hoelee/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-08-11 11:11:46 +00:00
Code Issues Actions 15 Packages Projects Releases Wiki Activity

Update to ytdl-commit-a08f2b7 (#10012)

Browse Source 
[ie] Rework JWPlayer extraction
- f66372403f
[ie/gbnews] Add extractor
- 70f230f9cf
[ie/caffeinetv] Add extractor
- 40bd5c1815
[ie/youporn] Improve extraction
- 0b2ce3685e
[ie/youporn] Add playlist extractors
- 668332b973

Closes #9188, Closes #9523
Authored by: Grub4K, bashonly
This commit is contained in:
Simon Sawicki
2024-05-26 23:09:53 +02:00
committed by GitHub
parent e897bd8292
commit a4da9db87b
6 changed files with 588 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
yt_dlp/extractor/common.py
View File

@@ -3384,23 +3384,16 @@ class InfoExtractor:
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 @@ class InfoExtractor:
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,