pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-10-23 03:28:01 +09:00
Code Issues Projects Releases Wiki Activity

Update 2023 draft to current API version, etc

Browse Source
This commit is contained in:
dirkf 2024-10-08 23:51:02 +01:00 committed by GitHub
parent ab5617be9e
commit de91fe794d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 42 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

100
youtube_dl/extractor/sbs.py
View File

@ -13,6 +13,7 @@ from ..utils import (
merge_dicts, merge_dicts,
parse_duration, parse_duration,
parse_iso8601, parse_iso8601,
T,
traverse_obj, traverse_obj,
update_url_query, update_url_query,
url_or_none, url_or_none,
@ -35,7 +36,7 @@ class SBSIE(InfoExtractor):
<meta\s+property="og:video"\s+content=| <meta\s+property="og:video"\s+content=|
<iframe[^>]+?src= <iframe[^>]+?src=
) )
(["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1'''] ("|\')(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''']
_TESTS = [{ _TESTS = [{
# Exceptional unrestricted show for testing, thanks SBS, # Exceptional unrestricted show for testing, thanks SBS,
@ -94,17 +95,13 @@ class SBSIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
# change default entry_protocol kwarg for _extract_smil_formats()
# TODO: ..._and_subtitles()
def _extract_m3u8_formats(self, m3u8_url, video_id, *args, **kwargs): def _extract_m3u8_formats(self, m3u8_url, video_id, *args, **kwargs):
# ext, entry_protocol, preference, m3u8_id, note, errnote, fatal, # ext, entry_protocol, ...
# live, data, headers, query entry_protocol = kwargs.get('entry_protocol')
entry_protocol = args[1] if len(args) > 1 else kwargs.get('entry_protocol') if not entry_protocol and len(args) <= 1:
if not entry_protocol: kwargs['entry_protocol'] = 'm3u8_native'
entry_protocol = 'm3u8_native'
if len(args) > 1:
args = list(args)
args[1] = entry_protocol
else:
kwargs['entry_protocol'] = entry_protocol
kwargs = compat_kwargs(kwargs) kwargs = compat_kwargs(kwargs)
return super(SBSIE, self)._extract_m3u8_formats(m3u8_url, video_id, *args, **kwargs) return super(SBSIE, self)._extract_m3u8_formats(m3u8_url, video_id, *args, **kwargs)
@ -144,8 +141,8 @@ class SBSIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
# get media links directly though later metadata may contain contentUrl # get media links directly though later metadata may contain contentUrl
smil_url = self._get_smil_url(video_id) formats, subtitles = self._extract_smil_formats( # self._extract_smil_formats_and_subtitles(
formats = self._extract_smil_formats(smil_url, video_id, fatal=False) or [] self._get_smil_url(video_id), video_id, fatal=False), {}
if not formats: if not formats:
urlh = self._request_webpage( urlh = self._request_webpage(
@ -160,16 +157,16 @@ class SBSIE(InfoExtractor):
# try for metadata from the same source # try for metadata from the same source
player_data = self._get_player_data(video_id, fatal=False) player_data = self._get_player_data(video_id, fatal=False)
media = traverse_obj(player_data, 'video_object', expected_type=dict) or {} media = traverse_obj(player_data, 'video_object', T(dict)) or {}
# get, or add, metadata from catalogue # get, or add, metadata from catalogue
media.update(self._call_api(video_id, 'mpx-media/' + video_id, fatal=not media)) media.update(self._call_api(video_id, 'mpx-media/' + video_id, fatal=not media))
# utils candidate for use with traverse_obj()
def txt_or_none(s): def txt_or_none(s):
return (s.strip() or None) if isinstance(s, compat_str) else None return (s.strip() or None) if isinstance(s, compat_str) else None
# expected_type fn for thumbs # expected_type fn for thumbs
def xlate_thumb(t): def mk_thumb(t):
