]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/tubitv.py
[cleanup] Add more ruff rules (#10149)
[yt-dlp.git] / 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 _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'
19 _TESTS = [{
20 'url': 'https://tubitv.com/movies/100004539/the-39-steps',
21 'info_dict': {
22 'id': '100004539',
23 'ext': 'mp4',
24 'title': 'The 39 Steps',
25 'description': 'md5:bb2f2dd337f0dc58c06cb509943f54c8',
26 'uploader_id': 'abc2558d54505d4f0f32be94f2e7108c',
27 'release_year': 1935,
28 'thumbnail': r're:^https?://.+\.(jpe?g|png)$',
29 'duration': 5187,
30 },
31 'params': {'skip_download': 'm3u8'},
32 }, {
33 'url': 'https://tubitv.com/tv-shows/554628/s01-e01-rise-of-the-snakes',
34 'info_dict': {
35 'id': '554628',
36 'ext': 'mp4',
37 'title': 'S01:E01 - Rise of the Snakes',
38 'description': 'md5:ba136f586de53af0372811e783a3f57d',
39 'episode': 'Rise of the Snakes',
40 'episode_number': 1,
41 'season': 'Season 1',
42 'season_number': 1,
43 'uploader_id': '2a9273e728c510d22aa5c57d0646810b',
44 'release_year': 2011,
45 'thumbnail': r're:^https?://.+\.(jpe?g|png)$',
46 'duration': 1376,
47 },
48 'params': {'skip_download': 'm3u8'},
49 }, {
50 'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
51 'md5': '43ac06be9326f41912dc64ccf7a80320',
52 'info_dict': {
53 'id': '283829',
54 'ext': 'mp4',
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',
58 },
59 'skip': 'Content Unavailable',
60 }, {
61 'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
62 'only_matching': True,
63 }, {
64 'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
65 'info_dict': {
66 'id': '560057',
67 'ext': 'mp4',
68 'title': 'Penitentiary',
69 'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
70 'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
71 'release_year': 1979,
72 },
73 'skip': 'Content Unavailable',
74 }]
75
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')
79
80 def _perform_login(self, username, password):
81 self.report_login()
82 form_data = {
83 'username': username,
84 'password': password,
85 }
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):
92 raise ExtractorError(
93 'Login failed (invalid username/password)', expected=True)
94
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]
101
102 formats = []
103 drm_formats = False
104
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_m3u8_formats(manifest_url, video_id, 'mp4', m3u8_id=resource_type, fatal=False))
112 elif resource_type in self._UNPLAYABLE_FORMATS:
113 drm_formats = True
114 else:
115 self.report_warning(f'Skipping unknown resource type "{resource_type}"')
116
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)
121
122 subtitles = {}
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']),
126 })
127
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))
131
132 return {
133 'id': video_id,
134 'title': title,
135 'formats': formats,
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}}),
146 }),
147 }
148
149
150 class TubiTvShowIE(InfoExtractor):
151 _WORKING = False
152 _VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)'
153 _TESTS = [{
154 'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
155 'playlist_mincount': 390,
156 'info_dict': {
157 'id': 'the-joy-of-painting-with-bob-ross',
158 },
159 }]
160
161 def _entries(self, show_url, show_name):
162 show_webpage = self._download_webpage(show_url, show_name)
163
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']
167
168 for episode_id in show_json['fullContentById']:
169 if traverse_obj(show_json, ('byId', episode_id, 'type')) == 's':
170 continue
171 yield self.url_result(
172 f'https://tubitv.com/tv-shows/{episode_id}/',
173 ie=TubiTvIE.ie_key(), video_id=episode_id)
174
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)