Compare commits

..

5 Commits

Author SHA1 Message Date
garret
fc2cc626f0
[ie/cineverse] Detect when login required (#9081)
Partially addresses #9072
Authored by: garret1317
2024-01-31 20:21:59 +00:00
columndeeply
a2bac6b7ad
[ie/PrankCastPost] Add extractor (#8933)
Authored by: columndeeply
2024-01-31 20:16:07 +00:00
rrgomes
4b8b0dded8
[ie/nfb] Add support for onf.ca and series (#8997)
Closes #8198
Authored by: bashonly, rrgomes

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
2024-01-31 18:00:15 +00:00
jazz1611
4a6ff0b47a
[ie/redtube] Support redtube.com.br URLs (#9103)
Authored by: jazz1611
2024-01-31 17:56:29 +00:00
Radu Manole
62c65bfaf8
[ie/NinaProtocol] Add extractor (#8946)
Closes #8709, Closes #8764
Authored by: RaduManole, seproDev

Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com>
2024-01-31 18:41:31 +01:00
6 changed files with 576 additions and 28 deletions

View File

@ -1247,7 +1247,10 @@ from .nexx import (
NexxIE, NexxIE,
NexxEmbedIE, NexxEmbedIE,
) )
from .nfb import NFBIE from .nfb import (
NFBIE,
NFBSeriesIE,
)
from .nfhsnetwork import NFHSNetworkIE from .nfhsnetwork import NFHSNetworkIE
from .nfl import ( from .nfl import (
NFLIE, NFLIE,
@ -1284,6 +1287,7 @@ from .niconico import (
NicovideoTagURLIE, NicovideoTagURLIE,
NiconicoLiveIE, NiconicoLiveIE,
) )
from .ninaprotocol import NinaProtocolIE
from .ninecninemedia import ( from .ninecninemedia import (
NineCNineMediaIE, NineCNineMediaIE,
CPTwentyFourIE, CPTwentyFourIE,
@ -1514,7 +1518,7 @@ from .puhutv import (
PuhuTVSerieIE, PuhuTVSerieIE,
) )
from .pr0gramm import Pr0grammIE from .pr0gramm import Pr0grammIE
from .prankcast import PrankCastIE from .prankcast import PrankCastIE, PrankCastPostIE
from .premiershiprugby import PremiershipRugbyIE from .premiershiprugby import PremiershipRugbyIE
from .presstv import PressTVIE from .presstv import PressTVIE
from .projectveritas import ProjectVeritasIE from .projectveritas import ProjectVeritasIE

View File

@ -67,7 +67,10 @@ class CineverseIE(CineverseBaseIE):
html = self._download_webpage(url, video_id) html = self._download_webpage(url, video_id)
idetails = self._search_nextjs_data(html, video_id)['props']['pageProps']['idetails'] idetails = self._search_nextjs_data(html, video_id)['props']['pageProps']['idetails']
if idetails.get('err_code') == 1200: err_code = idetails.get('err_code')
if err_code == 1002:
self.raise_login_required()
elif err_code == 1200:
self.raise_geo_restricted( self.raise_geo_restricted(
'This video is not available from your location due to geo restriction. ' 'This video is not available from your location due to geo restriction. '
'You may be able to bypass it by using the /details/ page instead of the /watch/ page', 'You may be able to bypass it by using the /details/ page instead of the /watch/ page',

