(item_url, DropoutIE) for item_url in traverse_obj(
 215             get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
 216
 217     def _real_extract(self, url):
 218         season_id = self._match_id(url)
 219         season_num = self._match_valid_url(url).group('season') or 1
 220         season_title = season_id.replace('-', ' ').title()
 221
 222         return self.playlist_result(
 223             OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
 224             f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')