3 from .common
import InfoExtractor
4 from ..networking
import Request
15 class TubiTvIE(InfoExtractor
):
16 _VALID_URL
= r
'https?://(?:www\.)?tubitv\.com/(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
17 _LOGIN_URL
= 'http://tubitv.com/login'
18 _NETRC_MACHINE
= 'tubitv'
20 'url': 'https://tubitv.com/movies/100004539/the-39-steps',
24 'title': 'The 39 Steps',
25 'description': 'md5:bb2f2dd337f0dc58c06cb509943f54c8',
26 'uploader_id': 'abc2558d54505d4f0f32be94f2e7108c',
28 'thumbnail': r
're:^https?://.+\.(jpe?g|png)$',
31 'params': {'skip_download': 'm3u8'}
,
33 'url': 'https://tubitv.com/tv-shows/554628/s01-e01-rise-of-the-snakes',
37 'title': 'S01:E01 - Rise of the Snakes',
38 'description': 'md5:ba136f586de53af0372811e783a3f57d',
39 'episode': 'Rise of the Snakes',
43 'uploader_id': '2a9273e728c510d22aa5c57d0646810b',
45 'thumbnail': r
're:^https?://.+\.(jpe?g|png)$',
48 'params': {'skip_download': 'm3u8'}
,
50 'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
51 'md5': '43ac06be9326f41912dc64ccf7a80320',
55 'title': 'The Comedian at The Friday',
56 '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.',
57 'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
59 'skip': 'Content Unavailable',
61 'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
62 'only_matching': True,
64 'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
68 'title': 'Penitentiary',
69 'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
70 'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
73 'skip': 'Content Unavailable',
76 # DRM formats are included only to raise appropriate error
77 _UNPLAYABLE_FORMATS
= ('hlsv6_widevine', 'hlsv6_widevine_nonclearlead', 'hlsv6_playready_psshv0',
78 'hlsv6_fairplay', 'dash_widevine', 'dash_widevine_nonclearlead')
80 def _perform_login(self
, username
, password
):
86 payload
= urlencode_postdata(form_data
)
87 request
= Request(self
._LOGIN
_URL
, payload
)
88 request
.headers
['Content-Type'] = 'application/x-www-form-urlencoded'
89 login_page
= self
._download
_webpage
(
90 request
, None, False, 'Wrong login info')
91 if not re
.search(r
'id="tubi-logout"', login_page
):
93 'Login failed (invalid username/password)', expected
=True)
95 def _real_extract(self
, url
):
96 video_id
, video_type
= self
._match
_valid
_url
(url
).group('id', 'type')
97 webpage
= self
._download
_webpage
(f
'https://tubitv.com/{video_type}/{video_id}/', video_id
)
98 video_data
= self
._search
_json
(
99 r
'window\.__data\s*=', webpage
, 'data', video_id
,
100 transform_source
=js_to_json
)['video']['byId'][video_id
]
105 for resource
in traverse_obj(video_data
, ('video_resources', lambda _
, v
: url_or_none(v
['manifest']['url']))):
106 resource_type
= resource
.get('type')
107 manifest_url
= resource
['manifest']['url']
108 if resource_type
== 'dash':
109 formats
.extend(self
._extract
_mpd
_formats
(manifest_url
, video_id
, mpd_id
=resource_type
, fatal
=False))
110 elif resource_type
in ('hlsv3', 'hlsv6'):
111 formats
.extend(self
._extract
_m
3u8_formats
(manifest_url
, video_id
, 'mp4', m3u8_id
=resource_type
, fatal
=False))
112 elif resource_type
in self
._UNPLAYABLE
_FORMATS
:
115 self
.report_warning(f
'Skipping unknown resource type "{resource_type}"')
117 if not formats
and drm_formats
:
118 self
.report_drm(video_id
)
119 elif not formats
and not video_data
.get('policy_match'): # policy_match is False if content was removed
120 raise ExtractorError('This content is currently unavailable', expected
=True)
123 for sub
in traverse_obj(video_data
, ('subtitles', lambda _
, v
: url_or_none(v
['url']))):
124 subtitles
.setdefault(sub
.get('lang', 'English'), []).append({
125 'url': self
._proto
_relative
_url
(sub
['url']),
128 title
= traverse_obj(video_data
, ('title', {str}
))
129 season_number
, episode_number
, episode_title
= self
._search
_regex
(
130 r
'^S(\d+):E(\d+) - (.+)', title
, 'episode info', fatal
=False, group
=(1, 2, 3), default
=(None, None, None))
136 'subtitles': subtitles
,
137 'season_number': int_or_none(season_number
),
138 'episode_number': int_or_none(episode_number
),
139 'episode': episode_title
,
140 **traverse_obj(video_data
, {
141 'description': ('description', {str}
),
142 'duration': ('duration', {int_or_none}
),
143 'uploader_id': ('publisher_id', {str}
),
144 'release_year': ('year', {int_or_none}
),
145 'thumbnails': ('thumbnails', ..., {url_or_none}
, {'url': {self._proto_relative_url}
}),
150 class TubiTvShowIE(InfoExtractor
):
152 _VALID_URL
= r
'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)'
154 'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
155 'playlist_mincount': 390,
157 'id': 'the-joy-of-painting-with-bob-ross',
161 def _entries(self
, show_url
, show_name
):
162 show_webpage
= self
._download
_webpage
(show_url
, show_name
)
164 show_json
= self
._parse
_json
(self
._search
_regex
(
165 r
'window\.__data\s*=\s*({[^<]+});\s*</script>',
166 show_webpage
, 'data'), show_name
, transform_source
=js_to_json
)['video']
168 for episode_id
in show_json
['fullContentById']:
169 if traverse_obj(show_json
, ('byId', episode_id
, 'type')) == 's':
171 yield self
.url_result(
172 f
'https://tubitv.com/tv-shows/{episode_id}/',
173 ie
=TubiTvIE
.ie_key(), video_id
=episode_id
)
175 def _real_extract(self
, url
):
176 show_name
= self
._match
_valid
_url
(url
).group('show_name')
177 return self
.playlist_result(self
._entries
(url
, show_name
), playlist_id
=show_name
)