Merge c72b48d49c into 3a84be9d16

yt_dlp/extractor/_extractors.py

@@ -1723,7 +1723,10 @@
 )
 from .restudy import RestudyIE
 from .reuters import ReutersIE
-from .reverbnation import ReverbNationIE
+from .reverbnation import (
+    ReverbNationArtistIE,
+    ReverbNationIE,
+)
 from .rheinmaintv import RheinMainTVIE
 from .ridehome import RideHomeIE
 from .rinsefm import (

yt_dlp/extractor/reverbnation.py

@@ -1,11 +1,17 @@
+import functools
+
 from .common import InfoExtractor
 from ..utils import (
-    qualities,
+    InAdvancePagedList,
+    int_or_none,
     str_or_none,
+    traverse_obj,
+    url_or_none,
 )
 
 
 class ReverbNationIE(InfoExtractor):
+    IE_NAME = 'reverbnation:song'
     _VALID_URL = r'https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
     _TESTS = [{
         'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
@@ -13,13 +19,30 @@ class ReverbNationIE(InfoExtractor):
         'info_dict': {
             'id': '16965047',
             'ext': 'mp3',
+            'vcodec': 'none',
+            'tbr': 192,
+            'duration': 217,
             'title': 'MONA LISA',
-            'uploader': 'ALKILADOS',
-            'uploader_id': '216429',
+            'artists': ['ALKILADOS'],
             'thumbnail': r're:^https?://.*\.jpg',
         },
     }]
 
+    def _extract_song(self, json_data):
+        return {
+            'ext': 'mp3',
+            'vcodec': 'none',
+            **traverse_obj(json_data, {
+                'id': ('id', {str_or_none}),
+                'title': ('name', {str}),
+                'artists': ('artist', 'name', all),
+                'thumbnail': ('image', {url_or_none}),
+                'duration': ('duration', {int_or_none}),
+                'tbr': ('bitrate', {int_or_none}),
+                'url': ('url', {url_or_none}),
+            }),
+        }
+
     def _real_extract(self, url):
         song_id = self._match_id(url)
 
@@ -29,23 +52,45 @@ def _real_extract(self, url):
             note=f'Downloading information of song {song_id}',
         )
 
-        THUMBNAILS = ('thumbnail', 'image')
-        quality = qualities(THUMBNAILS)
-        thumbnails = []
-        for thumb_key in THUMBNAILS:
-            if api_res.get(thumb_key):
-                thumbnails.append({
-                    'url': api_res[thumb_key],
-                    'preference': quality(thumb_key),
-                })
+        return self._extract_song(api_res)
 
-        return {
-            'id': song_id,
-            'title': api_res['name'],
-            'url': api_res['url'],
-            'uploader': api_res.get('artist', {}).get('name'),
-            'uploader_id': str_or_none(api_res.get('artist', {}).get('id')),
-            'thumbnails': thumbnails,
-            'ext': 'mp3',
-            'vcodec': 'none',
-        }
+
+class ReverbNationArtistIE(ReverbNationIE):
+    IE_NAME = 'reverbnation:artist'
+    _VALID_URL = r'https?://(?:www\.)?reverbnation\.com/(?P<id>[\w-]+)(?:/songs)?$'
+    _TESTS = [{
+        'url': 'https://www.reverbnation.com/morganandersson',
+        'info_dict': {
+            'id': '1078497',
+            'title': 'morganandersson',
+        },
+        'playlist_mincount': 8,
+    }, {
+        'url': 'https://www.reverbnation.com/monogem/songs',
+        'info_dict': {
+            'id': '3716672',
+            'title': 'monogem',
+        },
+        'playlist_mincount': 10,
+    }]
+    _PAGE_SIZE = 25
+
+    def _entries(self, artist_id, page):
+        page_data = self._download_json(
+            f'https://www.reverbnation.com/api/artist/{artist_id}/songs',
+            f'{artist_id}_{page + 1}', query={'page': page + 1, 'per_page': self._PAGE_SIZE})
+        for song_data in page_data['results']:
+            yield self._extract_song(song_data)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        artist_url = self._html_search_meta('twitter:player', webpage, 'player url')
+        artist_id = self._search_regex(r'artist_(?P<artist>\d+)', artist_url, 'artist id')
+        page_data = self._search_json('"SONGS_WITH_PAGINATION":', webpage, 'json_data', display_id)
+        total_pages = traverse_obj(page_data, ('pagination', 'page_count', {int}))
+        self._PAGE_SIZE = traverse_obj(page_data, ('pagination', 'per_page', {int}))
+
+        return self.playlist_result(InAdvancePagedList(
+            functools.partial(self._entries, artist_id),
+            total_pages, self._PAGE_SIZE), artist_id, display_id)