[soundcloud:user] Update tests

[youtube-dl] / youtube_dl / extractor / soundcloud.py

diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index 46332e5c238619c9b572e4c5701ed1169eae2d20..13463ae4fe867d2a0697b536d189d3fabc344ef7 100644 (file)
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -34,7 +34,7 @@ class SoundcloudIE(InfoExtractor):
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?!stations/track)
                             (?P<uploader>[\w\d-]+)/
-                            (?!(?:tracks|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
+                            (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
@@ -157,7 +157,7 @@ class SoundcloudIE(InfoExtractor):
         },
     ]
 
-    _CLIENT_ID = 'LvWovRaJZlWCHql0bISuum8Bd2KX79mb'
+    _CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK'
 
     @staticmethod
     def _extract_urls(webpage):
@@ -181,7 +181,6 @@ class SoundcloudIE(InfoExtractor):
         thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url')
         if isinstance(thumbnail, compat_str):
             thumbnail = thumbnail.replace('-large', '-t500x500')
-        ext = 'mp3'
         result = {
             'id': track_id,
             'uploader': info.get('user', {}).get('username'),
@@ -215,8 +214,11 @@ class SoundcloudIE(InfoExtractor):
             track_id, 'Downloading track url', query=query)
 
         for key, stream_url in format_dict.items():
-            abr = int_or_none(self._search_regex(
-                r'_(\d+)_url', key, 'audio bitrate', default=None))
+            ext, abr = 'mp3', None
+            mobj = re.search(r'_([^_]+)_(\d+)_url', key)
+            if mobj:
+                ext, abr = mobj.groups()
+                abr = int(abr)
             if key.startswith('http'):
                 stream_formats = [{
                     'format_id': key,
@@ -234,13 +236,14 @@ class SoundcloudIE(InfoExtractor):
                 }]
             elif key.startswith('hls'):
                 stream_formats = self._extract_m3u8_formats(
-                    stream_url, track_id, 'mp3', entry_protocol='m3u8_native',
+                    stream_url, track_id, ext, entry_protocol='m3u8_native',
                     m3u8_id=key, fatal=False)
             else:
                 continue
 
-            for f in stream_formats:
-                f['abr'] = abr
+            if abr:
+                for f in stream_formats:
+                    f['abr'] = abr
 
             formats.extend(stream_formats)
 
@@ -250,7 +253,7 @@ class SoundcloudIE(InfoExtractor):
             formats.append({
                 'format_id': 'fallback',
                 'url': update_url_query(info['stream_url'], query),
-                'ext': ext,
+                'ext': 'mp3',
             })
 
         for f in formats:
@@ -365,7 +368,6 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
 
 
 class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
-    _API_BASE = 'https://api.soundcloud.com'
     _API_V2_BASE = 'https://api-v2.soundcloud.com'
 
     def _extract_playlist(self, base_url, playlist_id, playlist_title):
@@ -386,8 +388,12 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
                 next_href, playlist_id, 'Downloading track page %s' % (i + 1))
 
             collection = response['collection']
-            if not collection:
-                break
+
+            if not isinstance(collection, list):
+                collection = []
+
+            # Empty collection may be returned, in this case we proceed
+            # straight to next_href
 
             def resolve_permalink_url(candidates):
                 for cand in candidates:
@@ -426,46 +432,53 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
                             (?:(?:www|m)\.)?soundcloud\.com/
                             (?P<user>[^/]+)
                             (?:/
-                                (?P<rsrc>tracks|sets|reposts|likes|spotlight)
+                                (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight)
                             )?
                             /?(?:[?#].*)?$
                     '''
     IE_NAME = 'soundcloud:user'
     _TESTS = [{
-        'url': 'https://soundcloud.com/the-akashic-chronicler',
+        'url': 'https://soundcloud.com/soft-cell-official',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (All)',
+            'id': '207965082',
+            'title': 'Soft Cell (All)',
         },
-        'playlist_mincount': 74,
+        'playlist_mincount': 28,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
+        'url': 'https://soundcloud.com/soft-cell-official/tracks',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Tracks)',
+            'id': '207965082',
+            'title': 'Soft Cell (Tracks)',
         },
-        'playlist_mincount': 37,
+        'playlist_mincount': 27,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/sets',
+        'url': 'https://soundcloud.com/soft-cell-official/albums',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Playlists)',
+            'id': '207965082',
+            'title': 'Soft Cell (Albums)',
+        },
+        'playlist_mincount': 1,
+    }, {
+        'url': 'https://soundcloud.com/jcv246/sets',
+        'info_dict': {
+            'id': '12982173',
+            'title': 'Jordi / cv (Playlists)',
         },
         'playlist_mincount': 2,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/reposts',
+        'url': 'https://soundcloud.com/jcv246/reposts',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Reposts)',
+            'id': '12982173',
+            'title': 'Jordi / cv (Reposts)',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 6,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/likes',
+        'url': 'https://soundcloud.com/clalberg/likes',
         'info_dict': {
-            'id': '114582580',
-            'title': 'The Akashic Chronicler (Likes)',
+            'id': '11817582',
+            'title': 'clalberg (Likes)',
         },
-        'playlist_mincount': 321,
+        'playlist_mincount': 5,
     }, {
         'url': 'https://soundcloud.com/grynpyret/spotlight',
         'info_dict': {
@@ -476,10 +489,11 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
     }]
 
     _BASE_URL_MAP = {
-        'all': '%s/profile/soundcloud:users:%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_BASE,
+        'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'reposts': '%s/profile/soundcloud:users:%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
     }
@@ -487,6 +501,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
     _TITLE_MAP = {
         'all': 'All',
         'tracks': 'Tracks',
+        'albums': 'Albums',
         'sets': 'Playlists',
         'reposts': 'Reposts',
         'likes': 'Likes',