View File

@ -1,10 +1,54 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
int_or_none,
join_nonempty,
merge_dicts,
parse_count,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class NFBIE(InfoExtractor): class NFBBaseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nfb\.ca/film/(?P<id>[^/?#&]+)' _VALID_URL_BASE = r'https?://(?:www\.)?(?P<site>nfb|onf)\.ca'
_GEO_COUNTRIES = ['CA']
def _extract_ep_data(self, webpage, video_id, fatal=False):
return self._search_json(
r'const\s+episodesData\s*=', webpage, 'episode data', video_id,
contains_pattern=r'\[\s*{(?s:.+)}\s*\]', fatal=fatal) or []
def _extract_ep_info(self, data, video_id, slug=None):
info = traverse_obj(data, (lambda _, v: video_id in v['embed_url'], {
'description': ('description', {str}),
'thumbnail': ('thumbnail_url', {url_or_none}),
'uploader': ('data_layer', 'episodeMaker', {str}),
'release_year': ('data_layer', 'episodeYear', {int_or_none}),
'episode': ('data_layer', 'episodeTitle', {str}),
'season': ('data_layer', 'seasonTitle', {str}),
'season_number': ('data_layer', 'seasonTitle', {parse_count}),
'series': ('data_layer', 'seriesTitle', {str}),
}), get_all=False)
return {
**info,
'id': video_id,
'title': join_nonempty('series', 'episode', from_dict=info, delim=' - '),
'episode_number': int_or_none(self._search_regex(
r'[/-]e(?:pisode)?-?(\d+)(?:[/-]|$)', slug or video_id, 'episode number', default=None)),
}
class NFBIE(NFBBaseIE):
IE_NAME = 'nfb'
IE_DESC = 'nfb.ca and onf.ca films and episodes'
_VALID_URL = [
rf'{NFBBaseIE._VALID_URL_BASE}/(?P<type>film)/(?P<id>[^/?#&]+)',
rf'{NFBBaseIE._VALID_URL_BASE}/(?P<type>series?)/(?P<id>[^/?#&]+/s(?:ea|ai)son\d+/episode\d+)',
]
_TESTS = [{ _TESTS = [{
'note': 'NFB film',
'url': 'https://www.nfb.ca/film/trafficopter/', 'url': 'https://www.nfb.ca/film/trafficopter/',
'info_dict': { 'info_dict': {
'id': 'trafficopter', 'id': 'trafficopter',
@ -14,29 +58,192 @@ class NFBIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Barrie Howells', 'uploader': 'Barrie Howells',
'release_year': 1972, 'release_year': 1972,
'duration': 600.0,
}, },
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF film',
'url': 'https://www.onf.ca/film/mal-du-siecle/',
'info_dict': {
'id': 'mal-du-siecle',
'ext': 'mp4',
'title': 'Le mal du siècle',
'description': 'md5:1abf774d77569ebe603419f2d344102b',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Catherine Lepage',
'release_year': 2019,
'duration': 300.0,
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB episode with English title',
'url': 'https://www.nfb.ca/series/true-north-inside-the-rise-of-toronto-basketball/season1/episode9/',
'info_dict': {
'id': 'true-north-episode9-true-north-finale-making-it',
'ext': 'mp4',
'title': 'True North: Inside the Rise of Toronto Basketball - Finale: Making It',
'description': 'We catch up with each player in the midst of their journey as they reflect on their road ahead.',
'series': 'True North: Inside the Rise of Toronto Basketball',
'release_year': 2018,
'season': 'Season 1',
'season_number': 1,
'episode': 'Finale: Making It',
'episode_number': 9,
'uploader': 'Ryan Sidhoo',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF episode with French title',
'url': 'https://www.onf.ca/serie/direction-nord-la-montee-du-basketball-a-toronto/saison1/episode9/',
'info_dict': {
'id': 'direction-nord-episode-9',
'ext': 'mp4',
'title': 'Direction nord La montée du basketball à Toronto - Finale : Réussir',
'description': 'md5:349a57419b71432b97bf6083d92b029d',
'series': 'Direction nord La montée du basketball à Toronto',
'release_year': 2018,
'season': 'Saison 1',
'season_number': 1,
'episode': 'Finale : Réussir',
'episode_number': 9,
