]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/appleconnect.py
[ie/orf:on] Improve extraction (#9677)
[yt-dlp.git] / yt_dlp / extractor / appleconnect.py
1 from .common import InfoExtractor
2 from ..utils import (
3 str_to_int,
4 ExtractorError
5 )
6
7
8 class AppleConnectIE(InfoExtractor):
9 _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
10 _TESTS = [{
11 'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
12 'md5': 'c1d41f72c8bcaf222e089434619316e4',
13 'info_dict': {
14 'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
15 'ext': 'm4v',
16 'title': 'Energy',
17 'uploader': 'Drake',
18 'thumbnail': r're:^https?://.*\.jpg$',
19 'upload_date': '20150710',
20 'timestamp': 1436545535,
21 },
22 }, {
23 'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
24 'only_matching': True,
25 }]
26
27 def _real_extract(self, url):
28 video_id = self._match_id(url)
29 webpage = self._download_webpage(url, video_id)
30
31 try:
32 video_json = self._html_search_regex(
33 r'class="auc-video-data">(\{.*?\})', webpage, 'json')
34 except ExtractorError:
35 raise ExtractorError('This post doesn\'t contain a video', expected=True)
36
37 video_data = self._parse_json(video_json, video_id)
38 timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
39 like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
40
41 return {
42 'id': video_id,
43 'url': video_data['sslSrc'],
44 'title': video_data['title'],
45 'description': video_data['description'],
46 'uploader': video_data['artistName'],
47 'thumbnail': video_data['artworkUrl'],
48 'timestamp': timestamp,
49 'like_count': like_count,
50 }