Merge branch 'yt-dlp:master' into biliSearchPageIE

pyproject.toml

@@ -72,7 +72,7 @@ dev = [
 ]
 static-analysis = [
     "autopep8~=2.0",
-    "ruff~=0.4.4",
+    "ruff~=0.5.0",
 ]
 test = [
     "pytest~=8.1",
@@ -211,6 +211,7 @@ ignore = [
     "TD002",   # missing-todo-author
     "TD003",   # missing-todo-link
     "PLE0604", # invalid-all-object (false positives)
+    "PLE0643", # potential-index-error (false positives)
     "PLW0603", # global-statement
     "PLW1510", # subprocess-run-without-check
     "PLW2901", # redefined-loop-name

test/test_download.py

@@ -20,7 +20,6 @@
     gettestcases,
     getwebpagetestcases,
     is_download_test,
-    report_warning,
     try_rm,
 )
 
@@ -178,8 +177,7 @@ def try_rm_tcs_files(tcs=None):
                         raise
 
                     if try_num == RETRIES:
-                        report_warning(f'{tname} failed due to network errors, skipping...')
+                        raise
-                        return
 
                     print(f'Retrying: {try_num} failed tries\n\n##########\n\n')
 

yt_dlp/extractor/_extractors.py

@@ -76,6 +76,7 @@
 )
 from .aeonco import AeonCoIE
 from .afreecatv import (
+    AfreecaTVCatchStoryIE,
     AfreecaTVIE,
     AfreecaTVLiveIE,
     AfreecaTVUserIE,

yt_dlp/extractor/afreecatv.py

@@ -72,7 +72,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
                             )\?.*?\bnTitleNo=|
                             vod\.afreecatv\.com/(PLAYER/STATION|player)/
                         )
-                        (?P<id>\d+)
+                        (?P<id>\d+)/?(?:$|[?#&])
                     '''
     _TESTS = [{
         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
@@ -189,7 +189,7 @@ def _real_extract(self, url):
             headers={'Referer': url}, data=urlencode_postdata({
                 'nTitleNo': video_id,
                 'nApiLevel': 10,
-            }))['data']
+            }), impersonate=True)['data']
 
         error_code = traverse_obj(data, ('code', {int}))
         if error_code == -6221:
@@ -253,6 +253,43 @@ def _real_extract(self, url):
         return self.playlist_result(entries, video_id, multi_video=True, **common_info)
 
 
+class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
+    IE_NAME = 'afreecatv:catchstory'
+    IE_DESC = 'afreecatv.com catch story'
+    _VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory'
+    _TESTS = [{
+        'url': 'https://vod.afreecatv.com/player/103247/catchstory',
+        'info_dict': {
+            'id': '103247',
+        },
+        'playlist_count': 2,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_json(
+            'https://api.m.afreecatv.com/catchstory/a/view', video_id, headers={'Referer': url},
+            query={'aStoryListIdx': '', 'nStoryIdx': video_id}, impersonate=True)
+
+        return self.playlist_result(self._entries(data), video_id)
+
+    @staticmethod
+    def _entries(data):
+        # 'files' is always a list with 1 element
+        yield from traverse_obj(data, (
+            'data', lambda _, v: v['story_type'] == 'catch',
+            'catch_list', lambda _, v: v['files'][0]['file'], {
+                'id': ('files', 0, 'file_info_key', {str}),
+                'url': ('files', 0, 'file', {url_or_none}),
+                'duration': ('files', 0, 'duration', {functools.partial(int_or_none, scale=1000)}),
+                'title': ('title', {str}),
+                'uploader': ('writer_nick', {str}),
+                'uploader_id': ('writer_id', {str}),
+                'thumbnail': ('thumb', {url_or_none}),
+                'timestamp': ('write_timestamp', {int_or_none}),
+            }))
+
+
 class AfreecaTVLiveIE(AfreecaTVBaseIE):
     IE_NAME = 'afreecatv:live'
     IE_DESC = 'afreecatv.com livestreams'

yt_dlp/extractor/atresplayer.py

@@ -33,14 +33,6 @@ class AtresPlayerIE(InfoExtractor):
     ]
     _API_BASE = 'https://api.atresplayer.com/'
 