'uploader': 'Ryan Sidhoo',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB episode with French title (needs geo-bypass)',
'url': 'https://www.nfb.ca/series/etoile-du-nord/saison1/episode1/',
'info_dict': {
'id': 'etoile-du-nord-episode-1-lobservation',
'ext': 'mp4',
'title': 'Étoile du Nord - L\'observation',
'description': 'md5:161a4617260dee3de70f509b2c9dd21b',
'series': 'Étoile du Nord',
'release_year': 2023,
'season': 'Saison 1',
'season_number': 1,
'episode': 'L\'observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF episode with English title (needs geo-bypass)',
'url': 'https://www.onf.ca/serie/north-star/season1/episode1/',
'info_dict': {
'id': 'north-star-episode-1-observation',
'ext': 'mp4',
'title': 'North Star - Observation',
'description': 'md5:c727f370839d8a817392b9e3f23655c7',
'series': 'North Star',
'release_year': 2023,
'season': 'Season 1',
'season_number': 1,
'episode': 'Observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB episode with /film/ URL and English title (needs geo-bypass)',
'url': 'https://www.nfb.ca/film/north-star-episode-1-observation/',
'info_dict': {
'id': 'north-star-episode-1-observation',
'ext': 'mp4',
'title': 'North Star - Observation',
'description': 'md5:c727f370839d8a817392b9e3f23655c7',
'series': 'North Star',
'release_year': 2023,
'season': 'Season 1',
'season_number': 1,
'episode': 'Observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'ONF episode with /film/ URL and French title (needs geo-bypass)',
'url': 'https://www.onf.ca/film/etoile-du-nord-episode-1-lobservation/',
'info_dict': {
'id': 'etoile-du-nord-episode-1-lobservation',
'ext': 'mp4',
'title': 'Étoile du Nord - L\'observation',
'description': 'md5:161a4617260dee3de70f509b2c9dd21b',
'series': 'Étoile du Nord',
'release_year': 2023,
'season': 'Saison 1',
'season_number': 1,
'episode': 'L\'observation',
'episode_number': 1,
'uploader': 'Patrick Bossé',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'Season 2 episode w/o episode num in id, extract from json ld',
'url': 'https://www.onf.ca/film/liste-des-choses-qui-existent-saison-2-ours',
'info_dict': {
'id': 'liste-des-choses-qui-existent-saison-2-ours',
'ext': 'mp4',
'title': 'La liste des choses qui existent - L\'ours en peluche',
'description': 'md5:d5e8d8fc5f3a7385a9cf0f509b37e28a',
'series': 'La liste des choses qui existent',
'release_year': 2022,
'season': 'Saison 2',
'season_number': 2,
'episode': 'L\'ours en peluche',
'episode_number': 12,
'uploader': 'Francis Papillon',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'NFB film /embed/player/ page',
'url': 'https://www.nfb.ca/film/afterlife/embed/player/',
'info_dict': {
'id': 'afterlife',
'ext': 'mp4',
'title': 'Afterlife',
'description': 'md5:84951394f594f1fb1e62d9c43242fdf5',
'release_year': 1978,
'duration': 420.0,
'uploader': 'Ishu Patel',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) site, type_, slug = self._match_valid_url(url).group('site', 'type', 'id')
# Need to construct the URL since we match /embed/player/ URLs as well
webpage, urlh = self._download_webpage_handle(f'https://www.{site}.ca/{type_}/{slug}/', slug)
# type_ can change from film to serie(s) after redirect; new slug may have episode number
type_, slug = self._match_valid_url(urlh.url).group('type', 'id')
webpage = self._download_webpage('https://www.nfb.ca/film/%s/' % video_id, video_id) embed_url = urljoin(f'https://www.{site}.ca', self._html_search_regex(
r'<[^>]+\bid=["\']player-iframe["\'][^>]*\bsrc=["\']([^"\']+)', webpage, 'embed url'))
video_id = self._match_id(embed_url) # embed url has unique slug
player = self._download_webpage(embed_url, video_id, 'Downloading player page')
if 'MESSAGE_GEOBLOCKED' in player:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
