yt_dlp/extractor/rottentomatoes.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     clean_html,
   5     float_or_none,
   6     get_element_by_class,
   7     join_nonempty,
   8     traverse_obj,
   9     url_or_none,
  10 )
  11
  12
  13 class RottenTomatoesIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?rottentomatoes\.com/m/(?P<playlist>[^/]+)(?:/(?P<tr>trailers)(?:/(?P<id>\w+))?)?'
  15
  16     _TESTS = [{
  17         'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
  18         'info_dict': {
  19             'id': '11028566',
  20             'ext': 'mp4',
  21             'title': 'Toy Story 3',
  22             'description': 'From the creators of the beloved TOY STORY films, comes a story that will reunite the gang in a whole new way.',
  23         },
  24         'skip': 'No longer available',
  25     }, {
  26         'url': 'https://www.rottentomatoes.com/m/toy_story_3/trailers/VycaVoBKhGuk',
  27         'info_dict': {
  28             'id': 'VycaVoBKhGuk',
  29             'ext': 'mp4',
  30             'title': 'Toy Story 3: Trailer 2',
  31             'description': '',
  32             'thumbnail': r're:^https?://.*\.jpg$',
  33             'duration': 149.941,
  34         },
  35     }, {
  36         'url': 'http://www.rottentomatoes.com/m/toy_story_3',
  37         'info_dict': {
  38             'id': 'toy_story_3',
  39             'title': 'Toy Story 3',
  40         },
  41         'playlist_mincount': 4,
  42     }, {
  43         'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers',
  44         'info_dict': {
  45             'id': 'toy_story_3-trailers',
  46         },
  47         'playlist_mincount': 5,
  48     }]
  49
  50     def _extract_videos(self, data, display_id):
  51         for video in traverse_obj(data, (lambda _, v: v['publicId'] and v['file'] and v['type'] == 'hls')):
  52             yield {
  53                 'formats': self._extract_m3u8_formats(
  54                     video['file'], display_id, 'mp4', m3u8_id='hls', fatal=False),
  55                 **traverse_obj(video, {
  56                     'id': 'publicId',
  57                     'title': 'title',
  58                     'description': 'description',
  59                     'duration': ('durationInSeconds', {float_or_none}),
  60                     'thumbnail': ('image', {url_or_none}),
  61                 }),
  62             }
  63
  64     def _real_extract(self, url):
  65         playlist_id, trailers, video_id = self._match_valid_url(url).group('playlist', 'tr', 'id')
  66         playlist_id = join_nonempty(playlist_id, trailers)
  67         webpage = self._download_webpage(url, playlist_id)
  68         data = self._search_json(
  69             r'<script[^>]+\bid=["\'](?:heroV|v)ideos["\'][^>]*>', webpage,
  70             'data', playlist_id, contains_pattern=r'\[{(?s:.+)}\]')
  71
  72         if video_id:
  73             video_data = traverse_obj(data, lambda _, v: v['publicId'] == video_id)
  74             if not video_data:
  75                 raise ExtractorError('Unable to extract video from webpage')
  76             return next(self._extract_videos(video_data, video_id))
  77
  78         return self.playlist_result(
  79             self._extract_videos(data, playlist_id), playlist_id,
  80             clean_html(get_element_by_class('scoreboard__title', webpage)))