- # extract uploader (which is in the url)
- uploader = mobj.group(1)
- # extract simple title (uploader + slug of song title)
- slug_title = mobj.group(2)
- full_title = '%s/%s' % (uploader, slug_title)
-
- self.report_resolve(full_title)
-
- url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
- info_json_url = self._resolv_url(url)
- info_json = self._download_webpage(info_json_url, full_title, u'Downloading info JSON')
-
- info = json.loads(info_json)
- return self._extract_info_dict(info, full_title)
-
-class SoundcloudSetIE(SoundcloudIE):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
- IE_NAME = u'soundcloud:set'
- _TEST = {
- u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
- u"playlist": [
- {
- u"file":"30510138.mp3",
- u"md5":"f9136bf103901728f29e419d2c70f55d",
- u"info_dict": {
- u"upload_date": u"20111213",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"D-D-Dance"
- }
- },
- {
- u"file":"47127625.mp3",
- u"md5":"09b6758a018470570f8fd423c9453dd8",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"The Royal Concept - Gimme Twice"
- }
- },
- {
- u"file":"47127627.mp3",
- u"md5":"154abd4e418cea19c3b901f1e1306d9c",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"uploader": u"The Royal Concept",
- u"title": u"Goldrushed"
- }
- },
- {
- u"file":"47127629.mp3",
- u"md5":"2f5471edc79ad3f33a683153e96a79c1",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"In the End"
- }
- },
- {
- u"file":"47127631.mp3",
- u"md5":"f9ba87aa940af7213f98949254f1c6e2",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"Knocked Up"
- }
- },
- {
- u"file":"75206121.mp3",
- u"md5":"f9d1fe9406717e302980c30de4af9353",
- u"info_dict": {
- u"upload_date": u"20130116",
- u"description": u"The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central). \r\nAs a gift to our fans we would like to offer you a free download of the track! ",
- u"uploader": u"The Royal Concept",
- u"title": u"World On Fire"
- }
- }
- ]
+ full_title = resolve_title = '%s/%s' % mobj.group('uploader', 'title')
+ token = mobj.group('token')
+ if token:
+ resolve_title += '/%s' % token
+ info_json_url = self._resolv_url(self._BASE_URL + resolve_title)
+
+ info = self._download_json(
+ info_json_url, full_title, 'Downloading info JSON', query=query)
+
+ return self._extract_info_dict(info, full_title, token)
+
+
+class SoundcloudPlaylistBaseIE(SoundcloudIE):
+ 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 = track.get('permalink_url')
+ if not url:
+ if not track_id:
+ continue
+ url = self._API_V2_BASE + 'tracks/' + track_id
+ if token:
+ url += '?secret_token=' + token
+ entries.append(self.url_result(
+ url, SoundcloudIE.ie_key(), track_id))
+ return self.playlist_result(
+ entries, playlist_id,
+ playlist.get('title'),
+ playlist.get('description'))
+
+
+class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
+ _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?'
