mirror of https://github.com/yt-dlp/yt-dlp
Update to ytdl-commit-a08f2b7 (#10012)
[ie] Rework JWPlayer extraction -pull/9986/headf66372403f[ie/gbnews] Add extractor -70f230f9cf[ie/caffeinetv] Add extractor -40bd5c1815[ie/youporn] Improve extraction -0b2ce3685e[ie/youporn] Add playlist extractors -668332b973Closes #9188, Closes #9523 Authored by: Grub4K, bashonly
Simon Sawicki
7 months ago
committed by
GitHub
parent
e897bd8292
commit
a4da9db87b
@ -0,0 +1,74 @@
|
|||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
determine_ext,
|
||||||
|
int_or_none,
|
||||||
|
parse_iso8601,
|
||||||
|
traverse_obj,
|
||||||
|
urljoin,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class CaffeineTVIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?caffeine\.tv/[^/?#]+/video/(?P<id>[\da-f-]+)'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://www.caffeine.tv/TsuSurf/video/cffc0a00-e73f-11ec-8080-80017d29f26e',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'cffc0a00-e73f-11ec-8080-80017d29f26e',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'GOOOOD MORNINNNNN #highlights',
|
||||||
|
'timestamp': 1654702180,
|
||||||
|
'upload_date': '20220608',
|
||||||
|
'uploader': 'RahJON Wicc',
|
||||||
|
'uploader_id': 'TsuSurf',
|
||||||
|
'duration': 3145,
|
||||||
|
'age_limit': 17,
|
||||||
|
'thumbnail': 'https://www.caffeine.tv/broadcasts/776b6f84-9cd5-42e3-af1d-4a776eeed697/replay/lobby.jpg',
|
||||||
|
'comment_count': int,
|
||||||
|
'view_count': int,
|
||||||
|
'like_count': int,
|
||||||
|
'tags': ['highlights', 'battlerap'],
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
'skip_download': 'm3u8',
|
||||||
|
},
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
json_data = self._download_json(
|
||||||
|
f'https://api.caffeine.tv/social/public/activity/{video_id}', video_id)
|
||||||
|
broadcast_info = traverse_obj(json_data, ('broadcast_info', {dict})) or {}
|
||||||
|
|
||||||
|
video_url = broadcast_info['video_url']
|
||||||
|
ext = determine_ext(video_url)
|
||||||
|
if ext == 'm3u8':
|
||||||
|
formats = self._extract_m3u8_formats(video_url, video_id, 'mp4')
|
||||||
|
else:
|
||||||
|
formats = [{'url': video_url}]
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'formats': formats,
|
||||||
|
**traverse_obj(json_data, {
|
||||||
|
'like_count': ('like_count', {int_or_none}),
|
||||||
|
'view_count': ('view_count', {int_or_none}),
|
||||||
|
'comment_count': ('comment_count', {int_or_none}),
|
||||||
|
'tags': ('tags', ..., {str}, {lambda x: x or None}),
|
||||||
|
'uploader': ('user', 'name', {str}),
|
||||||
|
'uploader_id': (((None, 'user'), 'username'), {str}, any),
|
||||||
|
'is_live': ('is_live', {bool}),
|
||||||
|
}),
|
||||||
|
**traverse_obj(broadcast_info, {
|
||||||
|
'title': ('broadcast_title', {str}),
|
||||||
|
'duration': ('content_duration', {int_or_none}),
|
||||||
|
'timestamp': ('broadcast_start_time', {parse_iso8601}),
|
||||||
|
'thumbnail': ('preview_image_path', {lambda x: urljoin(url, x)}),
|
||||||
|
}),
|
||||||
|
'age_limit': {
|
||||||
|
# assume Apple Store ratings: https://en.wikipedia.org/wiki/Mobile_software_content_rating_system
|
||||||
|
'FOUR_PLUS': 0,
|
||||||
|
'NINE_PLUS': 9,
|
||||||
|
'TWELVE_PLUS': 12,
|
||||||
|
'SEVENTEEN_PLUS': 17,
|
||||||
|
}.get(broadcast_info.get('content_rating'), 17),
|
||||||
|
}
|
||||||
@ -0,0 +1,107 @@
|
|||||||
|
import functools
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
ExtractorError,
|
||||||
|
extract_attributes,
|
||||||
|
get_elements_html_by_class,
|
||||||
|
url_or_none,
|
||||||
|
)
|
||||||
|
from ..utils.traversal import traverse_obj
|
||||||
|
|
||||||
|
|
||||||
|
class GBNewsIE(InfoExtractor):
|
||||||
|
IE_DESC = 'GB News clips, features and live streams'
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?gbnews\.(?:uk|com)/(?:\w+/)?(?P<id>[^#?]+)'
|
||||||
|
|
||||||
|
_PLATFORM = 'safari'
|
||||||
|