-    def _handle_error(self, e, code):
-        if isinstance(e.cause, HTTPError) and e.cause.status == code:
-            error = self._parse_json(e.cause.response.read(), None)
-            if error.get('error') == 'required_registered':
-                self.raise_login_required()
-            raise ExtractorError(error['error_description'], expected=True)
-        raise
-
     def _perform_login(self, username, password):
         self._request_webpage(
             self._API_BASE + 'login', None, 'Downloading login page')
@@ -55,7 +47,9 @@ def _perform_login(self, username, password):
                     'password': password,
                 }))['targetUrl']
         except ExtractorError as e:
-            self._handle_error(e, 400)
+            if isinstance(e.cause, HTTPError) and e.cause.status == 400:
+                raise ExtractorError('Invalid username and/or password', expected=True)
+            raise
 
         self._request_webpage(target_url, None, 'Following Target URL')
 
@@ -66,7 +60,12 @@ def _real_extract(self, url):
             episode = self._download_json(
                 self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
         except ExtractorError as e:
-            self._handle_error(e, 403)
+            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
+                error = self._parse_json(e.cause.response.read(), None)
+                if error.get('error') == 'required_registered':
+                    self.raise_login_required()
+                raise ExtractorError(error['error_description'], expected=True)
+            raise
 
         title = episode['titulo']
 

yt_dlp/extractor/bitchute.py

@@ -24,7 +24,7 @@
 
 
 class BitChuteIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
     _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
     _TESTS = [{
         'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
@@ -91,6 +91,9 @@ class BitChuteIE(InfoExtractor):
     }, {
         'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
         'only_matching': True,
+    }, {
+        'url': 'https://old.bitchute.com/video/UGlrF9o9b-Q/',
+        'only_matching': True,
     }]
     _GEO_BYPASS = False
 
@@ -132,7 +135,7 @@ def _make_url(html):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
-            f'https://www.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
+            f'https://old.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
 
         self._raise_if_restricted(webpage)
         publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
@@ -171,13 +174,13 @@ def _real_extract(self, url):
 
 
 class BitChuteChannelIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://www.bitchute.com/channel/bitchute/',
         'info_dict': {
             'id': 'bitchute',
             'title': 'BitChute',
-            'description': 'md5:5329fb3866125afa9446835594a9b138',
+            'description': 'md5:2134c37d64fc3a4846787c402956adac',
         },
         'playlist': [
             {
@@ -210,6 +213,9 @@ class BitChuteChannelIE(InfoExtractor):
             'title': 'Bruce MacDonald and "The Light of Darkness"',
             'description': 'md5:747724ef404eebdfc04277714f81863e',
         },
+    }, {
+        'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
+        'only_matching': True,
     }]
 
     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
@@ -230,7 +236,7 @@ class BitChuteChannelIE(InfoExtractor):
 
     @staticmethod
     def _make_url(playlist_id, playlist_type):
-        return f'https://www.bitchute.com/{playlist_type}/{playlist_id}/'
+        return f'https://old.bitchute.com/{playlist_type}/{playlist_id}/'
 
     def _fetch_page(self, playlist_id, playlist_type, page_num):
         playlist_url = self._make_url(playlist_id, playlist_type)

yt_dlp/extractor/cbc.py

@@ -455,10 +455,8 @@ def _get_claims_token_expiry(self):
 
     def claims_token_expired(self):
         exp = self._get_claims_token_expiry()
-        if exp - time.time() < 10:
+        # It will expire in less than 10 seconds, or has already expired
-            # It will expire in less than 10 seconds, or has already expired
+        return exp - time.time() < 10
-            return True
-        return False
 
     def claims_token_valid(self):
         return self._claims_token is not None and not self.claims_token_expired()

yt_dlp/extractor/digitalconcerthall.py

@@ -1,16 +1,16 @@
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
-    parse_resolution,
-    traverse_obj,
     try_get,
+    url_or_none,
     urlencode_postdata,
 )
+from ..utils.traversal import traverse_obj
 