+ IE_NAME = 'soundcloud:set'
+ _TESTS = [{
+ 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep',
+ 'info_dict': {
+ 'id': '2284613',
+ 'title': 'The Royal Concept EP',
+ 'description': 'md5:71d07087c7a449e8941a70a29e34671e',
+ },
+ 'playlist_mincount': 5,
+ }, {
+ 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep/token',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+
+ full_title = '%s/sets/%s' % mobj.group('uploader', 'slug_title')
+ token = mobj.group('token')
+ if token:
+ full_title += '/' + token
+
+ info = self._download_json(self._resolv_url(
+ self._BASE_URL + full_title), full_title)
+
+ if 'errors' in info:
+ msgs = (compat_str(err['error_message']) for err in info['errors'])
+ raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
+
+ return self._extract_set(info, token)
+
+
+class SoundcloudPagedPlaylistBaseIE(SoundcloudIE):
+ def _extract_playlist(self, base_url, playlist_id, playlist_title):
+ COMMON_QUERY = {
+ 'limit': 80000,
+ 'linked_partitioning': '1',
+ }
+
+ query = COMMON_QUERY.copy()
+ query['offset'] = 0
+
+ next_href = base_url
+
+ entries = []
+ for i in itertools.count():
+ response = self._download_json(
+ next_href, playlist_id,
+ 'Downloading track page %s' % (i + 1), query=query)
+
+ collection = response['collection']
+
+ if not isinstance(collection, list):
+ collection = []
+
+ # Empty collection may be returned, in this case we proceed
+ # straight to next_href
+
+ def resolve_entry(candidates):
+ for cand in candidates:
+ if not isinstance(cand, dict):
+ continue
+ permalink_url = url_or_none(cand.get('permalink_url'))
+ if not permalink_url:
+ continue
+ return self.url_result(
+ permalink_url,
+ SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None,
+ str_or_none(cand.get('id')), cand.get('title'))
+
+ for e in collection:
+ entry = resolve_entry((e, e.get('track'), e.get('playlist')))
+ if entry:
+ entries.append(entry)
+
+ next_href = response.get('next_href')
+ if not next_href:
+ break
+
+ next_href = response['next_href']
+ parsed_next_href = compat_urlparse.urlparse(next_href)
+ query = compat_urlparse.parse_qs(parsed_next_href.query)
+ query.update(COMMON_QUERY)
+
+ return {
+ '_type': 'playlist',
+ 'id': playlist_id,
+ 'title': playlist_title,
+ 'entries': entries,
+ }
+
+
+class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:(?:www|m)\.)?soundcloud\.com/
+ (?P<user>[^/]+)
+ (?:/
+ (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight)
+ )?
+ /?(?:[?#].*)?$
+ '''
+ IE_NAME = 'soundcloud:user'
+ _TESTS = [{
+ 'url': 'https://soundcloud.com/soft-cell-official',
+ 'info_dict': {
+ 'id': '207965082',
+ 'title': 'Soft Cell (All)',
+ },
+ 'playlist_mincount': 28,
+ }, {
+ 'url': 'https://soundcloud.com/soft-cell-official/tracks',
+ 'info_dict': {
+ 'id': '207965082',
+ 'title': 'Soft Cell (Tracks)',
+ },
+ 'playlist_mincount': 27,
+ }, {
+ 'url': 'https://soundcloud.com/soft-cell-official/albums',
+ 'info_dict': {
+ 'id': '207965082',
+ 'title': 'Soft Cell (Albums)',
+ },
+ 'playlist_mincount': 1,
+ }, {
+ 'url': 'https://soundcloud.com/jcv246/sets',
+ 'info_dict': {
+ 'id': '12982173',
+ 'title': 'Jordi / cv (Sets)',
+ },
+ 'playlist_mincount': 2,
+ }, {
+ 'url': 'https://soundcloud.com/jcv246/reposts',
+ 'info_dict': {
+ 'id': '12982173',
+ 'title': 'Jordi / cv (Reposts)',
+ },
+ 'playlist_mincount': 6,
+ }, {
+ 'url': 'https://soundcloud.com/clalberg/likes',
+ 'info_dict': {
+ 'id': '11817582',
+ 'title': 'clalberg (Likes)',
+ },
+ 'playlist_mincount': 5,
+ }, {
+ 'url': 'https://soundcloud.com/grynpyret/spotlight',
+ 'info_dict': {
+ 'id': '7098329',
+ 'title': 'Grynpyret (Spotlight)',
+ },
+ 'playlist_mincount': 1,
+ }]
+
+ _BASE_URL_MAP = {
+ 'all': 'stream/users/%s',
+ 'tracks': 'users/%s/tracks',
+ 'albums': 'users/%s/albums',
+ 'sets': 'users/%s/playlists',
+ 'reposts': 'stream/users/%s/reposts',
+ 'likes': 'users/%s/likes',
+ 'spotlight': 'users/%s/spotlight',