iframe = self._html_search_regex( formats, subtitles = self._extract_m3u8_formats_and_subtitles(
r'<[^>]+\bid=["\']player-iframe["\'][^>]*src=["\']([^"\']+)', self._html_search_regex(r'source:\s*\'([^\']+)', player, 'm3u8 url'),
webpage, 'iframe', default=None, fatal=True) video_id, 'mp4', m3u8_id='hls')
if iframe.startswith('/'):
iframe = f'https://www.nfb.ca{iframe}'
player = self._download_webpage(iframe, video_id) if dv_source := self._html_search_regex(r'dvSource:\s*\'([^\']+)', player, 'dv', default=None):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
dv_source, video_id, 'mp4', m3u8_id='dv', preference=-2, fatal=False)
for fmt in fmts:
fmt['format_note'] = 'described video'
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
source = self._html_search_regex( info = {
r'source:\s*\'([^\']+)',
player, 'source', default=None, fatal=True)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(source, video_id, ext='mp4')
return {
'id': video_id, 'id': video_id,
'title': self._html_search_regex( 'title': self._html_search_regex(
r'<[^>]+\bid=["\']titleHeader["\'][^>]*>\s*<h1[^>]*>\s*([^<]+?)\s*</h1>', r'<[^>]+\bid=["\']titleHeader["\'][^>]*>\s*<h1[^>]*>\s*([^<]+?)\s*</h1>',
@ -45,14 +252,49 @@ class NFBIE(InfoExtractor):
r'<[^>]+\bid=["\']tabSynopsis["\'][^>]*>\s*<p[^>]*>\s*([^<]+)', r'<[^>]+\bid=["\']tabSynopsis["\'][^>]*>\s*<p[^>]*>\s*([^<]+)',
webpage, 'description', default=None), webpage, 'description', default=None),
'thumbnail': self._html_search_regex( 'thumbnail': self._html_search_regex(
r'poster:\s*\'([^\']+)', r'poster:\s*\'([^\']+)', player, 'thumbnail', default=None),
player, 'thumbnail', default=None),
'uploader': self._html_search_regex( 'uploader': self._html_search_regex(
r'<[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', r'<[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', webpage, 'uploader', default=None),
webpage, 'uploader', default=None),
'release_year': int_or_none(self._html_search_regex( 'release_year': int_or_none(self._html_search_regex(
r'<[^>]+\bitemprop=["\']datePublished["\'][^>]*>([^<]+)', r'<[^>]+\bitemprop=["\']datePublished["\'][^>]*>([^<]+)',
webpage, 'release_year', default=None)), webpage, 'release_year', default=None)),
} if type_ == 'film' else self._extract_ep_info(self._extract_ep_data(webpage, video_id, slug), video_id)
return merge_dicts({
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
} }, info, self._search_json_ld(webpage, video_id, default={}))
class NFBSeriesIE(NFBBaseIE):
IE_NAME = 'nfb:series'
IE_DESC = 'nfb.ca and onf.ca series'
_VALID_URL = rf'{NFBBaseIE._VALID_URL_BASE}/(?P<type>series?)/(?P<id>[^/?#&]+)/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://www.nfb.ca/series/true-north-inside-the-rise-of-toronto-basketball/',
'playlist_mincount': 9,
'info_dict': {
'id': 'true-north-inside-the-rise-of-toronto-basketball',
},
}, {
'url': 'https://www.onf.ca/serie/la-liste-des-choses-qui-existent-serie/',
'playlist_mincount': 26,
'info_dict': {
'id': 'la-liste-des-choses-qui-existent-serie',
},
}]
def _entries(self, episodes):
for episode in traverse_obj(episodes, lambda _, v: NFBIE.suitable(v['embed_url'])):
mobj = NFBIE._match_valid_url(episode['embed_url'])
yield self.url_result(
mobj[0], NFBIE, **self._extract_ep_info([episode], mobj.group('id')))
def _real_extract(self, url):
site, type_, series_id = self._match_valid_url(url).group('site', 'type', 'id')
season_path = 'saison' if type_ == 'serie' else 'season'
webpage = self._download_webpage(
f'https://www.{site}.ca/{type_}/{series_id}/{season_path}1/episode1', series_id)
episodes = self._extract_ep_data(webpage, series_id, fatal=True)
return self.playlist_result(self._entries(episodes), series_id)

