compat_urlparse,
)
from ..utils import (
+ error_to_compat_str,
ExtractorError,
float_or_none,
HEADRequest,
'repost_count': int,
}
},
- # not streamable song
+ # not streamable song, preview
{
'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
'info_dict': {
# rtmp
'skip_download': True,
},
- 'skip': 'Preview',
},
# private link
{
'ext': 'mp3',
'title': 'Mezzo Valzer',
'description': 'md5:4138d582f81866a530317bae316e8b61',
- 'uploader': 'Giovanni Sarani',
+ 'uploader': 'Micronie',
'uploader_id': '3352531',
'timestamp': 1551394171,
'upload_date': '20190228',
'original': 0,
}
+ def _store_client_id(self, client_id):
+ self._downloader.cache.store('soundcloud', 'client_id', client_id)
+
def _update_client_id(self):
webpage = self._download_webpage('https://soundcloud.com/', None)
for src in reversed(re.findall(r'<script[^>]+src="([^"]+)"', webpage)):
script, 'client id', default=None)
if client_id:
self._CLIENT_ID = client_id
- self._downloader.cache.store('soundcloud', 'client_id', client_id)
+ self._store_client_id(client_id)
return
raise ExtractorError('Unable to extract client id')
def _download_json(self, *args, **kwargs):
+ non_fatal = kwargs.get('fatal') is False
+ if non_fatal:
+ del kwargs['fatal']
query = kwargs.get('query', {}).copy()
for _ in range(2):
query['client_id'] = self._CLIENT_ID
return super(SoundcloudIE, self)._download_json(*args, **compat_kwargs(kwargs))
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ self._store_client_id(None)
self._update_client_id()
continue
+ elif non_fatal:
+ self._downloader.report_warning(error_to_compat_str(e))
+ return False
raise
def _real_initialize(self):
})
def invalid_url(url):
- return not url or url in format_urls or re.search(r'/(?:preview|playlist)/0/30/', url)
+ return not url or url in format_urls
- def add_format(f, protocol):
+ def add_format(f, protocol, is_preview=False):
mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url)
if mobj:
for k, v in mobj.groupdict().items():
v = f.get(k)
if v:
format_id_list.append(v)
+ preview = is_preview or re.search(r'/(?:preview|playlist)/0/30/', f['url'])
+ if preview:
+ format_id_list.append('preview')
abr = f.get('abr')
if abr:
f['abr'] = int(abr)
f.update({
'format_id': '_'.join(format_id_list),
'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
+ 'preference': -10 if preview else None,
})
formats.append(f)
if not isinstance(t, dict):
continue
format_url = url_or_none(t.get('url'))
- if not format_url or t.get('snipped') or '/preview/' in format_url:
+ if not format_url:
continue
stream = self._download_json(
format_url, track_id, query=query, fatal=False)
add_format({
'url': stream_url,
'ext': ext,
- }, 'http' if protocol == 'progressive' else protocol)
+ }, 'http' if protocol == 'progressive' else protocol,
+ t.get('snipped') or '/preview/' in format_url)
if not formats:
# Old API, does not work for some tracks (e.g.
class SoundcloudPlaylistBaseIE(SoundcloudIE):
- def _extract_track_entries(self, tracks, token=None):
+ def _extract_set(self, playlist, token=None):
+ playlist_id = compat_str(playlist['id'])
+ tracks = playlist.get('tracks') or []
+ if not all([t.get('permalink_url') for t in tracks]) and token:
+ tracks = self._download_json(
+ self._API_V2_BASE + 'tracks', playlist_id,
+ 'Downloading tracks', query={
+ 'ids': ','.join([compat_str(t['id']) for t in tracks]),
+ 'playlistId': playlist_id,
+ 'playlistSecretToken': token,
+ })
entries = []
for track in tracks:
track_id = str_or_none(track.get('id'))
url += '?secret_token=' + token
entries.append(self.url_result(
url, SoundcloudIE.ie_key(), track_id))
- return entries
+ return self.playlist_result(
+ entries, playlist_id,
+ playlist.get('title'),
+ playlist.get('description'))
class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
'info_dict': {
'id': '2284613',
'title': 'The Royal Concept EP',
+ 'description': 'md5:71d07087c7a449e8941a70a29e34671e',
},
'playlist_mincount': 5,
}, {
msgs = (compat_str(err['error_message']) for err in info['errors'])
raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
- entries = self._extract_track_entries(info['tracks'], token)
-
- return self.playlist_result(
- entries, str_or_none(info.get('id')), info.get('title'))
+ return self._extract_set(info, token)
-class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
+class SoundcloudPagedPlaylistBaseIE(SoundcloudIE):
def _extract_playlist(self, base_url, playlist_id, playlist_title):
COMMON_QUERY = {
'limit': 2000000000,
self._API_V2_BASE + 'playlists/' + playlist_id,
playlist_id, 'Downloading playlist', query=query)
- entries = self._extract_track_entries(data['tracks'], token)
-
- return self.playlist_result(
- entries, playlist_id, data.get('title'), data.get('description'))
+ return self._extract_set(data, token)
class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
projects / youtube-dl / blobdiff