]>
Commit | Line | Data |
---|---|---|
b9ed3af3 S |
1 | import json |
2 | ||
3 | from .common import InfoExtractor | |
4 | from ..utils import ( | |
5 | js_to_json, | |
6 | qualities, | |
7 | ) | |
8 | ||
9 | ||
10 | class TassIE(InfoExtractor): | |
11 | _VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)' | |
12 | _TESTS = [ | |
13 | { | |
14 | 'url': 'http://tass.ru/obschestvo/1586870', | |
15 | 'md5': '3b4cdd011bc59174596b6145cda474a4', | |
16 | 'info_dict': { | |
17 | 'id': '1586870', | |
18 | 'ext': 'mp4', | |
19 | 'title': 'Посетителям московского зоопарка показали красную панду', | |
20 | 'description': 'Приехавшую из Дублина Зейну можно увидеть в павильоне "Кошки тропиков"', | |
ec85ded8 | 21 | 'thumbnail': r're:^https?://.*\.jpg$', |
b9ed3af3 S |
22 | }, |
23 | }, | |
24 | { | |
25 | 'url': 'http://itar-tass.com/obschestvo/1600009', | |
26 | 'only_matching': True, | |
27 | }, | |
28 | ] | |
29 | ||
30 | def _real_extract(self, url): | |
31 | video_id = self._match_id(url) | |
32 | ||
33 | webpage = self._download_webpage(url, video_id) | |
34 | ||
35 | sources = json.loads(js_to_json(self._search_regex( | |
36 | r'(?s)sources\s*:\s*(\[.+?\])', webpage, 'sources'))) | |
37 | ||
38 | quality = qualities(['sd', 'hd']) | |
39 | ||
40 | formats = [] | |
41 | for source in sources: | |
42 | video_url = source.get('file') | |
43 | if not video_url or not video_url.startswith('http') or not video_url.endswith('.mp4'): | |
44 | continue | |
45 | label = source.get('label') | |
46 | formats.append({ | |
47 | 'url': video_url, | |
48 | 'format_id': label, | |
49 | 'quality': quality(label), | |
50 | }) | |
51 | self._sort_formats(formats) | |
52 | ||
53 | return { | |
54 | 'id': video_id, | |
55 | 'title': self._og_search_title(webpage), | |
56 | 'description': self._og_search_description(webpage), | |
57 | 'thumbnail': self._og_search_thumbnail(webpage), | |
58 | 'formats': formats, | |
59 | } |