mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
Code Issues Projects Releases Wiki Activity

[ie/difm] enhance extractor, fix test and clean up code

Browse Source
This commit is contained in:
Subrat Lima 2025-04-06 17:04:43 +05:30
parent e4b1fd68f8
commit a1694a14c3
1 changed files with 43 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
yt_dlp/extractor/difm.py
View File

@ -8,40 +8,32 @@
str_or_none,
traverse_obj,
unescapeHTML,
unified_strdate,
unified_timestamp,
)
clean_url = lambda x: unescapeHTML(sanitize_url(x, scheme='https'))
def extract_episode(episode):
return traverse_obj(episode, {
'id': ('id', {str_or_none}),
'timestamp': ('start_at', {unified_strdate}, {int_or_none}),
'duration': ('tracks', 0, 'length', {int_or_none}),
'artist': ('tracks', 0, 'display_artist', {str_or_none}),
'title': ('tracks', 0, 'display_title', {str_or_none}),
'thumbnail': ('tracks', 0, 'asset_url', {clean_url}),
'url': ('tracks', 0, 'content', 'assets', 0, 'url', {clean_url}),
'filesize': ('tracks', 0, 'content', 'assets', 0, 'size', {int_or_none}),
})
class DIFMShowEpisodeIE(InfoExtractor):
IE_NAME = 'difm:showepisode'
_VALID_URL = r'https?://www\.di\.fm/shows/(?P<show_name>[\w-]+)/episodes/(?P<episode_id>[\w-]+)'
_VALID_URL = r'https?://www\.di\.fm/shows/(?P<show_id>[\w-]+)/episodes/(?P<episode_id>[\w-]+)'
_TESTS = [
{
'url': 'https://www.di.fm/shows/airwaves-progressions-radio/episodes/001',
'md5': '5725ec4226aed05c58b6460df5e4b4df',
'info_dict': {
'id': '130151',
'ext': 'm4a',
'title': 'Progressions 001 (04 April 2020)',
'description': '',
'duration': 7456,
'thumbnail': r're:https?://.*\.jpg',
'timestamp': 20200404,
'artist': 'Airwave',
'upload_date': '20200404',
'timestamp': 1586008800,
'artists': ['Airwave'],
'filesize': 120584191,
'like_count': int,
'dislike_count': int,
},
}, {
'url': 'https://www.di.fm/shows/the-global-warm-up/episodes/1095',
@ -49,17 +41,35 @@ class DIFMShowEpisodeIE(InfoExtractor):
},
]
def _extract_data(self, episode):
return {
'ext': 'm4a',
**traverse_obj(episode, {
'id': ('id', {str_or_none}),
'timestamp': ('start_at', {unified_timestamp}),
'description': ('description', {str}),
'duration': ('tracks', 0, 'length', {int_or_none}),
'artist': ('tracks', 0, 'display_artist', {str}),
'title': ('tracks', 0, 'display_title', {str}),
'like_count': ('tracks', 0, 'votes', 'up', {int_or_none}),
'dislike_count': ('tracks', 0, 'votes', 'down', {int_or_none}),
'thumbnail': ('tracks', 0, 'asset_url', {clean_url}),
'url': ('tracks', 0, 'content', 'assets', 0, 'url', {clean_url}),
'filesize': ('tracks', 0, 'content', 'assets', 0, 'size', {int_or_none}),
}),
}
def _real_extract(self, url):
show_name, episode_id = self._match_valid_url(url).group('show_name', 'episode_id')
video_id = f'{show_name}-{episode_id}'
show_id, episode_id = self._match_valid_url(url).group('show_id', 'episode_id')
video_id = f'{show_id}-{episode_id}'
webpage = self._download_webpage(url, video_id, fatal=True, impersonate=True)
json_data = self._search_json('"EpisodeDetail.LayoutEngine",', webpage, 'json_data', video_id)['episode']
return extract_episode(json_data)
return self._extract_data(json_data)
class DIFMShowIE(InfoExtractor):
class DIFMShowIE(DIFMShowEpisodeIE):
IE_NAME = 'difm:show'
_VALID_URL = r'https?://www\.di\.fm/shows/(?P<show_name>[\w-]+)$'
_VALID_URL = r'https?://www\.di\.fm/shows/(?P<id>[\w-]+)$'
_TESTS = [{
'url': 'https://www.di.fm/shows/the-global-warm-up',
'info_dict': {
@ -71,15 +81,19 @@ class DIFMShowIE(InfoExtractor):
}]
_PAGE_SIZE = 5
def _entries(self, show_name, session_key, page):
show_metadata = self._download_json(f'https://api.audioaddict.com/v1/di/shows/{show_name}/episodes?page={page + 1}&per_page={self._PAGE_SIZE}', f'{show_name}-{page + 1}', headers={'X-Session-Key': session_key})
def _entries(self, show_id, session_key, page):
show_metadata = self._download_json(
f'https://api.audioaddict.com/v1/di/shows/{show_id}/episodes',
f'{show_id}-{page + 1}', headers={'X-Session-Key': session_key},
query={'page': str(page + 1), 'per_page': str(self._PAGE_SIZE)},
)
for episode_metadata in show_metadata:
yield extract_episode(episode_metadata)
yield self._extract_data(episode_metadata)
def _real_extract(self, url):
show_name = self._match_valid_url(url).group('show_name')
webpage = self._download_webpage(url, show_name, fatal=True, impersonate=True)
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id, fatal=True, impersonate=True)
show_title = self._html_extract_title(webpage).removesuffix(' - DI.FM')
session_key = self._search_regex(r'"session_key"\s*:\s*"(?P<session_key>\w+)"', webpage, 'session_key')
entries = OnDemandPagedList(functools.partial(self._entries, show_name, session_key), self._PAGE_SIZE)
return self.playlist_result(entries, show_name, show_title)
entries = OnDemandPagedList(functools.partial(self._entries, show_id, session_key), self._PAGE_SIZE)
return self.playlist_result(entries, show_id, show_title)