[utils] write_xattr: Use os.setxattr if available (#8205)

Closes #8193
Authored by: bashonly, Grub4K

Co-authored-by: Simon Sawicki <contact@grub4k.xyz>

README.md

@@ -280,7 +280,7 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly
 
 * [**mutagen**](https://github.com/quodlibet/mutagen)\* - For `--embed-thumbnail` in certain formats. Licensed under [GPLv2+](https://github.com/quodlibet/mutagen/blob/master/COPYING)
 * [**AtomicParsley**](https://github.com/wez/atomicparsley) - For `--embed-thumbnail` in `mp4`/`m4a` files when `mutagen`/`ffmpeg` cannot. Licensed under [GPLv2+](https://github.com/wez/atomicparsley/blob/master/COPYING)
-* [**xattr**](https://github.com/xattr/xattr), [**pyxattr**](https://github.com/iustin/pyxattr) or [**setfattr**](http://savannah.nongnu.org/projects/attr) - For writing xattr metadata (`--xattr`) on **Linux**. Licensed under [MIT](https://github.com/xattr/xattr/blob/master/LICENSE.txt), [LGPL2.1](https://github.com/iustin/pyxattr/blob/master/COPYING) and [GPLv2+](http://git.savannah.nongnu.org/cgit/attr.git/tree/doc/COPYING) respectively
+* [**xattr**](https://github.com/xattr/xattr), [**pyxattr**](https://github.com/iustin/pyxattr) or [**setfattr**](http://savannah.nongnu.org/projects/attr) - For writing xattr metadata (`--xattr`) on **Mac** and **BSD**. Licensed under [MIT](https://github.com/xattr/xattr/blob/master/LICENSE.txt), [LGPL2.1](https://github.com/iustin/pyxattr/blob/master/COPYING) and [GPLv2+](http://git.savannah.nongnu.org/cgit/attr.git/tree/doc/COPYING) respectively
 
 ### Misc
 

yt_dlp/extractor/_extractors.py

@@ -1992,7 +1992,10 @@ from .tencent import (
     WeTvSeriesIE,
 )
 from .tennistv import TennisTVIE
-from .tenplay import TenPlayIE
+from .tenplay import (
+    TenPlayIE,
+    TenPlaySeasonIE,
+)
 from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .tfo import TFOIE

yt_dlp/extractor/arte.py

@@ -48,17 +48,7 @@ class ArteTVIE(ArteTVBaseIE):
     }, {
         'note': 'No alt_title',
         'url': 'https://www.arte.tv/fr/videos/110371-000-A/la-chaleur-supplice-des-arbres-de-rue/',
-        'info_dict': {
-            'id': '110371-000-A',
-            'ext': 'mp4',
-            'upload_date': '20220718',
-            'duration': 154,
-            'timestamp': 1658162460,
-            'description': 'md5:5890f36fe7dccfadb8b7c0891de54786',
-            'title': 'La chaleur, supplice des arbres de rue',
-            'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/CPE2sQDtD8GLQgt8DuYHLf/940x530',
-        },
-        'params': {'skip_download': 'm3u8'}
+        'only_matching': True,
     }, {
         'url': 'https://api.arte.tv/api/player/v2/config/de/100605-013-A',
         'only_matching': True,
@@ -67,19 +57,20 @@ class ArteTVIE(ArteTVBaseIE):
         'only_matching': True,
     }, {
         'url': 'https://www.arte.tv/de/videos/110203-006-A/zaz/',
+        'only_matching': True,
+    }, {
+        'note': 'age-restricted',
+        'url': 'https://www.arte.tv/de/videos/006785-000-A/the-element-of-crime/',
         'info_dict': {
-            'id': '110203-006-A',
-            'chapters': 'count:16',
-            'description': 'md5:cf592f1df52fe52007e3f8eac813c084',
-            'alt_title': 'Zaz',
-            'title': 'Baloise Session 2022',
-            'timestamp': 1668445200,
-            'duration': 4054,
-            'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/ubQjmVCGyRx3hmBuZEK9QZ/940x530',
-            'upload_date': '20221114',
+            'id': '006785-000-A',
+            'description': 'md5:c2f94fdfefc8a280e4dab68ab96ab0ba',
+            'title': 'The Element of Crime',
+            'timestamp': 1696111200,
+            'duration': 5849,
+            'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/q82dTTfyuCXupPsGxXsd7B/940x530',
+            'upload_date': '20230930',
             'ext': 'mp4',
-        },
-        'expected_warnings': ['geo restricted']
+        }
     }]
 
