[ie/bandcamp] Extract tags (#13480)

Authored by: WouterGordts

yt_dlp/extractor/bandcamp.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     KNOWN_EXTENSIONS,
     ExtractorError,
+    clean_html,
     extract_attributes,
     float_or_none,
     int_or_none,
@@ -19,7 +20,7 @@ from ..utils import (
     url_or_none,
     urljoin,
 )
-from ..utils.traversal import find_element, traverse_obj
+from ..utils.traversal import find_element, find_elements, traverse_obj
 
 
 class BandcampIE(InfoExtractor):
@@ -70,6 +71,9 @@ class BandcampIE(InfoExtractor):
             'album': 'FTL: Advanced Edition Soundtrack',
             'uploader_url': 'https://benprunty.bandcamp.com',
             'uploader_id': 'benprunty',
+            'tags': ['soundtrack', 'chiptunes', 'cinematic', 'electronic', 'video game music', 'California'],
+            'artists': ['Ben Prunty'],
+            'album_artists': ['Ben Prunty'],
         },
     }, {
         # no free download, mp3 128
@@ -94,6 +98,9 @@ class BandcampIE(InfoExtractor):
             'album': 'Call of the Mastodon',
             'uploader_url': 'https://relapsealumni.bandcamp.com',
             'uploader_id': 'relapsealumni',
+            'tags': ['Philadelphia'],
+            'artists': ['Mastodon'],
+            'album_artists': ['Mastodon'],
         },
     }, {
         # track from compilation album (artist/album_artist difference)
@@ -118,6 +125,9 @@ class BandcampIE(InfoExtractor):
             'album': 'DSK F/W 2016-2017 Free Compilation',
             'uploader_url': 'https://diskotopia.bandcamp.com',
             'uploader_id': 'diskotopia',
+            'tags': ['Japan'],
+            'artists': ['submerse'],
+            'album_artists': ['Diskotopia'],
         },
     }]
 
@@ -252,6 +262,7 @@ class BandcampIE(InfoExtractor):
             'album': embed.get('album_title'),
             'album_artist': album_artist,
             'formats': formats,
+            'tags': traverse_obj(webpage, ({find_elements(cls='tag')}, ..., {clean_html})),
         }
 
 

yt_dlp/extractor/mlb.py

@@ -457,12 +457,9 @@ mutation initPlaybackSession(
                 self.report_warning(f'No formats available for {format_id} broadcast; skipping')
             return [], {}
 
-        cdn_headers = {'x-cdn-token': token}
         fmts, subs = self._extract_m3u8_formats_and_subtitles(
-            m3u8_url.replace(f'/{token}/', '/'), video_id, 'mp4',
+            m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
-            m3u8_id=format_id, fatal=False, headers=cdn_headers)
         for fmt in fmts:
-            fmt['http_headers'] = cdn_headers
             fmt.setdefault('format_note', join_nonempty(feed, medium, delim=' '))
             fmt.setdefault('language', language)
             if fmt.get('vcodec') == 'none' and fmt['language'] == 'en':

yt_dlp/extractor/tenplay.py

@@ -7,11 +7,11 @@ from ..utils import int_or_none, traverse_obj, url_or_none, urljoin
 
 class TenPlayIE(InfoExtractor):
     IE_NAME = '10play'
-    _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/?#]+/)+(?P<id>tpv\d{6}[a-z]{5})'
+    _VALID_URL = r'https?://(?:www\.)?10(?:play)?\.com\.au/(?:[^/?#]+/)+(?P<id>tpv\d{6}[a-z]{5})'
     _NETRC_MACHINE = '10play'
     _TESTS = [{
         # Geo-restricted to Australia
-        'url': 'https://10play.com.au/australian-survivor/web-extras/season-10-brains-v-brawn-ii/myless-journey/tpv250414jdmtf',
+        'url': 'https://10.com.au/australian-survivor/web-extras/season-10-brains-v-brawn-ii/myless-journey/tpv250414jdmtf',
         'info_dict': {
             'id': '7440980000013868',
             'ext': 'mp4',
@@ -32,7 +32,7 @@ class TenPlayIE(InfoExtractor):
         'params': {'skip_download': 'm3u8'},
     }, {
         # Geo-restricted to Australia
-        'url': 'https://10play.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp',
+        'url': 'https://10.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp',
         'info_dict': {
             'id': '9000000000091177',
             'ext': 'mp4',
@@ -55,7 +55,7 @@ class TenPlayIE(InfoExtractor):
         'params': {'skip_download': 'm3u8'},
     }, {
         # Geo-restricted to Australia; upgrading the m3u8 quality fails and we need the fallback
-        'url': 'https://10play.com.au/tiny-chef-show/episodes/season-1/episode-2/tpv240228pofvt',
+        'url': 'https://10.com.au/tiny-chef-show/episodes/season-1/episode-2/tpv240228pofvt',
         'info_dict': {
             'id': '9000000000084116',
             'ext': 'mp4',
@@ -77,6 +77,7 @@ class TenPlayIE(InfoExtractor):
         },
         'params': {'skip_download': 'm3u8'},
         'expected_warnings': ['Failed to download m3u8 information: HTTP Error 502'],
+        'skip': 'video unavailable',
     }, {
         'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
         'only_matching': True,
@@ -96,7 +97,7 @@ class TenPlayIE(InfoExtractor):
     def _real_extract(self, url):
         content_id = self._match_id(url)
         data = self._download_json(
-            'https://10play.com.au/api/v1/videos/' + content_id, content_id)
+            'https://10.com.au/api/v1/videos/' + content_id, content_id)
 
         video_data = self._download_json(
             f'https://vod.ten.com.au/api/videos/bcquery?command=find_videos_by_id&video_id={data["altId"]}',
@@ -137,21 +138,24 @@ class TenPlayIE(InfoExtractor):
 
 class TenPlaySeasonIE(InfoExtractor):
     IE_NAME = '10play:season'
-    _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?P<show>[^/?#]+)/episodes/(?P<season>[^/?#]+)/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?10(?:play)?\.com\.au/(?P<show>[^/?#]+)/episodes/(?P<season>[^/?#]+)/?(?:$|[?#])'
     _TESTS = [{
-        'url': 'https://10play.com.au/masterchef/episodes/season-15',
+        'url': 'https://10.com.au/masterchef/episodes/season-15',
         'info_dict': {
             'title': 'Season 15',
             'id': 'MTQ2NjMxOQ==',
         },
         'playlist_mincount': 50,
     }, {
-        'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2024',
+        'url': 'https://10.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2024',
         'info_dict': {
             'title': 'Season 2024',
             'id': 'Mjc0OTIw',
         },
         'playlist_mincount': 159,
+    }, {
+        'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2024',
+        'only_matching': True,
     }]
 
     def _entries(self, load_more_url, display_id=None):
@@ -172,7 +176,7 @@ class TenPlaySeasonIE(InfoExtractor):
     def _real_extract(self, url):
         show, season = self._match_valid_url(url).group('show', 'season')
         season_info = self._download_json(
-            f'https://10play.com.au/api/shows/{show}/episodes/{season}', f'{show}/{season}')
+            f'https://10.com.au/api/shows/{show}/episodes/{season}', f'{show}/{season}')
 
         episodes_carousel = traverse_obj(season_info, (
             'content', 0, 'components', (