]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/startrek.py
[extractor] Deprecate `_sort_formats`
[yt-dlp.git] / yt_dlp / extractor / startrek.py
1 from .common import InfoExtractor
2 from ..utils import int_or_none, urljoin
3
4
5 class StarTrekIE(InfoExtractor):
6 _VALID_URL = r'(?P<base>https?://(?:intl|www)\.startrek\.com)/videos/(?P<id>[^/]+)'
7 _TESTS = [{
8 'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room',
9 'md5': '491df5035c9d4dc7f63c79caaf9c839e',
10 'info_dict': {
11 'id': 'watch-welcoming-jess-bush-to-the-ready-room',
12 'ext': 'mp4',
13 'title': 'WATCH: Welcoming Jess Bush to The Ready Room',
14 'duration': 1888,
15 'timestamp': 1655388000,
16 'upload_date': '20220616',
17 'description': 'md5:1ffee884e3920afbdd6dd04e926a1221',
18 'thumbnail': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14794_rr_thumb_107_yt_16x9\.jpg(?:\?.+)?',
19 'subtitles': {'en-US': [{
20 'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_107_v4\.vtt',
21 }, {
22 'url': 'https://media.startrek.com/2022/06/16/2043801155561/1069981_hls/trr_snw_107_v4-c4bfc25d/stream_vtt.m3u8',
23 }]},
24 }
25 }, {
26 'url': 'https://www.startrek.com/videos/watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
27 'md5': 'f5ad74fbb86e91e0882fc0a333178d1d',
28 'info_dict': {
29 'id': 'watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
30 'ext': 'mp4',
31 'title': 'WATCH: Ethan Peck and Gia Sandhu Beam Down to The Ready Room',
32 'duration': 1986,
33 'timestamp': 1654221600,
34 'upload_date': '20220603',
35 'description': 'md5:b3aa0edacfe119386567362dec8ed51b',
36 'thumbnail': r're:https://www\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14792_rr_thumb_105_yt_16x9_1.jpg(?:\?.+)?',
37 'subtitles': {'en-US': [{
38 'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_105_v5\.vtt',
39 }]},
40 }
41 }]
42
43 def _real_extract(self, url):
44 urlbase, video_id = self._match_valid_url(url).group('base', 'id')
45 webpage = self._download_webpage(url, video_id)
46
47 player = self._search_regex(
48 r'(<\s*div\s+id\s*=\s*"cvp-player-[^<]+<\s*/div\s*>)', webpage, 'player')
49
50 hls = self._html_search_regex(r'\bdata-hls\s*=\s*"([^"]+)"', player, 'HLS URL')
51 formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls, video_id, 'mp4')
52
53 captions = self._html_search_regex(
54 r'\bdata-captions-url\s*=\s*"([^"]+)"', player, 'captions URL', fatal=False)
55 if captions:
56 subtitles.setdefault('en-US', [])[:0] = [{'url': urljoin(urlbase, captions)}]
57
58 # NB: Most of the data in the json_ld is undesirable
59 json_ld = self._search_json_ld(webpage, video_id, fatal=False)
60
61 return {
62 'id': video_id,
63 'title': self._html_search_regex(
64 r'\bdata-title\s*=\s*"([^"]+)"', player, 'title', json_ld.get('title')),
65 'description': self._html_search_regex(
66 r'(?s)<\s*div\s+class\s*=\s*"header-body"\s*>(.+?)<\s*/div\s*>',
67 webpage, 'description', fatal=False),
68 'duration': int_or_none(self._html_search_regex(
69 r'\bdata-duration\s*=\s*"(\d+)"', player, 'duration', fatal=False)),
70 'formats': formats,
71 'subtitles': subtitles,
72 'thumbnail': urljoin(urlbase, self._html_search_regex(
73 r'\bdata-poster-url\s*=\s*"([^"]+)"', player, 'thumbnail', fatal=False)),
74 'timestamp': json_ld.get('timestamp'),
75 }