]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/kinopoisk.py
[ie/matchtv] Fix extractor (#10190)
[yt-dlp.git] / yt_dlp / extractor / kinopoisk.py
CommitLineData
df4d817b
S
1from .common import InfoExtractor
2from ..utils import (
3 dict_get,
4 int_or_none,
5)
6
7
8class KinoPoiskIE(InfoExtractor):
9 _GEO_COUNTRIES = ['RU']
10 _VALID_URL = r'https?://(?:www\.)?kinopoisk\.ru/film/(?P<id>\d+)'
11 _TESTS = [{
12 'url': 'https://www.kinopoisk.ru/film/81041/watch/',
13 'md5': '4f71c80baea10dfa54a837a46111d326',
14 'info_dict': {
15 'id': '81041',
16 'ext': 'mp4',
17 'title': 'Алеша попович и тугарин змей',
18 'description': 'md5:43787e673d68b805d0aa1df5a5aea701',
19 'thumbnail': r're:^https?://.*',
20 'duration': 4533,
21 'age_limit': 12,
22 },
df4d817b
S
23 }, {
24 'url': 'https://www.kinopoisk.ru/film/81041',
25 'only_matching': True,
26 }]
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30
31 webpage = self._download_webpage(
32 'https://ott-widget.kinopoisk.ru/v1/kp/', video_id,
33 query={'kpId': video_id})
34
35 data = self._parse_json(
36 self._search_regex(
37 r'(?s)<script[^>]+\btype=["\']application/json[^>]+>(.+?)<',
38 webpage, 'data'),
39 video_id)['models']
40
41 film = data['filmStatus']
42 title = film.get('title') or film['originalTitle']
43
44 formats = self._extract_m3u8_formats(
45 data['playlistEntity']['uri'], video_id, 'mp4',
46 entry_protocol='m3u8_native', m3u8_id='hls')
df4d817b
S
47
48 description = dict_get(
49 film, ('descriptscription', 'description',
50 'shortDescriptscription', 'shortDescription'))
51 thumbnail = film.get('coverUrl') or film.get('posterUrl')
52 duration = int_or_none(film.get('duration'))
53 age_limit = int_or_none(film.get('restrictionAge'))
54
55 return {
56 'id': video_id,
57 'title': title,
58 'description': description,
59 'thumbnail': thumbnail,
60 'duration': duration,
61 'age_limit': age_limit,
62 'formats': formats,
63 }