]>
Commit | Line | Data |
---|---|---|
5196b988 NJ |
1 | import re |
2 | ||
3 | from .common import InfoExtractor | |
5196b988 NJ |
4 | from ..utils import ( |
5 | ExtractorError, | |
6 | int_or_none, | |
b5be6dd5 | 7 | js_to_json, |
5c2266df | 8 | sanitized_Request, |
6e6bc8da | 9 | urlencode_postdata, |
2dc4970e | 10 | traverse_obj, |
5196b988 NJ |
11 | ) |
12 | ||
13 | ||
14 | class TubiTvIE(InfoExtractor): | |
b5be6dd5 A |
15 | _VALID_URL = r'''(?x) |
16 | (?: | |
17 | tubitv:| | |
18 | https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/ | |
19 | ) | |
20 | (?P<id>[0-9]+)''' | |
5196b988 NJ |
21 | _LOGIN_URL = 'http://tubitv.com/login' |
22 | _NETRC_MACHINE = 'tubitv' | |
68f17a9c | 23 | _GEO_COUNTRIES = ['US'] |
4fe4bda2 | 24 | _TESTS = [{ |
3b55aaac | 25 | 'url': 'https://tubitv.com/movies/383676/tracker', |
26 | 'md5': '566fa0f76870302d11af0de89511d3f0', | |
27 | 'info_dict': { | |
28 | 'id': '383676', | |
29 | 'ext': 'mp4', | |
30 | 'title': 'Tracker', | |
31 | 'description': 'md5:ff320baf43d0ad2655e538c1d5cd9706', | |
32 | 'uploader_id': 'f866e2677ea2f0dff719788e4f7f9195', | |
33 | 'release_year': 2010, | |
34 | 'thumbnail': r're:^https?://.+\.(jpe?g|png)$', | |
35 | 'duration': 6122, | |
36 | }, | |
37 | }, { | |
9260cf1d | 38 | 'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday', |
f4dfa9a5 | 39 | 'md5': '43ac06be9326f41912dc64ccf7a80320', |
5196b988 | 40 | 'info_dict': { |
9260cf1d | 41 | 'id': '283829', |
5196b988 | 42 | 'ext': 'mp4', |
9260cf1d | 43 | 'title': 'The Comedian at The Friday', |
44 | '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.', | |
f4dfa9a5 | 45 | 'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434', |
5196b988 | 46 | }, |
3b55aaac | 47 | 'skip': 'Content Unavailable' |
4fe4bda2 RA |
48 | }, { |
49 | 'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories', | |
50 | 'only_matching': True, | |
29f7c58a | 51 | }, { |
52 | 'url': 'https://tubitv.com/movies/560057/penitentiary?start=true', | |
53 | 'info_dict': { | |
54 | 'id': '560057', | |
55 | 'ext': 'mp4', | |
56 | 'title': 'Penitentiary', | |
57 | 'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9', | |
58 | 'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2', | |
59 | 'release_year': 1979, | |
60 | }, | |
3b55aaac | 61 | 'skip': 'Content Unavailable' |
4fe4bda2 | 62 | }] |
5196b988 | 63 | |
3b55aaac | 64 | # DRM formats are included only to raise appropriate error |
65 | _UNPLAYABLE_FORMATS = ('hlsv6_widevine', 'hlsv6_widevine_nonclearlead', 'hlsv6_playready_psshv0', | |
66 | 'hlsv6_fairplay', 'dash_widevine', 'dash_widevine_nonclearlead') | |
67 | ||
52efa4b3 | 68 | def _perform_login(self, username, password): |
5196b988 NJ |
69 | self.report_login() |
70 | form_data = { | |
71 | 'username': username, | |
72 | 'password': password, | |
73 | } | |
6e6bc8da | 74 | payload = urlencode_postdata(form_data) |
5c2266df | 75 | request = sanitized_Request(self._LOGIN_URL, payload) |
5196b988 NJ |
76 | request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
77 | login_page = self._download_webpage( | |
78 | request, None, False, 'Wrong login info') | |
79 | if not re.search(r'id="tubi-logout"', login_page): | |
80 | raise ExtractorError( | |
81 | 'Login failed (invalid username/password)', expected=True) | |
82 | ||
5196b988 NJ |
83 | def _real_extract(self, url): |
84 | video_id = self._match_id(url) | |
3b55aaac | 85 | video_data = self._download_json(f'https://tubitv.com/oz/videos/{video_id}/content', video_id, query={ |
86 | 'video_resources': ['dash', 'hlsv3', 'hlsv6', *self._UNPLAYABLE_FORMATS], | |
87 | }) | |
f4dfa9a5 | 88 | title = video_data['title'] |
5196b988 | 89 | |
