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