u = url_or_none(t.get('contentUrl')) u = url_or_none(t.get('contentUrl'))
return u and { return u and {
'id': t.get('name'), 'id': t.get('name'),
@ -185,51 +182,36 @@ class SBSIE(InfoExtractor):
result = parse_duration(d) result = parse_duration(d)
return result return result
def traverse_media(*args, **kwargs):
nkwargs = None
if 'expected_type' not in kwargs:
kwargs['expected_type'] = txt_or_none
nkwargs = kwargs
if 'get_all' not in kwargs:
kwargs['get_all'] = False
nkwargs = kwargs
if nkwargs:
kwargs = compat_kwargs(nkwargs)
return traverse_obj(media, *args, **kwargs)
# For named episodes, use the catalogue's title to set episode, rather than generic 'Episode N'. # For named episodes, use the catalogue's title to set episode, rather than generic 'Episode N'.
if traverse_media('partOfSeries', expected_type=dict): if traverse_obj(media, ('partOfSeries', T(dict))):
media['epName'] = traverse_media('title') media['epName'] = traverse_obj(media, 'title')
return merge_dicts(*reversed(({ str = txt_or_none # instant compat
return merge_dicts({
'id': video_id, 'id': video_id,
}, dict((k, traverse_media(v)) for k, v in { }, traverse_obj(media, {
'title': 'name', 'title': ('name', T(str)),
'description': 'description', 'description': ('description', T(str)),
'channel': ('taxonomy', 'channel', 'name'), 'channel': ('taxonomy', 'channel', 'name', T(str)),
'series': ((('partOfSeries', 'name'), 'seriesTitle')), 'series': ((('partOfSeries', 'name'), 'seriesTitle'), T(str)),
'series_id': ((('partOfSeries', 'uuid'), 'seriesID')), 'series_id': ((('partOfSeries', 'uuid'), 'seriesID'), T(str)),
'episode': 'epName', 'season_number': (('partOfSeries', None), 'seasonNumber', T(int_or_none)),
}.items()), { 'episode': ('epName', T(str)),
'season_number': traverse_media((('partOfSeries', None), 'seasonNumber'), expected_type=int_or_none), 'episode_number': ('episodeNumber', T(int_or_none)),
'episode_number': traverse_media('episodeNumber', expected_type=int_or_none), 'timestamp': ('datePublished', ('publication', 'startDate'), T(parse_iso8601)),
'timestamp': traverse_media('datePublished', ('publication', 'startDate'), 'release_year': ('releaseYear', T(int_or_none)),
expected_type=parse_iso8601), 'duration': ('duration', T(really_parse_duration)),
'release_year': traverse_media('releaseYear', expected_type=int_or_none), 'is_live': ('liveStream', T(bool)),
'duration': traverse_media('duration', expected_type=really_parse_duration), 'age_limit': ('classificationID', 'contentRating',
'is_live': traverse_media('liveStream', expected_type=bool), T(lambda x: self.AUS_TV_PARENTAL_GUIDELINES.get(x, '').upper() or None)), # dict.get is unhashable in py3.7
'age_limit': self.AUS_TV_PARENTAL_GUIDELINES.get(traverse_media( }, get_all=False), traverse_obj(media, {
'classificationID', 'contentRating', default='').upper()), 'categories': (('genres', Ellipsis), ('taxonomy', ('genre', 'subgenre'),
'categories': traverse_media( 'name', T(str))),
('genres', Ellipsis), ('taxonomy', ('genre', 'subgenre'), 'name'), 'tags': (('consumerAdviceTexts', ('sbsSubCertification', 'consumerAdvice')),
get_all=True) or None, Ellipsis, T(str)),
'tags': traverse_media( 'thumbnails': ('thumbnails', lambda _, v: v['contentUrl'], T(mk_thumb)),
(('consumerAdviceTexts', ('sbsSubCertification', 'consumerAdvice')), Ellipsis), }), {
get_all=True) or None,
'thumbnails': traverse_media(('thumbnails', Ellipsis),
expected_type=xlate_thumb, get_all=True),
'formats': formats, 'formats': formats,
# TODO: _extract_smil_formats_and_subtitles() 'subtitles': subtitles,
# 'subtitles': subtitles,
'uploader': 'SBSC', 'uploader': 'SBSC',
}))) }, rev=True)