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