]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/motorsport.py
[ie/matchtv] Fix extractor (#10190)
[yt-dlp.git] / yt_dlp / extractor / motorsport.py
1 import urllib.parse
2
3 from .common import InfoExtractor
4
5
6 class MotorsportIE(InfoExtractor):
7 _WORKING = False
8 IE_DESC = 'motorsport.com'
9 _VALID_URL = r'https?://(?:www\.)?motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
10 _TEST = {
11 'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
12 'info_dict': {
13 'id': '2-T3WuR-KMM',
14 'ext': 'mp4',
15 'title': 'Red Bull Racing: 2014 Rules Explained',
16 'duration': 208,
17 'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
18 'uploader': 'mcomstaff',
19 'uploader_id': 'UC334JIYKkVnyFoNCclfZtHQ',
20 'upload_date': '20140903',
21 'thumbnail': r're:^https?://.+\.jpg$',
22 },
23 'add_ie': ['Youtube'],
24 'params': {
25 'skip_download': True,
26 },
27 }
28
29 def _real_extract(self, url):
30 display_id = self._match_id(url)
31 webpage = self._download_webpage(url, display_id)
32
33 iframe_path = self._html_search_regex(
34 r'<iframe id="player_iframe"[^>]+src="([^"]+)"', webpage, 'iframe path', default=None)
35
36 if iframe_path is None:
37 iframe_path = self._html_search_regex(
38 r'<iframe [^>]*\bsrc="(https://motorsport\.tv/embed/[^"]+)', webpage, 'embed iframe path')
39 return self.url_result(iframe_path)
40
41 iframe = self._download_webpage(
42 urllib.parse.urljoin(url, iframe_path), display_id,
43 'Downloading iframe')
44 youtube_id = self._search_regex(
45 r'www.youtube.com/embed/(.{11})', iframe, 'youtube id')
46
47 return {
48 '_type': 'url_transparent',
49 'display_id': display_id,
50 'url': f'https://youtube.com/watch?v={youtube_id}',
51 }