_SSMP_URL = 'https://mm-v2.simplestream.com/ssmp/api.php'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://www.gbnews.com/news/bbc-claudine-gay-harvard-university-antisemitism-row',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '52264136',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)',
|
||||||
|
'display_id': 'bbc-claudine-gay-harvard-university-antisemitism-row',
|
||||||
|
'description': 'The post was criticised by former employers of the broadcaster',
|
||||||
|
'title': 'BBC deletes post after furious backlash over headline downplaying antisemitism',
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.gbnews.com/royal/prince-harry-in-love-with-kate-meghan-markle-jealous-royal',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '52328390',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)',
|
||||||
|
'display_id': 'prince-harry-in-love-with-kate-meghan-markle-jealous-royal',
|
||||||
|
'description': 'Ingrid Seward has published 17 books documenting the highs and lows of the Royal Family',
|
||||||
|
'title': 'Royal author claims Prince Harry was \'in love\' with Kate - Meghan was \'jealous\'',
|
||||||
|
}
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.gbnews.uk/watchlive',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '1069',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)',
|
||||||
|
'display_id': 'watchlive',
|
||||||
|
'live_status': 'is_live',
|
||||||
|
'title': r're:^GB News Live',
|
||||||
|
},
|
||||||
|
'params': {'skip_download': 'm3u8'},
|
||||||
|
}]
|
||||||
|
|
||||||
|
@functools.lru_cache
|
||||||
|
def _get_ss_endpoint(self, data_id, data_env):
|
||||||
|
if not data_id:
|
||||||
|
data_id = 'GB003'
|
||||||
|
if not data_env:
|
||||||
|
data_env = 'production'
|
||||||
|
|
||||||
|
json_data = self._download_json(
|
||||||
|
self._SSMP_URL, None, 'Downloading Simplestream JSON metadata', query={
|
||||||
|
'id': data_id,
|
||||||
|
'env': data_env,
|
||||||
|
})
|
||||||
|
meta_url = traverse_obj(json_data, ('response', 'api_hostname', {url_or_none}))
|
||||||
|
if not meta_url:
|
||||||
|
raise ExtractorError('No API host found')
|
||||||
|
|
||||||
|
return meta_url
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
display_id = self._match_id(url).rpartition('/')[2]
|
||||||
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
|
||||||
|
video_data = None
|
||||||
|
elements = get_elements_html_by_class('simplestream', webpage)
|
||||||
|
for html_tag in elements:
|
||||||
|
attributes = extract_attributes(html_tag)
|
||||||
|
if 'sidebar' not in (attributes.get('class') or ''):
|
||||||
|
video_data = attributes
|
||||||
|
if not video_data:
|
||||||
|
raise ExtractorError('Could not find video element', expected=True)
|
||||||
|
|
||||||
|
endpoint_url = self._get_ss_endpoint(video_data.get('data-id'), video_data.get('data-env'))
|
||||||
|
|
||||||
|
uvid = video_data['data-uvid']
|
||||||
|
video_type = video_data.get('data-type')
|
||||||
|
if not video_type or video_type == 'vod':
|
||||||
|
video_type = 'show'
|
||||||
|
stream_data = self._download_json(
|
||||||
|
f'{endpoint_url}/api/{video_type}/stream/{uvid}',
|
||||||
|
uvid, 'Downloading stream JSON', query={
|
||||||
|
'key': video_data.get('data-key'),
|
||||||
|
'platform': self._PLATFORM,
|
||||||
|
})
|
||||||
|
if traverse_obj(stream_data, 'drm'):
|
||||||
|
self.report_drm(uvid)
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': uvid,
|
||||||
|
'display_id': display_id,
|
||||||
|
'title': self._og_search_title(webpage, default=None),
|
||||||
|
'description': self._og_search_description(webpage, default=None),
|
||||||
|
'formats': self._extract_m3u8_formats(traverse_obj(stream_data, (
|
||||||
|
'response', 'stream', {url_or_none})), uvid, 'mp4'),
|
||||||
|
'thumbnail': self._og_search_thumbnail(webpage, default=None),
|
||||||
|
'is_live': video_type == 'live',
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue