Add albums parsing

Author: vanyasem

examples/get_album_audio.py

@@ -24,27 +24,26 @@ def main():
     offset = 0
 
     while True:
-        audios = vkaudio.get(album_id='-89975290_74038117', offset=offset)
+        albums = vkaudio.get(owner_id='194957739', get_albums=True, offset=offset)
 
-        if not audios:
+        if not albums:
             break
 
-        for audio in audios:
-            artists[audio['artist']] += 1
+        for album in albums:
+            artists[album['artist']] += 1
 
-        offset += len(audios)
+        offset += len(albums)
 
     # Составляем рейтинг первых 15
     print('\nTop 15:')
     for artist, tracks in artists.most_common(15):
         print('{} - {} tracks'.format(artist, tracks))
 
-    # Ищем треки самого популярного
-    most_common_artist = artists.most_common(1)[0][0]
+    # Ищем треки последнего альбома
+    album = vkaudio.get(owner_id='194957739', get_albums=True)[0]
+    print('\nSearch for', album['title'])
 
-    print('\nSearch for', most_common_artist)
-
-    tracks = vkaudio.search(q=most_common_artist)[:10]
+    tracks = vkaudio.get(album_id=album['id'][25:])
 
     for n, track in enumerate(tracks, 1):
         print('{}. {} {}'.format(n, track['title'], track['url']))

vk_api/audio.py

@@ -6,7 +6,7 @@
 from .audio_url_decoder import decode_audio_url
 from .exceptions import AccessDenied
 
-RE_AUDIO = re.compile(r'audio\d+_\d+_audios\d+')
+RE_AUDIO = re.compile(r'audio[-\d]+_\d+_audios\d+')
 
 
 class VkAudio:
@@ -30,12 +30,16 @@ def get(self, owner_id=None, album_id=None, offset=0):
             )
         elif owner_id is not None and album_id is not None:
             raise TypeError('get() too many arguments')
+        if album_id is not None and get_albums is True:
+            raise TypeError('get() too many arguments')
 
         id = owner_id
         url = 'https://m.vk.com/audios{}'
         if album_id is not None:
             id = album_id
             url = 'https://m.vk.com/audio?act=audio_playlist{}'
+        if get_albums is True:
+            url = 'https://m.vk.com/audio?act=audio_playlists{}'
 
         response = self._vk.http.get(
             url.format(id),
@@ -52,6 +56,8 @@ def get(self, owner_id=None, album_id=None, offset=0):
                 )
             )
 
+        if get_albums:
+            return scrap_albums(response.text)
         return scrap_data(response.text)
 
     def search_user(self, owner_id, q=''):
@@ -123,3 +129,22 @@ def scrap_data(html):
         })
 
     return tracks
+
+
+def scrap_albums(html):
+    """ Парсинг списка альбомов из html странцы """
+
+    soup = BeautifulSoup(html, 'html.parser')
+    albums = []
+    for album in soup.find_all('div', {'class': 'audioPlaylistsPage__item'}):
+        link = album.select('.audioPlaylistsPage__itemLink')[0]['href']
+
+        albums.append({
+            'artist': album.select('.audioPlaylistsPage__author')[0].text,
+            'title': album.select('.audioPlaylistsPage__title')[0].text,
+            'plays': album.select('.audioPlaylistsPage__stats')[0].text,
+            'id': album['class'][1],
+            'url': 'https://m.vk.com/audio?act=audio_playlist{}'.format(link)
+        })
+
+    return albums