]>
Commit | Line | Data |
---|---|---|
ea3a012d C |
1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
4 | import re | |
5 | import uuid | |
6 | ||
7 | from .common import InfoExtractor | |
8 | from ..compat import ( | |
9 | compat_str, | |
10 | compat_urlparse, | |
11 | ) | |
12 | from ..utils import ( | |
13 | ExtractorError, | |
14 | float_or_none, | |
15 | int_or_none, | |
16 | try_get, | |
17 | url_or_none, | |
18 | ) | |
19 | ||
20 | ||
21 | class PlutoTVIE(InfoExtractor): | |
22 | _VALID_URL = r'https?://(?:www\.)?pluto\.tv/on-demand/(?P<video_type>movies|series)/(?P<slug>.*)/?$' | |
23 | _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/' | |
24 | _INFO_QUERY_PARAMS = { | |
25 | 'appName': 'web', | |
26 | 'appVersion': 'na', | |
27 | 'clientID': compat_str(uuid.uuid1()), | |
28 | 'clientModelNumber': 'na', | |
29 | 'serverSideAds': 'false', | |
30 | 'deviceMake': 'unknown', | |
31 | 'deviceModel': 'web', | |
32 | 'deviceType': 'web', | |
33 | 'deviceVersion': 'unknown', | |
34 | 'sid': compat_str(uuid.uuid1()), | |
35 | } | |
36 | _TESTS = [ | |
37 | { | |
38 | 'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3', | |
39 | 'md5': 'ebcdd8ed89aaace9df37924f722fd9bd', | |
40 | 'info_dict': { | |
41 | 'id': '5de6c598e9379ae4912df0a8', | |
42 | 'ext': 'mp4', | |
43 | 'title': 'It\'s In The Cards', | |
44 | 'episode': 'It\'s In The Cards', | |
45 | '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.', | |
46 | 'series': 'I Love Money', | |
47 | 'season_number': 2, | |
48 | 'episode_number': 3, | |
49 | 'duration': 3600, | |
50 | } | |
51 | }, | |
52 | { | |
53 | 'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/', | |
54 | 'playlist_count': 11, | |
55 | 'info_dict': { | |
56 | 'id': '5de6c582e9379ae4912dedbd', | |
57 | 'title': 'I Love Money - Season 1', | |
58 | } | |
59 | }, | |
60 | { | |
61 | 'url': 'https://pluto.tv/on-demand/series/i-love-money/', | |
62 | 'playlist_count': 26, | |
63 | 'info_dict': { | |
64 | 'id': '5de6c582e9379ae4912dedbd', | |
65 | 'title': 'I Love Money', | |
66 | } | |
67 | }, | |
68 | { | |
69 | 'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1', | |
70 | 'md5': '3cead001d317a018bf856a896dee1762', | |
71 | 'info_dict': { | |
72 | 'id': '5e83ac701fa6a9001bb9df24', | |
73 | 'ext': 'mp4', | |
74 | 'title': 'Arrival', | |
75 | '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.', | |
76 | 'duration': 9000, | |
77 | } | |
78 | }, | |
79 | ] | |
80 | ||
81 | def _to_ad_free_formats(self, video_id, formats): | |
82 | ad_free_formats = [] | |
83 | m3u8_urls = set() | |
84 | for format in formats: | |
85 | res = self._download_webpage( | |
86 | format.get('url'), video_id, note='Downloading m3u8 playlist', | |
87 | fatal=False) | |
88 | if not res: | |
89 | continue | |
90 | first_segment_url = re.search( | |
91 | r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res, | |
92 | re.MULTILINE) | |
93 | if not first_segment_url: | |
94 | continue | |
95 | m3u8_urls.add( | |
96 | compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8')) | |
97 | ||
98 | for m3u8_url in m3u8_urls: | |
99 | ad_free_formats.extend( | |
100 | self._extract_m3u8_formats( | |
101 | m3u8_url, video_id, 'mp4', 'm3u8_native', | |
102 | m3u8_id='hls', fatal=False)) | |
103 | self._sort_formats(ad_free_formats) | |
104 | return ad_free_formats | |
105 | ||
106 | def _get_video_info(self, video_json, slug, series_name=None): | |
107 | video_id = video_json.get('_id', slug) | |
108 | formats = [] | |
109 | for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []: | |
110 | if video_url.get('type') != 'hls': | |
111 | continue | |
112 | url = url_or_none(video_url.get('url')) | |
113 | formats.extend( | |
114 | self._extract_m3u8_formats( | |
115 | url, video_id, 'mp4', 'm3u8_native', | |
116 | m3u8_id='hls', fatal=False)) | |
117 | info = { | |
118 | 'id': video_id, | |
119 | 'formats': self._to_ad_free_formats(video_id, formats), | |
120 | 'title': video_json.get('name'), | |
121 | 'description': video_json.get('description'), | |
122 | 'duration': float_or_none(video_json.get('duration'), scale=1000), | |
123 | } | |
124 | if series_name: | |
125 | info.update({ | |
126 | 'series': series_name, | |
127 | 'episode': video_json.get('name'), | |
128 | 'season_number': int_or_none(video_json.get('season')), | |
129 | 'episode_number': int_or_none(video_json.get('number')), | |
130 | }) | |
131 | return info | |
132 | ||
133 | def _real_extract(self, url): | |
134 | path = compat_urlparse.urlparse(url).path | |
135 | path_components = path.split('/') | |
136 | video_type = path_components[2] | |
137 | info_slug = path_components[3] | |
138 | video_json = self._download_json(self._INFO_URL + info_slug, info_slug, | |
139 | query=self._INFO_QUERY_PARAMS) | |
140 | ||
141 | if video_type == 'series': | |
142 | series_name = video_json.get('name', info_slug) | |
143 | season_number = int_or_none(try_get(path_components, lambda x: x[5])) | |
144 | episode_slug = try_get(path_components, lambda x: x[7]) | |
145 | ||
146 | videos = [] | |
147 | for season in video_json['seasons']: | |
148 | if season_number is not None and season_number != int_or_none(season.get('number')): | |
149 | continue | |
150 | for episode in season['episodes']: | |
151 | if episode_slug is not None and episode_slug != episode.get('slug'): | |
152 | continue | |
153 | videos.append(self._get_video_info(episode, episode_slug, series_name)) | |
154 | if not videos: | |
155 | raise ExtractorError('Failed to find any videos to extract') | |
156 | if episode_slug is not None and len(videos) == 1: | |
157 | return videos[0] | |
158 | playlist_title = series_name | |
159 | if season_number is not None: | |
160 | playlist_title += ' - Season %d' % season_number | |
161 | return self.playlist_result(videos, | |
162 | playlist_id=video_json.get('_id', info_slug), | |
163 | playlist_title=playlist_title) | |
164 | return self._get_video_info(video_json, info_slug) |