]>
Commit | Line | Data |
---|---|---|
ea3a012d C |
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): | |
826446bd | 19 | _VALID_URL = r'''(?x) |
aab41cdd | 20 | https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand |
826446bd | 21 | /(?P<video_type>movies|series) |
22 | /(?P<series_or_movie_slug>[^/]+) | |
23 | (?: | |
aab41cdd | 24 | (?:/seasons?/(?P<season_no>\d+))? |
826446bd | 25 | (?:/episode/(?P<episode_slug>[^/]+))? |
26 | )? | |
27 | /?(?:$|[#?])''' | |
28 | ||
ea3a012d C |
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 | } | |
2b18a8c5 | 57 | }, { |
ea3a012d C |
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 | } | |
2b18a8c5 | 64 | }, { |
ea3a012d C |
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 | } | |
2b18a8c5 | 71 | }, { |
ea3a012d C |
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 | } | |
2b18a8c5 | 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, | |
aab41cdd | 84 | }, { |
85 | 'url': 'https://pluto.tv/it/on-demand/series/csi-vegas/episode/legacy-2021-1-1', | |
86 | 'only_matching': True, | |
2b18a8c5 | 87 | } |
ea3a012d C |
88 | ] |
89 | ||
7700b37f | 90 | def _to_ad_free_formats(self, video_id, formats, subtitles): |
91 | ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set() | |
12e73423 | 92 | for fmt in formats: |
ea3a012d | 93 | res = self._download_webpage( |
12e73423 | 94 | fmt.get('url'), video_id, note='Downloading m3u8 playlist', |
ea3a012d C |
95 | fatal=False) |
96 | if not res: | |
97 | continue | |
98 | first_segment_url = re.search( | |
99 | r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res, | |
100 | re.MULTILINE) | |
12e73423 | 101 | if first_segment_url: |
102 | m3u8_urls.add( | |
103 | compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8')) | |
104 | continue | |
105 | first_segment_url = re.search( | |
106 | r'^(https?://.*/).+\-0+\.ts$', res, | |
107 | re.MULTILINE) | |
108 | if first_segment_url: | |
109 | m3u8_urls.add( | |
110 | compat_urlparse.urljoin(first_segment_url.group(1), 'master.m3u8')) | |
ea3a012d | 111 | continue |
ea3a012d C |
112 | |
113 | for m3u8_url in m3u8_urls: | |
7700b37f | 114 | fmts, subs = self._extract_m3u8_formats_and_subtitles( |
115 | m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) | |
116 | ad_free_formats.extend(fmts) | |
117 | ad_free_subtitles = self._merge_subtitles(ad_free_subtitles, subs) | |
12e73423 | 118 | if ad_free_formats: |
119 | formats, subtitles = ad_free_formats, ad_free_subtitles | |
120 | else: | |
a06916d9 | 121 | self.report_warning('Unable to find ad-free formats') |
12e73423 | 122 | return formats, subtitles |
ea3a012d C |
123 | |
124 | def _get_video_info(self, video_json, slug, series_name=None): | |
125 | video_id = video_json.get('_id', slug) | |
7700b37f | 126 | formats, subtitles = [], {} |
ea3a012d C |
127 | for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []: |
128 | if video_url.get('type') != 'hls': | |
129 | continue | |
130 | url = url_or_none(video_url.get('url')) | |
7700b37f | 131 | |
132 | fmts, subs = self._extract_m3u8_formats_and_subtitles( | |
133 | url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) | |
134 | formats.extend(fmts) | |
135 | subtitles = self._merge_subtitles(subtitles, subs) | |
136 | ||
137 | formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles) | |
138 | self._sort_formats(formats) | |
139 | ||
ea3a012d C |
140 | info = { |
141 | 'id': video_id, | |
7700b37f | 142 | 'formats': formats, |
143 | 'subtitles': subtitles, | |
ea3a012d C |
144 | 'title': video_json.get('name'), |
145 | 'description': video_json.get('description'), | |
146 | 'duration': float_or_none(video_json.get('duration'), scale=1000), | |
147 | } | |
148 | if series_name: | |
149 | info.update({ | |
150 | 'series': series_name, | |
151 | 'episode': video_json.get('name'), | |
152 | 'season_number': int_or_none(video_json.get('season')), | |
153 | 'episode_number': int_or_none(video_json.get('number')), | |
154 | }) | |
155 | return info | |
156 | ||
157 | def _real_extract(self, url): | |
826446bd | 158 | mobj = self._match_valid_url(url).groupdict() |
159 | info_slug = mobj['series_or_movie_slug'] | |
160 | video_json = self._download_json(self._INFO_URL + info_slug, info_slug, query=self._INFO_QUERY_PARAMS) | |
ea3a012d | 161 | |
826446bd | 162 | if mobj['video_type'] == 'series': |
ea3a012d | 163 | series_name = video_json.get('name', info_slug) |
826446bd | 164 | season_number, episode_slug = mobj.get('season_number'), mobj.get('episode_slug') |
ea3a012d C |
165 | |
166 | videos = [] | |
167 | for season in video_json['seasons']: | |
168 | if season_number is not None and season_number != int_or_none(season.get('number')): | |
169 | continue | |
170 | for episode in season['episodes']: | |
171 | if episode_slug is not None and episode_slug != episode.get('slug'): | |
172 | continue | |
173 | videos.append(self._get_video_info(episode, episode_slug, series_name)) | |
174 | if not videos: | |
175 | raise ExtractorError('Failed to find any videos to extract') | |
176 | if episode_slug is not None and len(videos) == 1: | |
177 | return videos[0] | |
178 | playlist_title = series_name | |
179 | if season_number is not None: | |
180 | playlist_title += ' - Season %d' % season_number | |
181 | return self.playlist_result(videos, | |
182 | playlist_id=video_json.get('_id', info_slug), | |
183 | playlist_title=playlist_title) | |
184 | return self._get_video_info(video_json, info_slug) |