diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-15 16:49:24 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-15 16:49:24 +0000 |
commit | 2415e66f889f38503b73e8ebc5f43ca342390e5c (patch) | |
tree | ac48ab69d1d96bae3d83756134921e0d90593aa5 /yt_dlp/extractor/appleconnect.py | |
parent | Initial commit. (diff) | |
download | yt-dlp-2415e66f889f38503b73e8ebc5f43ca342390e5c.tar.xz yt-dlp-2415e66f889f38503b73e8ebc5f43ca342390e5c.zip |
Adding upstream version 2024.03.10.upstream/2024.03.10
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'yt_dlp/extractor/appleconnect.py')
-rw-r--r-- | yt_dlp/extractor/appleconnect.py | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/yt_dlp/extractor/appleconnect.py b/yt_dlp/extractor/appleconnect.py new file mode 100644 index 0000000..d00b0f9 --- /dev/null +++ b/yt_dlp/extractor/appleconnect.py @@ -0,0 +1,50 @@ +from .common import InfoExtractor +from ..utils import ( + str_to_int, + ExtractorError +) + + +class AppleConnectIE(InfoExtractor): + _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)' + _TESTS = [{ + 'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3', + 'md5': 'c1d41f72c8bcaf222e089434619316e4', + 'info_dict': { + 'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3', + 'ext': 'm4v', + 'title': 'Energy', + 'uploader': 'Drake', + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20150710', + 'timestamp': 1436545535, + }, + }, { + 'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + try: + video_json = self._html_search_regex( + r'class="auc-video-data">(\{.*?\})', webpage, 'json') + except ExtractorError: + raise ExtractorError('This post doesn\'t contain a video', expected=True) + + video_data = self._parse_json(video_json, video_id) + timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp')) + like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None)) + + return { + 'id': video_id, + 'url': video_data['sslSrc'], + 'title': video_data['title'], + 'description': video_data['description'], + 'uploader': video_data['artistName'], + 'thumbnail': video_data['artworkUrl'], + 'timestamp': timestamp, + 'like_count': like_count, + } |