logo

oasis-root

Compiled tree of Oasis Linux based on own branch at <https://hacktivis.me/git/oasis/> git clone https://anongit.hacktivis.me/git/oasis-root.git

tubitv.py (8599B)


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