cf9d6cfb | 90 | formats = [] |
3b55aaac | 91 | drm_formats = False |
ffcd62c2 | 92 | |
93 | for resource in video_data['video_resources']: | |
94 | if resource['type'] in ('dash', ): | |
95 | formats += self._extract_mpd_formats(resource['manifest']['url'], video_id, mpd_id=resource['type'], fatal=False) | |
96 | elif resource['type'] in ('hlsv3', 'hlsv6'): | |
97 | formats += self._extract_m3u8_formats(resource['manifest']['url'], video_id, 'mp4', m3u8_id=resource['type'], fatal=False) | |
3b55aaac | 98 | elif resource['type'] in self._UNPLAYABLE_FORMATS: |
99 | drm_formats = True | |
100 | ||
101 | if not formats and drm_formats: | |
102 | self.report_drm(video_id) | |
103 | elif not formats and not video_data.get('policy_match'): # policy_match is False if content was removed | |
104 | raise ExtractorError('This content is currently unavailable', expected=True) | |
ffcd62c2 | 105 | |
f4dfa9a5 RA |
106 | thumbnails = [] |
107 | for thumbnail_url in video_data.get('thumbnails', []): | |
108 | if not thumbnail_url: | |
109 | continue | |
110 | thumbnails.append({ | |
111 | 'url': self._proto_relative_url(thumbnail_url), | |
112 | }) | |
113 | ||
9260cf1d | 114 | subtitles = {} |
f4dfa9a5 RA |
115 | for sub in video_data.get('subtitles', []): |
116 | sub_url = sub.get('url') | |
9260cf1d | 117 | if not sub_url: |
118 | continue | |
f4dfa9a5 RA |
119 | subtitles.setdefault(sub.get('lang', 'English'), []).append({ |
120 | 'url': self._proto_relative_url(sub_url), | |
9260cf1d | 121 | }) |
122 | ||
febff4c1 B |
123 | season_number, episode_number, episode_title = self._search_regex( |
124 | r'^S(\d+):E(\d+) - (.+)', title, 'episode info', fatal=False, group=(1, 2, 3), default=(None, None, None)) | |
125 | ||
5196b988 NJ |
126 | return { |
127 | 'id': video_id, | |
128 | 'title': title, | |
129 | 'formats': formats, | |
9260cf1d | 130 | 'subtitles': subtitles, |
f4dfa9a5 RA |
131 | 'thumbnails': thumbnails, |
132 | 'description': video_data.get('description'), | |
133 | 'duration': int_or_none(video_data.get('duration')), | |
134 | 'uploader_id': video_data.get('publisher_id'), | |
29f7c58a | 135 | 'release_year': int_or_none(video_data.get('year')), |
febff4c1 B |
136 | 'season_number': int_or_none(season_number), |
137 | 'episode_number': int_or_none(episode_number), | |
138 | 'episode_title': episode_title | |
5196b988 | 139 | } |
b5be6dd5 A |
140 | |
141 | ||
142 | class TubiTvShowIE(InfoExtractor): | |
143 | _VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)' | |
144 | _TESTS = [{ | |
145 | 'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true', | |
146 | 'playlist_mincount': 390, | |
147 | 'info_dict': { | |
148 | 'id': 'the-joy-of-painting-with-bob-ross', | |
149 | } | |
150 | }] | |
151 | ||
152 | def _entries(self, show_url, show_name): | |
153 | show_webpage = self._download_webpage(show_url, show_name) | |
febff4c1 | 154 | |
b5be6dd5 | 155 | show_json = self._parse_json(self._search_regex( |
febff4c1 B |
156 | r'window\.__data\s*=\s*({[^<]+});\s*</script>', |
157 | show_webpage, 'data'), show_name, transform_source=js_to_json)['video'] | |
158 | ||
b5be6dd5 | 159 | for episode_id in show_json['fullContentById'].keys(): |
2dc4970e | 160 | if traverse_obj(show_json, ('byId', episode_id, 'type')) == 's': |
161 | continue | |
b5be6dd5 A |
162 | yield self.url_result( |
163 | 'tubitv:%s' % episode_id, | |
164 | ie=TubiTvIE.ie_key(), video_id=episode_id) | |
165 | ||
166 | def _real_extract(self, url): | |
5ad28e7f | 167 | show_name = self._match_valid_url(url).group('show_name') |
b5be6dd5 | 168 | return self.playlist_result(self._entries(url, show_name), playlist_id=show_name) |