     _GEO_BYPASS = True
@@ -136,7 +127,9 @@ class ArteTVIE(ArteTVBaseIE):
         lang = mobj.group('lang') or mobj.group('lang_2')
         langauge_code = self._LANG_MAP.get(lang)
 
-        config = self._download_json(f'{self._API_BASE}/config/{lang}/{video_id}', video_id)
+        config = self._download_json(f'{self._API_BASE}/config/{lang}/{video_id}', video_id, headers={
+            'x-validated-age': '18'
+        })
 
         geoblocking = traverse_obj(config, ('data', 'attributes', 'restriction', 'geoblocking')) or {}
         if geoblocking.get('restrictedArea'):

yt_dlp/extractor/nhk.py

@@ -68,11 +68,12 @@ class NhkBaseIE(InfoExtractor):
 
     def _extract_episode_info(self, url, episode=None):
         fetch_episode = episode is None
-        lang, m_type, episode_id = NhkVodIE._match_valid_url(url).groups()
-        if len(episode_id) == 7:
+        lang, m_type, episode_id = NhkVodIE._match_valid_url(url).group('lang', 'type', 'id')
+        is_video = m_type == 'video'
+
+        if is_video:
             episode_id = episode_id[:4] + '-' + episode_id[4:]
 
-        is_video = m_type == 'video'
         if fetch_episode:
             episode = self._call_api(
                 episode_id, lang, is_video, True, episode_id[:4] == '9999')[0]
@@ -133,47 +134,46 @@ class NhkBaseIE(InfoExtractor):
 