 
 class DigitalConcertHallIE(InfoExtractor):
     IE_DESC = 'DigitalConcertHall extractor'
-    _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert)/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?'
     _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
     _ACCESS_TOKEN = None
     _NETRC_MACHINE = 'digitalconcerthall'
@@ -26,7 +26,8 @@ class DigitalConcertHallIE(InfoExtractor):
             'upload_date': '20210624',
             'timestamp': 1624548600,
             'duration': 2798,
-            'album_artist': 'Members of the Berliner Philharmoniker / Simon Rössler',
+            'album_artists': ['Members of the Berliner Philharmoniker', 'Simon Rössler'],
+            'composers': ['Kurt Weill'],
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -34,8 +35,9 @@ class DigitalConcertHallIE(InfoExtractor):
         'url': 'https://www.digitalconcerthall.com/en/concert/53785',
         'info_dict': {
             'id': '53785',
-            'album_artist': 'Berliner Philharmoniker / Kirill Petrenko',
+            'album_artists': ['Berliner Philharmoniker', 'Kirill Petrenko'],
             'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
+            'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
         },
         'params': {'skip_download': 'm3u8'},
         'playlist_count': 3,
@@ -49,9 +51,20 @@ class DigitalConcertHallIE(InfoExtractor):
             'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
             'upload_date': '20220714',
             'timestamp': 1657785600,
-            'album_artist': 'Frank Peter Zimmermann / Benedikt von Bernstorff / Jakob von Bernstorff',
+            'album_artists': ['Frank Peter Zimmermann', 'Benedikt von Bernstorff', 'Jakob von Bernstorff'],
         },
         'params': {'skip_download': 'm3u8'},
+    }, {
+        'note': 'Concert with several works and an interview',
+        'url': 'https://www.digitalconcerthall.com/en/work/53785-1',
+        'info_dict': {
+            'id': '53785',
+            'album_artists': ['Berliner Philharmoniker', 'Kirill Petrenko'],
+            'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
+            'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'playlist_count': 1,
     }]
 
     def _perform_login(self, username, password):
@@ -97,15 +110,14 @@ def _entries(self, items, language, type_, **kwargs):
                     'Accept-Language': language,
                 })
 
-            m3u8_url = traverse_obj(
+            formats = []
-                stream_info, ('channel', lambda k, _: k.startswith('vod_mixed'), 'stream', 0, 'url'), get_all=False)
+            for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
-            formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False)
+                formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False))
 
             yield {
                 'id': video_id,
                 'title': item.get('title'),
                 'composer': item.get('name_composer'),
-                'url': m3u8_url,
                 'formats': formats,
                 'duration': item.get('duration_total'),
                 'timestamp': traverse_obj(item, ('date', 'published')),
@@ -119,31 +131,32 @@ def _entries(self, items, language, type_, **kwargs):
             }
 
     def _real_extract(self, url):
-        language, type_, video_id = self._match_valid_url(url).group('language', 'type', 'id')
+        language, type_, video_id, part = self._match_valid_url(url).group('language', 'type', 'id', 'part')
         if not language:
             language = 'en'
 
-        thumbnail_url = self._html_search_regex(
+        api_type = 'concert' if type_ == 'work' else type_
-            r'(https?://images\.digitalconcerthall\.com/cms/thumbnails/.*\.jpg)',
-            self._download_webpage(url, video_id), 'thumbnail')
-        thumbnails = [{
-            'url': thumbnail_url,
-            **parse_resolution(thumbnail_url),
-        }]
-
         vid_info = self._download_json(
-            f'https://api.digitalconcerthall.com/v2/{type_}/{video_id}', video_id, headers={
+            f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={
                 'Accept': 'application/json',
                 'Accept-Language': language,
             })
-        album_artist = ' / '.join(traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) or '')
+        album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name'))
         videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
 
+        if type_ == 'work':
+            videos = [videos[int(part) - 1]]
+
+        thumbnail = traverse_obj(vid_info, (
+            'image', ..., {self._proto_relative_url}, {url_or_none},
+            {lambda x: x.format(width=0, height=0)}, any))  # NB: 0x0 is the original size
+
         return {
             '_type': 'playlist',
             'id': video_id,
             'title': vid_info.get('title'),
-            'entries': self._entries(videos, language, thumbnails=thumbnails, album_artist=album_artist, type_=type_),
+            'entries': self._entries(
-            'thumbnails': thumbnails,
+                videos, language, type_, thumbnail=thumbnail, album_artists=album_artists),
-            'album_artist': album_artist,
+            'thumbnail': thumbnail,
+            'album_artists': album_artists,
         }

