]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/appleconnect.py
[misc] Add `hatch`, `ruff`, `pre-commit` and improve dev docs (#7409)
[yt-dlp.git] / yt_dlp / extractor / appleconnect.py
1 from .common import InfoExtractor
2 from ..utils import ExtractorError, str_to_int
3
4
5 class AppleConnectIE(InfoExtractor):
6 _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
7 _TESTS = [{
8 'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
9 'md5': 'c1d41f72c8bcaf222e089434619316e4',
10 'info_dict': {
11 'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
12 'ext': 'm4v',
13 'title': 'Energy',
14 'uploader': 'Drake',
15 'thumbnail': r're:^https?://.*\.jpg$',
16 'upload_date': '20150710',
17 'timestamp': 1436545535,
18 },
19 }, {
20 'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
21 'only_matching': True,
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 try:
29 video_json = self._html_search_regex(
30 r'class="auc-video-data">(\{.*?\})', webpage, 'json')
31 except ExtractorError:
32 raise ExtractorError('This post doesn\'t contain a video', expected=True)
33
34 video_data = self._parse_json(video_json, video_id)
35 timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
36 like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
37
38 return {
39 'id': video_id,
40 'url': video_data['sslSrc'],
41 'title': video_data['title'],
42 'description': video_data['description'],
43 'uploader': video_data['artistName'],
44 'thumbnail': video_data['artworkUrl'],
45 'timestamp': timestamp,
46 'like_count': like_count,
47 }