 class NhkVodIE(NhkBaseIE):
     # the 7-character IDs can have alphabetic chars too: assume [a-z] rather than just [a-f], eg
-    _VALID_URL = r'%s%s(?P<id>[0-9a-z]{7}|[^/]+?-\d{8}-[0-9a-z]+)' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
+    _VALID_URL = [rf'{NhkBaseIE._BASE_URL_REGEX}/(?P<type>video)/(?P<id>[0-9a-z]+)',
+                  rf'{NhkBaseIE._BASE_URL_REGEX}/(?P<type>audio)/(?P<id>[^/?#]+?-\d{{8}}-[0-9a-z]+)']
     # Content available only for a limited period of time. Visit
     # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
     _TESTS = [{
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2061601/',
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2049126/',
         'info_dict': {
-            'id': 'yd8322ch',
+            'id': 'nw_vod_v_en_2049_126_20230413233000_01_1681398302',
             'ext': 'mp4',
-            'description': 'md5:109c8b05d67a62d0592f2b445d2cd898',
-            'title': 'GRAND SUMO Highlights - [Recap] May Tournament Day 1 (Opening Day)',
-            'upload_date': '20230514',
-            'timestamp': 1684083791,
-            'series': 'GRAND SUMO Highlights',
-            'episode': '[Recap] May Tournament Day 1 (Opening Day)',
-            'thumbnail': 'https://mz-edge.stream.co.jp/thumbs/aid/t1684084443/4028649.jpg?w=1920&h=1080',
+            'title': 'Japan Railway Journal - The Tohoku Shinkansen: Full Speed Ahead',
+            'description': 'md5:49f7c5b206e03868a2fdf0d0814b92f6',
+            'thumbnail': 'md5:51bcef4a21936e7fea1ff4e06353f463',
+            'episode': 'The Tohoku Shinkansen: Full Speed Ahead',
+            'series': 'Japan Railway Journal',
         },
     }, {
         # video clip
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
-        'md5': '7a90abcfe610ec22a6bfe15bd46b30ca',
+        'md5': '153c3016dfd252ba09726588149cf0e7',
         'info_dict': {
-            'id': 'a95j5iza',
+            'id': 'lpZXIwaDE6_Z-976CPsFdxyICyWUzlT5',
             'ext': 'mp4',
-            'title': "Dining with the Chef - Chef Saito's Family recipe: MENCHI-KATSU",
+            'title': 'Dining with the Chef - Chef Saito\'s Family recipe: MENCHI-KATSU',
             'description': 'md5:5aee4a9f9d81c26281862382103b0ea5',
-            'timestamp': 1565965194,
-            'upload_date': '20190816',
-            'thumbnail': 'https://mz-edge.stream.co.jp/thumbs/aid/t1567086278/3715195.jpg?w=1920&h=1080',
+            'thumbnail': 'md5:d6a4d9b6e9be90aaadda0bcce89631ed',
             'series': 'Dining with the Chef',
             'episode': 'Chef Saito\'s Family recipe: MENCHI-KATSU',
         },
     }, {
-        # audio clip
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/r_inventions-20201104-1/',
+        # radio
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/livinginjapan-20231001-1/',
         'info_dict': {
-            'id': 'r_inventions-20201104-1-en',
+            'id': 'livinginjapan-20231001-1-en',
             'ext': 'm4a',
-            'title': "Japan's Top Inventions - Miniature Video Cameras",
-            'description': 'md5:07ea722bdbbb4936fdd360b6a480c25b',
+            'title': 'Living in Japan - Tips for Travelers to Japan / Ramen Vending Machines',
+            'series': 'Living in Japan',
+            'description': 'md5:850611969932874b4a3309e0cae06c2f',
+            'thumbnail': 'md5:960622fb6e06054a4a1a0c97ea752545',
+            'episode': 'Tips for Travelers to Japan / Ramen Vending Machines'
         },
-        'skip': '404 Not Found',
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
         'only_matching': True,
@@ -199,6 +199,19 @@ class NhkVodIE(NhkBaseIE):
             'timestamp': 1623722008,
         },
         'skip': '404 Not Found',
+    }, {
+        # japanese-language, longer id than english
+        'url': 'https://www3.nhk.or.jp/nhkworld/ja/ondemand/video/0020271111/',
+        'info_dict': {
+            'id': 'nw_ja_v_jvod_ohayou_20231008',
+            'ext': 'mp4',
+            'title': 'おはよう日本（7時台） - 10月8日放送',
+            'series': 'おはよう日本（7時台）',
+            'episode': '10月8日放送',
+            'thumbnail': 'md5:d733b1c8e965ab68fb02b2d347d0e9b4',
+            'description': 'md5:9c1d6cbeadb827b955b20e99ab920ff0',
+        },
+        'skip': 'expires 2023-10-15',
     }]
 
     def _real_extract(self, url):
@@ -206,7 +219,7 @@ class NhkVodIE(NhkBaseIE):
 
 
 class NhkVodProgramIE(NhkBaseIE):
-    _VALID_URL = r'%s/program%s(?P<id>[0-9a-z]+)(?:.+?\btype=(?P<episode_type>clip|(?:radio|tv)Episode))?' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
+    _VALID_URL = rf'{NhkBaseIE._BASE_URL_REGEX}/program{NhkBaseIE._TYPE_REGEX}(?P<id>\w+)(?:.+?\btype=(?P<episode_type>clip|(?:radio|tv)Episode))?'
     _TESTS = [{
         # video program episodes
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/sumo',
@@ -240,8 +253,7 @@ class NhkVodProgramIE(NhkBaseIE):
     }]
 
     def _real_extract(self, url):
-        lang, m_type, program_id, episode_type = self._match_valid_url(url).groups()
-
+        lang, m_type, program_id, episode_type = self._match_valid_url(url).group('lang', 'type', 'id', 'episode_type')
         episodes = self._call_api(
             program_id, lang, m_type == 'video', False, episode_type == 'clip')
 

yt_dlp/extractor/tenplay.py

@@ -1,9 +1,11 @@
-from datetime import datetime
 import base64
+import functools
+import itertools
+from datetime import datetime
 
 from .common import InfoExtractor
 from ..networking import HEADRequest
-from ..utils import int_or_none, urlencode_postdata
+from ..utils import int_or_none, traverse_obj, urlencode_postdata, urljoin
 