View File

@ -0,0 +1,225 @@
from .common import InfoExtractor
from ..utils import int_or_none, mimetype2ext, parse_iso8601, url_or_none
from ..utils.traversal import traverse_obj
class NinaProtocolIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ninaprotocol\.com/releases/(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'https://www.ninaprotocol.com/releases/3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ',
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ',
'title': 'The Spatulas - March Chant',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'channel': 'ppm',
'description': 'md5:bb9f9d39d8f786449cd5d0ff7c5772db',
'album': 'The Spatulas - March Chant',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'timestamp': 1701417610,
'uploader': 'ppmrecs',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'display_id': 'the-spatulas-march-chant',
'upload_date': '20231201',
'album_artist': 'Post Present Medium ',
},
'playlist': [{
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_1',
'title': 'March Chant In April',
'track': 'March Chant In April',
'ext': 'mp3',
'duration': 152,
'track_number': 1,
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'uploader': 'ppmrecs',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'timestamp': 1701417610,
'channel': 'ppm',
'album': 'The Spatulas - March Chant',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'upload_date': '20231201',
'album_artist': 'Post Present Medium ',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_2',
'title': 'Rescue Mission',
'track': 'Rescue Mission',
'ext': 'mp3',
'duration': 212,
'track_number': 2,
'album_artist': 'Post Present Medium ',
'uploader': 'ppmrecs',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'channel': 'ppm',
'upload_date': '20231201',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'timestamp': 1701417610,
'album': 'The Spatulas - March Chant',
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_3',
'title': 'Slinger Style',
'track': 'Slinger Style',
'ext': 'mp3',
'duration': 179,
'track_number': 3,
'timestamp': 1701417610,
'upload_date': '20231201',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'album_artist': 'Post Present Medium ',
'album': 'The Spatulas - March Chant',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'uploader': 'ppmrecs',
'channel': 'ppm',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_4',
'title': 'Psychic Signal',
'track': 'Psychic Signal',
'ext': 'mp3',
'duration': 220,
'track_number': 4,
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'upload_date': '20231201',
'album': 'The Spatulas - March Chant',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'timestamp': 1701417610,
'album_artist': 'Post Present Medium ',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'channel': 'ppm',
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'uploader': 'ppmrecs',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_5',
'title': 'Curvy Color',
'track': 'Curvy Color',
'ext': 'mp3',
'duration': 148,
'track_number': 5,
'timestamp': 1701417610,
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'album': 'The Spatulas - March Chant',
'album_artist': 'Post Present Medium ',
'channel': 'ppm',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'uploader': 'ppmrecs',
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'upload_date': '20231201',
}
}, {
'info_dict': {
'id': '3SvsMM3y4oTPZ5DXFJnLkCAqkxz34hjzFxqms1vu9XBJ_6',
'title': 'Caveman Star',
'track': 'Caveman Star',
'ext': 'mp3',
'duration': 121,
'track_number': 6,
'channel_id': '4ceG4zsb7VVxBTGPtZMqDZWGHo3VUg2xRvzC2b17ymWP',
'thumbnail': 'https://www.arweave.net/VyZA6CBeUuqP174khvSrD44Eosi3MLVyWN42uaQKg50',
'tags': ['punk', 'postpresentmedium', 'cambridge'],
'album_artist': 'Post Present Medium ',
'uploader': 'ppmrecs',
'timestamp': 1701417610,
'uploader_id': '2bGjgdKUddJoj2shYGqfNcUfoSoABP21RJoiwGMZDq3A',
'album': 'The Spatulas - March Chant',
'channel': 'ppm',
'upload_date': '20231201',
},
}],
}, {
'url': 'https://www.ninaprotocol.com/releases/f-g-s-american-shield',
'info_dict': {
'id': '76PZnJwaMgViQHYfA4NYJXds7CmW6vHQKAtQUxGene6J',
'description': 'md5:63f08d5db558b4b36e1896f317062721',
'title': 'F.G.S. - American Shield',
'uploader_id': 'Ej3rozs11wYqFk1Gs6oggGCkGLz8GzBhmJfnUxf6gPci',
'channel_id': '6JuksCZPXuP16wJ1BUfwuukJzh42C7guhLrFPPkVJfyE',
'channel': 'tinkscough',
'tags': [],
'album_artist': 'F.G.S.',
'album': 'F.G.S. - American Shield',
'thumbnail': 'https://www.arweave.net/YJpgImkXLT9SbpFb576KuZ5pm6bdvs452LMs3Rx6lm8',
'display_id': 'f-g-s-american-shield',
'uploader': 'flannerysilva',
'timestamp': 1702395858,
'upload_date': '20231212',
},
'playlist_count': 1,
}, {
'url': 'https://www.ninaprotocol.com/releases/time-to-figure-things-out',
'info_dict': {
'id': '6Zi1nC5hj6b13NkpxVYwRhFy6mYA7oLBbe9DMrgGDcYh',
'display_id': 'time-to-figure-things-out',
'description': 'md5:960202ed01c3134bb8958f1008527e35',
'timestamp': 1706283607,
'title': 'DJ STEPDAD - time to figure things out',
'album_artist': 'DJ STEPDAD',
'uploader': 'tddvsss',
'upload_date': '20240126',
'album': 'time to figure things out',
'uploader_id': 'AXQNRgTyYsySyAMFDwxzumuGjfmoXshorCesjpquwCBi',
'thumbnail': 'https://www.arweave.net/O4i8bcKVqJVZvNeHHFp6r8knpFGh9ZwEgbeYacr4nss',
'tags': [],
},
'playlist_count': 4,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
release = self._download_json(
f'https://api.ninaprotocol.com/v1/releases/{video_id}', video_id)['release']
video_id = release.get('publicKey') or video_id
common_info = traverse_obj(release, {
'album': ('metadata', 'properties', 'title', {str}),
'album_artist': ((('hub', 'data'), 'publisherAccount'), 'displayName', {str}),
'timestamp': ('datetime', {parse_iso8601}),
'thumbnail': ('metadata', 'image', {url_or_none}),
'uploader': ('publisherAccount', 'handle', {str}),
'uploader_id': ('publisherAccount', 'publicKey', {str}),
'channel': ('hub', 'handle', {str}),
'channel_id': ('hub', 'publicKey', {str}),
}, get_all=False)
common_info['tags'] = traverse_obj(release, ('metadata', 'properties', 'tags', ..., {str}))
entries = []
for track_num, track in enumerate(traverse_obj(release, (
'metadata', 'properties', 'files', lambda _, v: url_or_none(v['uri']))), 1):
entries.append({
'id': f'{video_id}_{track_num}',
'url': track['uri'],
**traverse_obj(track, {
'title': ('track_title', {str}),
'track': ('track_title', {str}),
'ext': ('type', {mimetype2ext}),
'track_number': ('track', {int_or_none}),
'duration': ('duration', {int_or_none}),
}),
'vcodec': 'none',
**common_info,
})
return {
'_type': 'playlist',
'id': video_id,
'entries': entries,
**traverse_obj(release, {
'display_id': ('slug', {str}),
'title': ('metadata', 'name', {str}),
'description': ('metadata', 'description', {str}),
}),
**common_info,
}

