]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/olympics.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
11 class OlympicsReplayIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:www\.)?olympics\.com(?:/tokyo-2020)?/[a-z]{2}/(?:replay|video)/(?P<id>[^/#&?]+)'
14 'url': 'https://olympics.com/fr/video/men-s-109kg-group-a-weightlifting-tokyo-2020-replays',
16 'id': 'f6a0753c-8e6f-4b7d-a435-027054a4f8e9',
18 'title': '+109kg (H) Groupe A - Haltérophilie | Replay de Tokyo 2020',
19 'upload_date': '20210801',
20 'timestamp': 1627783200,
21 'description': 'md5:c66af4a5bc7429dbcc43d15845ff03b3',
22 'uploader': 'International Olympic Committee',
25 'skip_download': True,
28 'url': 'https://olympics.com/tokyo-2020/en/replay/bd242924-4b22-49a5-a846-f1d4c809250d/mens-bronze-medal-match-hun-esp',
29 'only_matching': True,
32 def _real_extract(self
, url
):
33 id = self
._match
_id
(url
)
35 webpage
= self
._download
_webpage
(url
, id)
36 title
= self
._html
_search
_meta
(('title', 'og:title', 'twitter:title'), webpage
)
37 uuid
= self
._html
_search
_meta
('episode_uid', webpage
)
38 m3u8_url
= self
._html
_search
_meta
('video_url', webpage
)
39 json_ld
= self
._search
_json
_ld
(webpage
, uuid
)
40 thumbnails_list
= json_ld
.get('image')
41 if not thumbnails_list
:
42 thumbnails_list
= self
._html
_search
_regex
(
43 r
'["\']image
["\']:\s*["\']([^
"\']+)["\']', webpage, 'images
', default='')
44 thumbnails_list = thumbnails_list.replace('[', '').replace(']', '').split(',')
45 thumbnails_list = [thumbnail.strip() for thumbnail in thumbnails_list]
47 for thumbnail in thumbnails_list:
48 width_a, height_a, width = self._search_regex(
49 r'/images
/image
/private
/t_(?P
<width_a
>\d
+)-(?P
<height_a
>\d
+)_(?P
<width
>\d
+)/primary
/[\W\w\d
]+',
50 thumbnail, 'thumb
', group=(1, 2, 3), default=(None, None, None))
51 width_a, height_a, width = int_or_none(width_a), int_or_none(height_a), int_or_none(width)
55 'height
': int_or_none(try_get(width, lambda x: x * height_a / width_a))
57 m3u8_url = self._download_json(
58 f'https
://olympics
.com
/tokenGenerator?url
={m3u8_url}
', uuid, note='Downloading m3u8 url
')
59 formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, uuid, m3u8_id='hls
')
60 self._sort_formats(formats)
65 'thumbnails
': thumbnails,
67 'subtitles
': subtitles,