yt_dlp/extractor/tubitv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..networking import Request
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     js_to_json,
   9     strip_or_none,
  10     traverse_obj,
  11     url_or_none,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class TubiTvIE(InfoExtractor):
  17     IE_NAME = 'tubitv'
  18     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
  19     _LOGIN_URL = 'http://tubitv.com/login'
  20     _NETRC_MACHINE = 'tubitv'
  21     _TESTS = [{
  22         'url': 'https://tubitv.com/movies/100004539/the-39-steps',
  23         'info_dict': {
  24             'id': '100004539',
  25             'ext': 'mp4',
  26             'title': 'The 39 Steps',
  27             'description': 'md5:bb2f2dd337f0dc58c06cb509943f54c8',
  28             'uploader_id': 'abc2558d54505d4f0f32be94f2e7108c',
  29             'release_year': 1935,
  30             'thumbnail': r're:^https?://.+\.(jpe?g|png)$',
  31             'duration': 5187,
  32         },
  33         'params': {'skip_download': 'm3u8'},
  34     }, {
  35         'url': 'https://tubitv.com/tv-shows/554628/s01-e01-rise-of-the-snakes',
  36         'info_dict': {
  37             'id': '554628',
  38             'ext': 'mp4',
  39             'title': 'S01:E01 - Rise of the Snakes',
  40             'description': 'md5:ba136f586de53af0372811e783a3f57d',
  41             'episode': 'Rise of the Snakes',
  42             'episode_number': 1,
  43             'season': 'Season 1',
  44             'season_number': 1,
  45             'uploader_id': '2a9273e728c510d22aa5c57d0646810b',
  46             'release_year': 2011,
  47             'thumbnail': r're:^https?://.+\.(jpe?g|png)$',
  48             'duration': 1376,
  49         },
  50         'params': {'skip_download': 'm3u8'},
  51     }, {
  52         'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
  53         'md5': '43ac06be9326f41912dc64ccf7a80320',
  54         'info_dict': {
  55             'id': '283829',
  56             'ext': 'mp4',
  57             'title': 'The Comedian at The Friday',
  58             'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.',
  59             'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
  60         },
  61         'skip': 'Content Unavailable',
  62     }, {
  63         'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
  64         'only_matching': True,
  65     }, {
  66         'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
  67         'info_dict': {
  68             'id': '560057',
  69             'ext': 'mp4',
  70             'title': 'Penitentiary',
  71             'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
  72             'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
  73             'release_year': 1979,
  74         },
  75         'skip': 'Content Unavailable',
  76     }]
  77
  78     # DRM formats are included only to raise appropriate error
  79     _UNPLAYABLE_FORMATS = ('hlsv6_widevine', 'hlsv6_widevine_nonclearlead', 'hlsv6_playready_psshv0',
  80                            'hlsv6_fairplay', 'dash_widevine', 'dash_widevine_nonclearlead')
  81
  82     def _perform_login(self, username, password):
  83         self.report_login()
  84         form_data = {
  85             'username': username,
  86             'password': password,
  87         }
  88         payload = urlencode_postdata(form_data)
  89         request = Request(self._LOGIN_URL, payload)
  90         request.headers['Content-Type'] = 'application/x-www-form-urlencoded'
  91         login_page = self._download_webpage(
  92             request, None, False, 'Wrong login info')
  93         if not re.search(r'id="tubi-logout"', login_page):
  94             raise ExtractorError(
  95                 'Login failed (invalid username/password)', expected=True)
  96
  97     def _real_extract(self, url):
  98         video_id, video_type = self._match_valid_url(url).group('id', 'type')
  99         webpage = self._download_webpage(f'https://tubitv.com/{video_type}/{video_id}/', video_id)
 100         video_data = self._search_json(
 101             r'window\.__data\s*=', webpage, 'data', video_id,
 102             transform_source=js_to_json)['video']['byId'][video_id]
 103
 104         formats = []
 105         drm_formats = False
 106
 107         for resource in traverse_obj(video_data, ('video_resources', lambda _, v: url_or_none(v['manifest']['url']))):
 108             resource_type = resource.get('type')
 109             manifest_url = resource['manifest']['url']
 110             if resource_type == 'dash':
