yt_dlp: 96a134dea6397a5f2131947c427aac52c8b4e677

lib/yt_dlp/extractor/common.py

@@ -3384,23 +3384,16 @@ def manifest_url(manifest):
         return formats
 
     def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
-        mobj = re.search(
-            r'''(?s)jwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?!</script>).*?\.\s*setup\s*\(\s*(?P<options>(?:\([^)]*\)|[^)])+)\s*\)''',
-            webpage)
-        if mobj:
-            try:
-                jwplayer_data = self._parse_json(mobj.group('options'),
-                                                 video_id=video_id,
-                                                 transform_source=transform_source)
-            except ExtractorError:
-                pass
-            else:
-                if isinstance(jwplayer_data, dict):
-                    return jwplayer_data
+        return self._search_json(
+            r'''(?<!-)\bjwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?:(?!</script>).)*?\.\s*(?:setup\s*\(|(?P<load>load)\s*\(\s*\[)''',
+            webpage, 'JWPlayer data', video_id,
+            # must be a {...} or sequence, ending
+            contains_pattern=r'\{(?s:.*)}(?(load)(?:\s*,\s*\{(?s:.*)})*)', end_pattern=r'(?(load)\]|\))',
+            transform_source=transform_source, default=None)
 
-    def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
+    def _extract_jwplayer_data(self, webpage, video_id, *args, transform_source=js_to_json, **kwargs):
         jwplayer_data = self._find_jwplayer_data(
-            webpage, video_id, transform_source=js_to_json)
+            webpage, video_id, transform_source=transform_source)
         return self._parse_jwplayer_data(
             jwplayer_data, video_id, *args, **kwargs)
 
@@ -3432,22 +3425,14 @@ def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
                 mpd_id=mpd_id, rtmp_params=rtmp_params, base_url=base_url)
 
             subtitles = {}
-            tracks = video_data.get('tracks')
-            if tracks and isinstance(tracks, list):
-                for track in tracks:
-                    if not isinstance(track, dict):
-                        continue
-                    track_kind = track.get('kind')
-                    if not track_kind or not isinstance(track_kind, str):
-                        continue
-                    if track_kind.lower() not in ('captions', 'subtitles'):
-                        continue
-                    track_url = urljoin(base_url, track.get('file'))
-                    if not track_url:
-                        continue
-                    subtitles.setdefault(track.get('label') or 'en', []).append({
-                        'url': self._proto_relative_url(track_url)
-                    })
+            for track in traverse_obj(video_data, (
+                    'tracks', lambda _, v: v['kind'].lower() in ('captions', 'subtitles'))):
+                track_url = urljoin(base_url, track.get('file'))
+                if not track_url:
+                    continue
+                subtitles.setdefault(track.get('label') or 'en', []).append({
+                    'url': self._proto_relative_url(track_url)
+                })
 
             entry = {
                 'id': this_video_id,

lib/yt_dlp/options.py

@@ -478,7 +478,7 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs):
             }, 'aliases': {
                 'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx'],
                 'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx'],
-                '2021': ['2022', 'no-certifi', 'filename-sanitization', 'no-youtube-prefer-utc-upload-date'],
+                '2021': ['2022', 'no-certifi', 'filename-sanitization'],
                 '2022': ['2023', 'no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
                 '2023': [],
             }

lib/yt_dlp/utils/_utils.py

@@ -1134,7 +1134,7 @@ def is_path_like(f):
     return isinstance(f, (str, bytes, os.PathLike))
 
 
-def extract_timezone(date_str):
+def extract_timezone(date_str, default=None):
     m = re.search(
         r'''(?x)
             ^.{8,}?                                              # >=8 char non-TZ prefix, if present
@@ -1146,21 +1146,25 @@ def extract_timezone(date_str):
                 (?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})       # hh[:]mm
             $)
         ''', date_str)
+    timezone = None
+
     if not m:
         m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
         timezone = TIMEZONE_NAMES.get(m and m.group('tz').strip())
         if timezone is not None:
             date_str = date_str[:-len(m.group('tz'))]
-        timezone = dt.timedelta(hours=timezone or 0)
+            timezone = dt.timedelta(hours=timezone)
     else:
         date_str = date_str[:-len(m.group('tz'))]
-        if not m.group('sign'):
-            timezone = dt.timedelta()
-        else:
+        if m.group('sign'):
             sign = 1 if m.group('sign') == '+' else -1
             timezone = dt.timedelta(
                 hours=sign * int(m.group('hours')),
                 minutes=sign * int(m.group('minutes')))
+
+    if timezone is None and default is not NO_DEFAULT:
+        timezone = default or dt.timedelta()
+
     return timezone, date_str
 
 
@@ -1172,10 +1176,9 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
 
     date_str = re.sub(r'\.[0-9]+', '', date_str)
 
-    if timezone is None:
-        timezone, date_str = extract_timezone(date_str)
+    timezone, date_str = extract_timezone(date_str, timezone)
 
-    with contextlib.suppress(ValueError):
+    with contextlib.suppress(ValueError, TypeError):
         date_format = f'%Y-%m-%d{delimiter}%H:%M:%S'
         dt_ = dt.datetime.strptime(date_str, date_format) - timezone
         return calendar.timegm(dt_.timetuple())