yt_dlp/extractor/jiocinema.py

@@ -364,20 +364,25 @@ class JioCinemaSeriesIE(JioCinemaBaseIE):
             'title': 'naagin',
         },
         'playlist_mincount': 120,
+    }, {
+        'url': 'https://www.jiocinema.com/tv-shows/mtv-splitsvilla-x5/3499820',
+        'info_dict': {
+            'id': '3499820',
+            'title': 'mtv-splitsvilla-x5',
+        },
+        'playlist_mincount': 310,
     }]
 
     def _entries(self, series_id):
-        seasons = self._download_json(
+        seasons = traverse_obj(self._download_json(
-            f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/season-by-show', series_id,
+            f'{self._METADATA_API_BASE}/voot/v1/voot-web/view/show/{series_id}', series_id,
-            'Downloading series metadata JSON', query={
+            'Downloading series metadata JSON', query={'responseType': 'common'}), (
-                'sort': 'season:asc',
+            'trays', lambda _, v: v['trayId'] == 'season-by-show-multifilter',
-                'id': series_id,
+            'trayTabs', lambda _, v: v['id']))
-                'responseType': 'common',
-            })
 
-        for season_num, season in enumerate(traverse_obj(seasons, ('result', lambda _, v: v['id'])), 1):
+        for season_num, season in enumerate(seasons, start=1):
             season_id = season['id']
-            label = season.get('season') or season_num
+            label = season.get('label') or season_num
             for page_num in itertools.count(1):
                 episodes = traverse_obj(self._download_json(
                     f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/series-wise-episode',

yt_dlp/extractor/mlb.py

@@ -9,9 +9,10 @@
     join_nonempty,
     parse_duration,
     parse_iso8601,
-    traverse_obj,
     try_get,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class MLBBaseIE(InfoExtractor):
@@ -326,15 +327,20 @@ def _real_extract(self, url):
             video_id)['data']['Airings']
 
         formats, subtitles = [], {}
-        for airing in airings:
+        for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']):
-            m3u8_url = self._download_json(
+            format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing)
+            m3u8_url = traverse_obj(self._download_json(
                 airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id,
-                headers={
+                note=f'Downloading {format_id} stream info JSON',
+                errnote=f'Failed to download {format_id} stream info, skipping',
+                fatal=False, headers={
                     'Authorization': self._access_token,
                     'Accept': 'application/vnd.media-service+json; version=2',
-                })['stream']['complete']
+                }), ('stream', 'complete', {url_or_none}))
+            if not m3u8_url:
+                continue
             f, s = self._extract_m3u8_formats_and_subtitles(
-                m3u8_url, video_id, 'mp4', m3u8_id=join_nonempty(airing.get('feedType'), airing.get('feedLanguage')))
+                m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
             formats.extend(f)
             self._merge_subtitles(s, target=subtitles)
 

yt_dlp/extractor/youtube.py

@@ -468,7 +468,10 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko',
     ]
 
-    _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
+    _IGNORED_WARNINGS = {
+        'Unavailable videos will be hidden during playback',
+        'Unavailable videos are hidden',
+    }
 
     _YT_HANDLE_RE = r'@[\w.-]{3,30}'  # https://support.google.com/youtube/answer/11585688?hl=en
     _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'

yt_dlp/jsinterp.py

@@ -667,12 +667,12 @@ def eval_method():
                     self.interpret_expression(v, local_vars, allow_recursion)
                     for v in self._separate(arg_str)]
 
-                if obj == str:
+                if obj is str:
                     if member == 'fromCharCode':
                         assertion(argvals, 'takes one or more arguments')
                         return ''.join(map(chr, argvals))
                     raise self.Exception(f'Unsupported String method {member}', expr)
-                elif obj == float:
+                elif obj is float:
                     if member == 'pow':
                         assertion(len(argvals) == 2, 'takes two arguments')
                         return argvals[0] ** argvals[1]

yt_dlp/networking/_requests.py

@@ -230,9 +230,7 @@ class Urllib3LoggingFilter(logging.Filter):
 
     def filter(self, record):
         # Ignore HTTP request messages since HTTPConnection prints those
-        if record.msg == '%s://%s:%s "%s %s %s" %s %s':
+        return record.msg != '%s://%s:%s "%s %s %s" %s %s'
-            return False
-        return True
 
 
 class Urllib3LoggingHandler(logging.Handler):