]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/oneplace.py
[ie/matchtv] Fix extractor (#10190)
[yt-dlp.git] / yt_dlp / extractor / oneplace.py
1 from .common import InfoExtractor
2
3
4 class OnePlacePodcastIE(InfoExtractor):
5 _VALID_URL = r'https?://www\.oneplace\.com/[\w]+/[^/]+/listen/[\w-]+-(?P<id>\d+)'
6 _TESTS = [{
7 'url': 'https://www.oneplace.com/ministries/a-daily-walk/listen/living-in-the-last-days-part-2-958461.html',
8 'info_dict': {
9 'id': '958461',
10 'ext': 'mp3',
11 'title': 'Living in the Last Days Part 2 | A Daily Walk with John Randall',
12 'description': 'md5:fbb8f1cf21447ac54ecaa2887fc20c6e',
13 },
14 }, {
15 'url': 'https://www.oneplace.com/ministries/ankerberg-show/listen/ep-3-relying-on-the-constant-companionship-of-the-holy-spirit-part-2-922513.html',
16 'info_dict': {
17 'id': '922513',
18 'ext': 'mp3',
19 'description': 'md5:8b810b4349aa40a5d033b4536fe428e1',
20 'title': 'md5:ce10f7d8d5ddcf485ed8905ef109659d',
21 },
22 }]
23
24 def _real_extract(self, url):
25 video_id = self._match_id(url)
26 webpage = self._download_webpage(url, video_id)
27
28 return {
29 'id': video_id,
30 'url': self._search_regex((
31 r'mp3-url\s*=\s*"([^"]+)',
32 r'<div[^>]+id\s*=\s*"player"[^>]+data-media-url\s*=\s*"(?P<media_url>[^"]+)',
33 ), webpage, 'media url'),
34 'ext': 'mp3',
35 'vcodec': 'none',
36 'title': self._html_search_regex((
37 r'<div[^>]class\s*=\s*"details"[^>]+>[^<]<h2[^>]+>(?P<content>[^>]+)>',
38 self._meta_regex('og:title'), self._meta_regex('title'),
39 ), webpage, 'title', group='content', default=None),
40 'description': self._html_search_regex(
41 r'<div[^>]+class="[^"]+epDesc"[^>]*>\s*(?P<desc>.+?)\s*</div>',
42 webpage, 'description', default=None),
43 }