 
 class TenPlayIE(InfoExtractor):
@@ -113,3 +115,55 @@ class TenPlayIE(InfoExtractor):
             'uploader': 'Channel 10',
             'uploader_id': '2199827728001',
         }
+
+
+class TenPlaySeasonIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?P<show>[^/?#]+)/episodes/(?P<season>[^/?#]+)/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://10play.com.au/masterchef/episodes/season-14',
+        'info_dict': {
+            'title': 'Season 14',
+            'id': 'MjMyOTIy',
+        },
+        'playlist_mincount': 64,
+    }, {
+        'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2022',
+        'info_dict': {
+            'title': 'Season 2022',
+            'id': 'Mjc0OTIw',
+        },
+        'playlist_mincount': 256,
+    }]
+
+    def _entries(self, load_more_url, display_id=None):
+        skip_ids = []
+        for page in itertools.count(1):
+            episodes_carousel = self._download_json(
+                load_more_url, display_id, query={'skipIds[]': skip_ids},
+                note=f'Fetching episodes page {page}')
+
+            episodes_chunk = episodes_carousel['items']
+            skip_ids.extend(ep['id'] for ep in episodes_chunk)
+
+            for ep in episodes_chunk:
+                yield ep['cardLink']
+            if not episodes_carousel['hasMore']:
+                break
+
+    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}')
+
+        episodes_carousel = traverse_obj(season_info, (
+            'content', 0, 'components', (
+                lambda _, v: v['title'].lower() == 'episodes',
+                (..., {dict}),
+            )), get_all=False) or {}
+
+        playlist_id = episodes_carousel['tpId']
+
+        return self.playlist_from_matches(
+            self._entries(urljoin(url, episodes_carousel['loadMoreUrl']), playlist_id),
+            playlist_id, traverse_obj(season_info, ('content', 0, 'title', {str})),
+            getter=functools.partial(urljoin, url))

yt_dlp/extractor/youku.py

@@ -20,7 +20,7 @@ class YoukuIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         (?:
             https?://(
-                (?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+                (?:v|play(?:er)?)\.(?:youku|tudou)\.com/(?:v_show/id_|player\.php/sid/)|
                 video\.tudou\.com/v/)|
             youku:)
         (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
@@ -87,6 +87,19 @@ class YoukuIE(InfoExtractor):
             'uploader_url': 'https://www.youku.com/profile/index/?uid=UNjU2MzY1MzM1Ng==',
             'tags': list,
         },
+    }, {
+        'url': 'https://play.tudou.com/v_show/id_XNjAxNjI2OTU3Ng==.html?',
+        'info_dict': {
+            'id': 'XNjAxNjI2OTU3Ng',
+            'ext': 'mp4',
+            'title': '阿斯塔意识到哈里杀了人，自己被骗了',
+            'thumbnail': 'https://m.ykimg.com/0541010164F732752794D4D7B70331D1',
+            'uploader_id': '88758207',
+            'tags': [],
+            'uploader_url': 'https://www.youku.com/profile/index/?uid=UMzU1MDMyODI4',
+            'uploader': '英美剧场',
+            'duration': 72.91,
+        },
     }]
 
     @staticmethod

yt_dlp/utils/_utils.py

@@ -4441,10 +4441,12 @@ def write_xattr(path, key, value):
             raise XAttrMetadataError(e.errno, e.strerror)
         return
 
-    # UNIX Method 1. Use xattrs/pyxattrs modules
+    # UNIX Method 1. Use os.setxattr/xattrs/pyxattrs modules
 
     setxattr = None
-    if getattr(xattr, '_yt_dlp__identifier', None) == 'pyxattr':
+    if callable(getattr(os, 'setxattr', None)):
+        setxattr = os.setxattr
+    elif getattr(xattr, '_yt_dlp__identifier', None) == 'pyxattr':
         # Unicode arguments are not supported in pyxattr until version 0.5.0
         # See https://github.com/ytdl-org/youtube-dl/issues/5498
         if version_tuple(xattr.__version__) >= (0, 5, 0):