Merge branch 'deezer' of https://github.com/LucBerge/youtube-dl into LucBerge-deezer

youtube_dlc/extractor/deezer.py

@@ -11,28 +11,15 @@
 )
 
 
-class DeezerPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.deezer.com/playlist/176747451',
-        'info_dict': {
-            'id': '176747451',
-            'title': 'Best!',
-            'uploader': 'Anonymous',
-            'thumbnail': r're:^https?://cdn-images\.deezer\.com/images/cover/.*\.jpg$',
-        },
-        'playlist_count': 30,
-        'skip': 'Only available in .de',
-    }
-
-    def _real_extract(self, url):
-        if 'test' not in self._downloader.params:
+class DeezerBaseInfoExtractor(InfoExtractor):
+    def get_data(self, url):
+        if not self._downloader.params.get('test'):
             self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
 
         mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        data_id = mobj.group('id')
 
-        webpage = self._download_webpage(url, playlist_id)
+        webpage = self._download_webpage(url, data_id)
         geoblocking_msg = self._html_search_regex(
             r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
             default=None)
@@ -45,6 +32,24 @@ def _real_extract(self, url):
              r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
             webpage, 'data JSON')
         data = json.loads(data_json)
+        return data_id, webpage, data
+
+
+class DeezerPlaylistIE(DeezerBaseInfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.deezer.com/playlist/176747451',
+        'info_dict': {
+            'id': '176747451',
+            'title': 'Best!',
+            'uploader': 'anonymous',
+            'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
+        },
+        'playlist_count': 29,
+    }
+
+    def _real_extract(self, url):
+        playlist_id, webpage, data = self.get_data(url)
 
         playlist_title = data.get('DATA', {}).get('TITLE')
         playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
@@ -52,31 +57,23 @@ def _real_extract(self, url):
             r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
             'playlist thumbnail')
 
-        preview_pattern = self._search_regex(
-            r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage,
-            'preview URL pattern', fatal=False)
         entries = []
-        for s in data['SONGS']['data']:
-            puid = s['MD5_ORIGIN']
-            preview_video_url = preview_pattern.\
-                replace('{0}', puid[0]).\
-                replace('{1}', puid).\
-                replace('{2}', s['MEDIA_VERSION'])
+        for s in data.get('SONGS', {}).get('data'):
             formats = [{
                 'format_id': 'preview',
-                'url': preview_video_url,
+                'url': s.get('MEDIA', [{}])[0].get('HREF'),
                 'preference': -100,  # Only the first 30 seconds
                 'ext': 'mp3',
             }]
             self._sort_formats(formats)
             artists = ', '.join(
-                orderedSet(a['ART_NAME'] for a in s['ARTISTS']))
+                orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
             entries.append({
-                'id': s['SNG_ID'],
+                'id': s.get('SNG_ID'),
                 'duration': int_or_none(s.get('DURATION')),
-                'title': '%s - %s' % (artists, s['SNG_TITLE']),
-                'uploader': s['ART_NAME'],
-                'uploader_id': s['ART_ID'],
+                'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
+                'uploader': s.get('ART_NAME'),
+                'uploader_id': s.get('ART_ID'),
                 'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
                 'formats': formats,
             })
@@ -89,3 +86,62 @@ def _real_extract(self, url):
             'thumbnail': playlist_thumbnail,
             'entries': entries,
         }
+
+
+class DeezerAlbumIE(DeezerBaseInfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.deezer.com/fr/album/67505622',
+        'info_dict': {
+            'id': '67505622',
+            'title': 'Last Week',
+            'uploader': 'Home Brew',
+            'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
+        },
+        'playlist_count': 7,
+    }
+
+    def _real_extract(self, url):
+        album_id, webpage, data = self.get_data(url)
+
+        album_title = data.get('DATA', {}).get('ALB_TITLE')
+        album_uploader = data.get('DATA', {}).get('ART_NAME')
+        album_thumbnail = self._search_regex(
+            r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
+            'album thumbnail')
+
+        entries = []
+        for s in data.get('SONGS', {}).get('data'):
+            formats = [{
+                'format_id': 'preview',
+                'url': s.get('MEDIA', [{}])[0].get('HREF'),
+                'preference': -100,  # Only the first 30 seconds
+                'ext': 'mp3',
+            }]
+            self._sort_formats(formats)
+            artists = ', '.join(
+                orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
+            entries.append({
+                'id': s.get('SNG_ID'),
+                'duration': int_or_none(s.get('DURATION')),
+                'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
+                'uploader': s.get('ART_NAME'),
+                'uploader_id': s.get('ART_ID'),
+                'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
+                'formats': formats,
+                'track': s.get('SNG_TITLE'),
+                'track_number': int_or_none(s.get('TRACK_NUMBER')),
+                'track_id': s.get('SNG_ID'),
+                'artist': album_uploader,
+                'album': album_title,
+                'album_artist': album_uploader,
+            })
+
+        return {
+            '_type': 'playlist',
+            'id': album_id,
+            'title': album_title,
+            'uploader': album_uploader,
+            'thumbnail': album_thumbnail,
+            'entries': entries,
+        }

youtube_dlc/extractor/extractors.py

@@ -262,7 +262,10 @@
 )
 from .dbtv import DBTVIE
 from .dctp import DctpTvIE
-from .deezer import DeezerPlaylistIE
+from .deezer import (
+    DeezerPlaylistIE,
+    DeezerAlbumIE,
+)
 from .democracynow import DemocracynowIE
 from .dfb import DFBIE
 from .dhm import DHMIE