 111                 formats.extend(self._extract_mpd_formats(manifest_url, video_id, mpd_id=resource_type, fatal=False))
 112             elif resource_type in ('hlsv3', 'hlsv6'):
 113                 formats.extend(self._extract_m3u8_formats(manifest_url, video_id, 'mp4', m3u8_id=resource_type, fatal=False))
 114             elif resource_type in self._UNPLAYABLE_FORMATS:
 115                 drm_formats = True
 116             else:
 117                 self.report_warning(f'Skipping unknown resource type "{resource_type}"')
 118
 119         if not formats and drm_formats:
 120             self.report_drm(video_id)
 121         elif not formats and not video_data.get('policy_match'):  # policy_match is False if content was removed
 122             raise ExtractorError('This content is currently unavailable', expected=True)
 123
 124         subtitles = {}
 125         for sub in traverse_obj(video_data, ('subtitles', lambda _, v: url_or_none(v['url']))):
 126             subtitles.setdefault(sub.get('lang', 'English'), []).append({
 127                 'url': self._proto_relative_url(sub['url']),
 128             })
 129
 130         title = traverse_obj(video_data, ('title', {str}))
 131         season_number, episode_number, episode_title = self._search_regex(
 132             r'^S(\d+):E(\d+) - (.+)', title, 'episode info', fatal=False, group=(1, 2, 3), default=(None, None, None))
 133
 134         return {
 135             'id': video_id,
 136             'title': strip_or_none(title),
 137             'formats': formats,
 138             'subtitles': subtitles,
 139             'season_number': int_or_none(season_number),
 140             'episode_number': int_or_none(episode_number),
 141             'episode': strip_or_none(episode_title),
 142             **traverse_obj(video_data, {
 143                 'description': ('description', {str}),
 144                 'duration': ('duration', {int_or_none}),
 145                 'uploader_id': ('publisher_id', {str}),
 146                 'release_year': ('year', {int_or_none}),
 147                 'thumbnails': ('thumbnails', ..., {url_or_none}, {'url': {self._proto_relative_url}}),
 148             }),
 149         }
 150
 151
 152 class TubiTvShowIE(InfoExtractor):
 153     IE_NAME = 'tubitv:series'
 154     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/\d+/(?P<show_name>[^/?#]+)(?:/season-(?P<season>\d+))?'
 155     _TESTS = [{
 156         'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
 157         'playlist_mincount': 389,
 158         'info_dict': {
 159             'id': 'the-joy-of-painting-with-bob-ross',
 160         },
 161     }, {
 162         'url': 'https://tubitv.com/series/2311/the-saddle-club/season-1',
 163         'playlist_count': 26,
 164         'info_dict': {
 165             'id': 'the-saddle-club-season-1',
 166         },
 167     }, {
 168         'url': 'https://tubitv.com/series/2311/the-saddle-club/season-3',
 169         'playlist_count': 19,
 170         'info_dict': {
 171             'id': 'the-saddle-club-season-3',
 172         },
 173     }, {
 174         'url': 'https://tubitv.com/series/2311/the-saddle-club/',
 175         'playlist_mincount': 71,
 176         'info_dict': {
 177             'id': 'the-saddle-club',
 178         },
 179     }]
 180
 181     def _entries(self, show_url, playlist_id, selected_season):
 182         webpage = self._download_webpage(show_url, playlist_id)
 183
 184         data = self._search_json(
 185             r'window\.__data\s*=', webpage, 'data', playlist_id,
 186             transform_source=js_to_json)['video']
 187
 188         # v['number'] is already a decimal string, but stringify to protect against API changes
 189         path = [lambda _, v: str(v['number']) == selected_season] if selected_season else [..., {dict}]
 190
 191         for season in traverse_obj(data, ('byId', lambda _, v: v['type'] == 's', 'seasons', *path)):
 192             season_number = int_or_none(season.get('number'))
 193             for episode in traverse_obj(season, ('episodes', lambda _, v: v['id'])):
 194                 episode_id = episode['id']
 195                 yield self.url_result(
 196                     f'https://tubitv.com/tv-shows/{episode_id}/', TubiTvIE, episode_id,
 197                     season_number=season_number, episode_number=int_or_none(episode.get('num')))
 198
 199     def _real_extract(self, url):
 200         playlist_id, selected_season = self._match_valid_url(url).group('show_name', 'season')
 201         if selected_season:
 202             playlist_id = f'{playlist_id}-season-{selected_season}'
 203         return self.playlist_result(self._entries(url, playlist_id, selected_season), playlist_id)