]>
Commit | Line | Data |
---|---|---|
1 | from .common import InfoExtractor | |
2 | from ..utils import ( | |
3 | determine_ext, | |
4 | ExtractorError, | |
5 | int_or_none, | |
6 | parse_qs, | |
7 | xpath_text, | |
8 | qualities, | |
9 | ) | |
10 | ||
11 | ||
12 | class PladformIE(InfoExtractor): | |
13 | _VALID_URL = r'''(?x) | |
14 | https?:// | |
15 | (?: | |
16 | (?: | |
17 | out\.pladform\.ru/player| | |
18 | static\.pladform\.ru/player\.swf | |
19 | ) | |
20 | \?.*\bvideoid=| | |
21 | video\.pladform\.ru/catalog/video/videoid/ | |
22 | ) | |
23 | (?P<id>\d+) | |
24 | ''' | |
25 | _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1'] | |
26 | _TESTS = [{ | |
27 | 'url': 'http://out.pladform.ru/player?pl=18079&type=html5&videoid=100231282', | |
28 | 'info_dict': { | |
29 | 'id': '6216d548e755edae6e8280667d774791', | |
30 | 'ext': 'mp4', | |
31 | 'timestamp': 1406117012, | |
32 | 'title': 'Гарик Мартиросян и Гарик Харламов - Кастинг на концерт ко Дню милиции', | |
33 | 'age_limit': 0, | |
34 | 'upload_date': '20140723', | |
35 | 'thumbnail': str, | |
36 | 'view_count': int, | |
37 | 'description': str, | |
38 | 'uploader_id': '12082', | |
39 | 'uploader': 'Comedy Club', | |
40 | 'duration': 367, | |
41 | }, | |
42 | 'expected_warnings': ['HTTP Error 404: Not Found'] | |
43 | }, { | |
44 | 'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0', | |
45 | 'md5': '53362fac3a27352da20fa2803cc5cd6f', | |
46 | 'info_dict': { | |
47 | 'id': '3777899', | |
48 | 'ext': 'mp4', | |
49 | 'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко', | |
50 | 'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95', | |
51 | 'thumbnail': r're:^https?://.*\.jpg$', | |
52 | 'duration': 3190, | |
53 | }, | |
54 | }, { | |
55 | 'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0', | |
56 | 'only_matching': True, | |
57 | }, { | |
58 | 'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0', | |
59 | 'only_matching': True, | |
60 | }] | |
61 | ||
62 | def _real_extract(self, url): | |
63 | video_id = self._match_id(url) | |
64 | ||
65 | qs = parse_qs(url) | |
66 | pl = qs.get('pl', ['1'])[0] | |
67 | ||
68 | video = self._download_xml( | |
69 | 'http://out.pladform.ru/getVideo', video_id, query={ | |
70 | 'pl': pl, | |
71 | 'videoid': video_id, | |
72 | }, fatal=False) | |
73 | ||
74 | def fail(text): | |
75 | raise ExtractorError( | |
76 | '%s returned error: %s' % (self.IE_NAME, text), | |
77 | expected=True) | |
78 | ||
79 | if not video: | |
80 | targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').url | |
81 | if targetUrl == url: | |
82 | raise ExtractorError('Can\'t parse page') | |
83 | return self.url_result(targetUrl) | |
84 | ||
85 | if video.tag == 'error': | |
86 | fail(video.text) | |
87 | ||
88 | quality = qualities(('ld', 'sd', 'hd')) | |
89 | ||
90 | formats = [] | |
91 | for src in video.findall('./src'): | |
92 | if src is None: | |
93 | continue | |
94 | format_url = src.text | |
95 | if not format_url: | |
96 | continue | |
97 | if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8': | |
98 | formats.extend(self._extract_m3u8_formats( | |
99 | format_url, video_id, 'mp4', entry_protocol='m3u8_native', | |
100 | m3u8_id='hls', fatal=False)) | |
101 | else: | |
102 | formats.append({ | |
103 | 'url': src.text, | |
104 | 'format_id': src.get('quality'), | |
105 | 'quality': quality(src.get('quality')), | |
106 | }) | |
107 | ||
108 | if not formats: | |
109 | error = xpath_text(video, './cap', 'error', default=None) | |
110 | if error: | |
111 | fail(error) | |
112 | ||
113 | webpage = self._download_webpage( | |
114 | 'http://video.pladform.ru/catalog/video/videoid/%s' % video_id, | |
115 | video_id) | |
116 | ||
117 | title = self._og_search_title(webpage, fatal=False) or xpath_text( | |
118 | video, './/title', 'title', fatal=True) | |
119 | description = self._search_regex( | |
120 | r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False) | |
121 | thumbnail = self._og_search_thumbnail(webpage) or xpath_text( | |
122 | video, './/cover', 'cover') | |
123 | ||
124 | duration = int_or_none(xpath_text(video, './/time', 'duration')) | |
125 | age_limit = int_or_none(xpath_text(video, './/age18', 'age limit')) | |
126 | ||
127 | return { | |
128 | 'id': video_id, | |
129 | 'title': title, | |
130 | 'description': description, | |
131 | 'thumbnail': thumbnail, | |
132 | 'duration': duration, | |
133 | 'age_limit': age_limit, | |
134 | 'formats': formats, | |
135 | } |