[ie/reverbnation] enhancement: added support for artist page

yt_dlp/extractor/_extractors.py

@@ -1704,7 +1704,7 @@
 )
 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 +1,11 @@
+import functools
+
 from .common import InfoExtractor
-from ..utils import (
+from ..utils import InAdvancePagedList, int_or_none, qualities, str_or_none, traverse_obj
-    qualities,
-    str_or_none,
-)
 
 
 class ReverbNationIE(InfoExtractor):
+    IE_NAME = 'reverbnation:song'
     _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
     _TESTS = [{
         'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
@@ -13,6 +13,8 @@ class ReverbNationIE(InfoExtractor):
         'info_dict': {
             'id': '16965047',
             'ext': 'mp3',
+            'tbr': 192,
+            'duration': 217,
             'title': 'MONA LISA',
             'uploader': 'ALKILADOS',
             'uploader_id': '216429',
@@ -46,6 +48,64 @@ def _real_extract(self, url):
             'uploader': api_res.get('artist', {}).get('name'),
             'uploader_id': str_or_none(api_res.get('artist', {}).get('id')),
             'thumbnails': thumbnails,
+            'duration': api_res.get('duration'),
+            'tbr': api_res.get('bitrate'),
             'ext': 'mp3',
             'vcodec': 'none',
         }
+
+
+class ReverbNationArtistIE(InfoExtractor):
+    IE_NAME = 'reverbnation:artist'
+    _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/(?P<id>[\w-]+)(?:/songs)?$'
+    _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 _yield_songs(self, json_data):
+        for song in json_data.get('results'):
+            data = {
+                'id': str_or_none(song.get('id')),
+                'title': song.get('name'),
+                'url': song.get('url'),
+                'uploader': song.get('artist', {}).get('name'),
+                'uploader_id': str_or_none(song.get('artist', {}).get('id')),
+                'thumbnail': song.get('thumbnail'),
+                'duration': int_or_none(song.get('duration')),
+                'tbr': int_or_none(song.get('bitrate')),
+                'ext': 'mp3',
+                'vcodec': 'none',
+            }
+            yield data
+
+    def _fetch_page(self, artist_id, page):
+        return self._download_json(f'https://www.reverbnation.com/api/artist/{artist_id}/songs?page={page}&per_page={self._PAGE_SIZE}', f'{artist_id}_{page}')
+
+    def _entries(self, token, first_page_data, page):
+        page_data = first_page_data if not page else self._fetch_page(token, page + 1)
+        yield from self._yield_songs(page_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')
+        playlist_data = self._fetch_page(artist_id, 1)
+        total_pages = traverse_obj(playlist_data, ('pagination', 'page_count', {int}))
+
+        return self.playlist_result(InAdvancePagedList(
+            functools.partial(self._entries, artist_id, playlist_data),
+            total_pages, self._PAGE_SIZE), artist_id, display_id)