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-195f22f6

Browse Source 
[generic] Improve KVS (etc) extraction
195f22f679

Closes #3716
Authored by: Grub4k, pukkandan
This commit is contained in:
Simon Sawicki
2023-01-02 14:45:36 +01:00
committed by GitHub
parent 8300774c4a
commit 32a84bcf4e
5 changed files with 529 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
yt_dlp/extractor/common.py
View File

@@ -1396,10 +1396,16 @@ class InfoExtractor:
# And then there are the jokers who advertise that they use RTA, but actually don't.
AGE_LIMIT_MARKERS = [
r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
r'>[^<]*you acknowledge you are at least (\d+) years old',
r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
]
if any(re.search(marker, html) for marker in AGE_LIMIT_MARKERS):
return 18
return 0
age_limit = 0
for marker in AGE_LIMIT_MARKERS:
mobj = re.search(marker, html)
if mobj:
age_limit = max(age_limit, int(traverse_obj(mobj, 1, default=18)))
return age_limit
def _media_rating_search(self, html):
# See http://www.tjg-designs.com/WP/metadata-code-examples-adding-metadata-to-your-web-pages/
@@ -3216,7 +3222,7 @@ class InfoExtractor:
def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
mobj = re.search(
r'(?s)jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)(?!</script>).*?\.setup\s*\((?P<options>[^)]+)\)',
r'''(?s)jwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?!</script>).*?\.\s*setup\s*\(\s*(?P<options>(?:\([^)]*\)|[^)])+)\s*\)''',
webpage)
if mobj:
try:
@@ -3237,19 +3243,20 @@ class InfoExtractor:
def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
# JWPlayer backward compatibility: flattened playlists
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
if 'playlist' not in jwplayer_data:
jwplayer_data = {'playlist': [jwplayer_data]}
entries = []
if not isinstance(jwplayer_data, dict):
return entries
# JWPlayer backward compatibility: single playlist item
playlist_items = jwplayer_data.get('playlist')
# JWPlayer backward compatibility: single playlist item/flattened playlists
# https://github.com/jwplayer/jwplayer/blob/v7.7.0/src/js/playlist/playlist.js#L10
if not isinstance(jwplayer_data['playlist'], list):
jwplayer_data['playlist'] = [jwplayer_data['playlist']]
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
if not isinstance(playlist_items, list):
playlist_items = (playlist_items or jwplayer_data, )
for video_data in jwplayer_data['playlist']:
for video_data in playlist_items:
if not isinstance(video_data, dict):
continue
# JWPlayer backward compatibility: flattened sources
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
if 'sources' not in video_data:
@@ -3287,6 +3294,13 @@ class InfoExtractor:
'timestamp': int_or_none(video_data.get('pubdate')),
'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
'subtitles': subtitles,
'alt_title': clean_html(video_data.get('subtitle')), # attributes used e.g. by Tele5 ...
'genre': clean_html(video_data.get('genre')),
'channel': clean_html(dict_get(video_data, ('category', 'channel'))),
'season_number': int_or_none(video_data.get('season')),
'episode_number': int_or_none(video_data.get('episode')),
'release_year': int_or_none(video_data.get('releasedate')),
'age_limit': int_or_none(video_data.get('age_restriction')),
}
# https://github.com/jwplayer/jwplayer/blob/master/src/js/utils/validator.js#L32
if len(formats) == 1 and re.search(r'^(?:http|//).*(?:youtube\.com|youtu\.be)/.+', formats[0]['url']):
@@ -3304,7 +3318,7 @@ class InfoExtractor:
def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
urls = []
urls = set()
formats = []
for source in jwplayer_sources_data:
if not isinstance(source, dict):
@@ -3313,14 +3327,14 @@ class InfoExtractor:
base_url, self._proto_relative_url(source.get('file')))
if not source_url or source_url in urls:
continue
urls.append(source_url)
urls.add(source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':
if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=m3u8_id, fatal=False))
elif source_type == 'dash' or ext == 'mpd':
elif source_type == 'dash' or ext == 'mpd' or 'format=mpd-time-csf' in source_url:
formats.extend(self._extract_mpd_formats(
source_url, video_id, mpd_id=mpd_id, fatal=False))
elif ext == 'smil':
@@ -3335,13 +3349,12 @@ class InfoExtractor:
'ext': ext,
})
else:
format_id = str_or_none(source.get('label'))
height = int_or_none(source.get('height'))
if height is None:
if height is None and format_id:
# Often no height is provided but there is a label in
# format like "1080p", "720p SD", or 1080.
height = int_or_none(self._search_regex(
r'^(\d{3,4})[pP]?(?:\b|$)', str(source.get('label') or ''),
'height', default=None))
height = parse_resolution(format_id).get('height')
a_format = {
'url': source_url,
'width': int_or_none(source.get('width')),
@@ -3349,6 +3362,7 @@ class InfoExtractor:
'tbr': int_or_none(source.get('bitrate'), scale=1000),
'filesize': int_or_none(source.get('filesize')),
'ext': ext,
'format_id': format_id
}
if source_url.startswith('rtmp'):
a_format['ext'] = 'flv'