]>
Commit | Line | Data |
---|---|---|
1 | import re | |
2 | import uuid | |
3 | ||
4 | from .common import InfoExtractor | |
5 | from ..compat import ( | |
6 | compat_str, | |
7 | compat_urlparse, | |
8 | ) | |
9 | from ..utils import ( | |
10 | ExtractorError, | |
11 | float_or_none, | |
12 | int_or_none, | |
13 | try_get, | |
14 | url_or_none, | |
15 | ) | |
16 | ||
17 | ||
18 | class PlutoTVIE(InfoExtractor): | |
19 | _VALID_URL = r'''(?x) | |
20 | https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand | |
21 | /(?P<video_type>movies|series) | |
22 | /(?P<series_or_movie_slug>[^/]+) | |
23 | (?: | |
24 | (?:/seasons?/(?P<season_no>\d+))? | |
25 | (?:/episode/(?P<episode_slug>[^/]+))? | |
26 | )? | |
27 | /?(?:$|[#?])''' | |
28 | ||
29 | _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/' | |
30 | _INFO_QUERY_PARAMS = { | |
31 | 'appName': 'web', | |
32 | 'appVersion': 'na', | |
33 | 'clientID': compat_str(uuid.uuid1()), | |
34 | 'clientModelNumber': 'na', | |
35 | 'serverSideAds': 'false', | |
36 | 'deviceMake': 'unknown', | |
37 | 'deviceModel': 'web', | |
38 | 'deviceType': 'web', | |
39 | 'deviceVersion': 'unknown', | |
40 | 'sid': compat_str(uuid.uuid1()), | |
41 | } | |
42 | _TESTS = [ | |
43 | { | |
44 | 'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3', | |
45 | 'md5': 'ebcdd8ed89aaace9df37924f722fd9bd', | |
46 | 'info_dict': { | |
47 | 'id': '5de6c598e9379ae4912df0a8', | |
48 | 'ext': 'mp4', | |
49 | 'title': 'It\'s In The Cards', | |
50 | 'episode': 'It\'s In The Cards', | |
51 | 'description': 'The teams face off against each other in a 3-on-2 soccer showdown. Strategy comes into play, though, as each team gets to select their opposing teams’ two defenders.', | |
52 | 'series': 'I Love Money', | |
53 | 'season_number': 2, | |
54 | 'episode_number': 3, | |
55 | 'duration': 3600, | |
56 | } | |
57 | }, { | |
58 | 'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/', | |
59 | 'playlist_count': 11, | |
60 | 'info_dict': { | |
61 | 'id': '5de6c582e9379ae4912dedbd', | |
62 | 'title': 'I Love Money - Season 1', | |
63 | } | |
64 | }, { | |
65 | 'url': 'https://pluto.tv/on-demand/series/i-love-money/', | |
66 | 'playlist_count': 26, | |
67 | 'info_dict': { | |
68 | 'id': '5de6c582e9379ae4912dedbd', | |
69 | 'title': 'I Love Money', | |
70 | } | |
71 | }, { | |
72 | 'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1', | |
73 | 'md5': '3cead001d317a018bf856a896dee1762', | |
74 | 'info_dict': { | |
75 | 'id': '5e83ac701fa6a9001bb9df24', | |
76 | 'ext': 'mp4', | |
77 | 'title': 'Arrival', | |
78 | 'description': 'When mysterious spacecraft touch down across the globe, an elite team - led by expert translator Louise Banks (Academy Award® nominee Amy Adams) – races against time to decipher their intent.', | |
79 | 'duration': 9000, | |
80 | } | |
81 | }, { | |
82 | 'url': 'https://pluto.tv/en/on-demand/series/manhunters-fugitive-task-force/seasons/1/episode/third-times-the-charm-1-1', | |
83 | 'only_matching': True, | |
84 | }, { | |
85 | 'url': 'https://pluto.tv/it/on-demand/series/csi-vegas/episode/legacy-2021-1-1', | |
86 | 'only_matching': True, | |
87 | }, | |
88 | { | |
89 | 'url': 'https://pluto.tv/en/on-demand/movies/attack-of-the-killer-tomatoes-1977-1-1-ptv1', | |
90 | 'md5': '7db56369c0da626a32d505ec6eb3f89f', | |
91 | 'info_dict': { | |
92 | 'id': '5b190c7bb0875c36c90c29c4', | |
93 | 'ext': 'mp4', | |
94 | 'title': 'Attack of the Killer Tomatoes', | |
95 | 'description': 'A group of scientists band together to save the world from mutated tomatoes that KILL! (1978)', | |
96 | 'duration': 5700, | |
97 | } | |
98 | } | |
99 | ] | |
100 | ||
101 | def _to_ad_free_formats(self, video_id, formats, subtitles): | |
102 | ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set() | |
103 | for fmt in formats: | |
104 | res = self._download_webpage( | |
