[extractor] Deprecate `_sort_formats`

[yt-dlp.git] / yt_dlp / extractor / bandcamp.py

diff --git a/yt_dlp/extractor/bandcamp.py b/yt_dlp/extractor/bandcamp.py
index 42223dab72017cfb1f4ca3ac6a7a6542f7b0f555..de81e0de7b00631ed8c60a01866ed1173159572e 100644 (file)
--- a/yt_dlp/extractor/bandcamp.py
+++ b/yt_dlp/extractor/bandcamp.py
@@ -1,6 +1,3 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import random
 import re
 import time
@@ -8,23 +5,24 @@
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    KNOWN_EXTENSIONS,
     ExtractorError,
     float_or_none,
     int_or_none,
-    KNOWN_EXTENSIONS,
     parse_filesize,
     str_or_none,
     try_get,
-    update_url_query,
     unified_strdate,
     unified_timestamp,
+    update_url_query,
     url_or_none,
     urljoin,
 )
 
 
 class BandcampIE(InfoExtractor):
-    _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?P<uploader>[^/]+)\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
+    _EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"']
     _TESTS = [{
         'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
         'md5': 'c557841d5e50261777a6585648adf439',
@@ -87,7 +85,7 @@ def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
             attr + ' data', group=2), video_id, fatal=fatal)
 
     def _real_extract(self, url):
-        title = self._match_id(url)
+        title, uploader = self._match_valid_url(url).group('id', 'uploader')
         webpage = self._download_webpage(url, title)
         tralbum = self._extract_data_attr(webpage, title)
         thumbnail = self._og_search_thumbnail(webpage)
@@ -183,10 +181,9 @@ def _real_extract(self, url):
                             'format_note': f.get('description'),
                             'filesize': parse_filesize(f.get('size_mb')),
                             'vcodec': 'none',
+                            'acodec': format_id.split('-')[0],
                         })
 
-        self._sort_formats(formats)
-
         title = '%s - %s' % (artist, track) if artist else track
 
         if not duration:
@@ -198,6 +195,8 @@ def _real_extract(self, url):
             'title': title,
             'thumbnail': thumbnail,
             'uploader': artist,
+            'uploader_id': uploader,
+            'uploader_url': f'https://{uploader}.bandcamp.com',
             'timestamp': timestamp,
             'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
             'duration': duration,
@@ -210,7 +209,7 @@ def _real_extract(self, url):
         }
 
 
-class BandcampAlbumIE(BandcampIE):
+class BandcampAlbumIE(BandcampIE):  # XXX: Do not subclass from concrete IE
     IE_NAME = 'Bandcamp:album'
     _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)'
 
@@ -313,7 +312,7 @@ def _real_extract(self, url):
         }
 
 
-class BandcampWeeklyIE(BandcampIE):
+class BandcampWeeklyIE(BandcampIE):  # XXX: Do not subclass from concrete IE
     IE_NAME = 'Bandcamp:weekly'
     _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
     _TESTS = [{
@@ -362,7 +361,6 @@ def _real_extract(self, url):
                 'ext': ext,
                 'vcodec': 'none',
             })
-        self._sort_formats(formats)
 
         title = show.get('audio_title') or 'Bandcamp Weekly'
         subtitle = show.get('subtitle')
@@ -438,7 +436,7 @@ def _real_extract(self, url):
         uploader = self._match_id(url)
         webpage = self._download_webpage(url, uploader)
 
-        discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\']([^"\']+)', webpage)
+        discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
                             or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
 
         return self.playlist_from_matches(