105 | fmt.get('url'), video_id, note='Downloading m3u8 playlist', | |
106 | fatal=False) | |
107 | if not res: | |
108 | continue | |
109 | first_segment_url = re.search( | |
110 | r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res, | |
111 | re.MULTILINE) | |
112 | if first_segment_url: | |
113 | m3u8_urls.add( | |
114 | compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8')) | |
115 | continue | |
116 | first_segment_url = re.search( | |
117 | r'^(https?://.*/).+\-0+[0-1]0\.ts$', res, | |
118 | re.MULTILINE) | |
119 | if first_segment_url: | |
120 | m3u8_urls.add( | |
121 | compat_urlparse.urljoin(first_segment_url.group(1), 'master.m3u8')) | |
122 | continue | |
123 | ||
124 | for m3u8_url in m3u8_urls: | |
125 | fmts, subs = self._extract_m3u8_formats_and_subtitles( | |
126 | m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) | |
127 | ad_free_formats.extend(fmts) | |
128 | ad_free_subtitles = self._merge_subtitles(ad_free_subtitles, subs) | |
129 | if ad_free_formats: | |
130 | formats, subtitles = ad_free_formats, ad_free_subtitles | |
131 | else: | |
132 | self.report_warning('Unable to find ad-free formats') | |
133 | return formats, subtitles | |
134 | ||
135 | def _get_video_info(self, video_json, slug, series_name=None): | |
136 | video_id = video_json.get('_id', slug) | |
137 | formats, subtitles = [], {} | |
138 | for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []: | |
139 | if video_url.get('type') != 'hls': | |
140 | continue | |
141 | url = url_or_none(video_url.get('url')) | |
142 | ||
143 | fmts, subs = self._extract_m3u8_formats_and_subtitles( | |
144 | url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) | |
145 | formats.extend(fmts) | |
146 | subtitles = self._merge_subtitles(subtitles, subs) | |
147 | ||
148 | formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles) | |
149 | ||
150 | info = { | |
151 | 'id': video_id, | |
152 | 'formats': formats, | |
153 | 'subtitles': subtitles, | |
154 | 'title': video_json.get('name'), | |
155 | 'description': video_json.get('description'), | |
156 | 'duration': float_or_none(video_json.get('duration'), scale=1000), | |
157 | } | |
158 | if series_name: | |
159 | info.update({ | |
160 | 'series': series_name, | |
161 | 'episode': video_json.get('name'), | |
162 | 'season_number': int_or_none(video_json.get('season')), | |
163 | 'episode_number': int_or_none(video_json.get('number')), | |
164 | }) | |
165 | return info | |
166 | ||
167 | def _real_extract(self, url): | |
168 | mobj = self._match_valid_url(url).groupdict() | |
169 | info_slug = mobj['series_or_movie_slug'] | |
170 | video_json = self._download_json(self._INFO_URL + info_slug, info_slug, query=self._INFO_QUERY_PARAMS) | |
171 | ||
172 | if mobj['video_type'] == 'series': | |
173 | series_name = video_json.get('name', info_slug) | |
174 | season_number, episode_slug = mobj.get('season_number'), mobj.get('episode_slug') | |
175 | ||
176 | videos = [] | |
177 | for season in video_json['seasons']: | |
178 | if season_number is not None and season_number != int_or_none(season.get('number')): | |
179 | continue | |
180 | for episode in season['episodes']: | |
181 | if episode_slug is not None and episode_slug != episode.get('slug'): | |
182 | continue | |
183 | videos.append(self._get_video_info(episode, episode_slug, series_name)) | |
184 | if not videos: | |
185 | raise ExtractorError('Failed to find any videos to extract') | |
186 | if episode_slug is not None and len(videos) == 1: | |
187 | return videos[0] | |
188 | playlist_title = series_name | |
189 | if season_number is not None: | |
190 | playlist_title += ' - Season %d' % season_number | |
191 | return self.playlist_result(videos, | |
192 | playlist_id=video_json.get('_id', info_slug), | |
193 | playlist_title=playlist_title) | |
194 | return self._get_video_info(video_json, info_slug) |