View File

@ -1,5 +1,8 @@
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import parse_iso8601, traverse_obj, try_call from ..utils import float_or_none, parse_iso8601, str_or_none, try_call
from ..utils.traversal import traverse_obj
class PrankCastIE(InfoExtractor): class PrankCastIE(InfoExtractor):
@ -64,3 +67,71 @@ class PrankCastIE(InfoExtractor):
'categories': [json_info.get('broadcast_category')], 'categories': [json_info.get('broadcast_category')],
'tags': try_call(lambda: json_info['broadcast_tags'].split(',')) 'tags': try_call(lambda: json_info['broadcast_tags'].split(','))
} }
class PrankCastPostIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?prankcast\.com/[^/?#]+/posts/(?P<id>\d+)-(?P<display_id>[^/?#]+)'
_TESTS = [{
'url': 'https://prankcast.com/devonanustart/posts/6214-happy-national-rachel-day-',
'info_dict': {
'id': '6214',
'ext': 'mp3',
'title': 'Happy National Rachel Day!',
'display_id': 'happy-national-rachel-day-',
'timestamp': 1704333938,
'uploader': 'Devonanustart',
'channel_id': '4',
'duration': 13175,
'cast': ['Devonanustart'],
'description': '',
'categories': ['prank call'],
'upload_date': '20240104'
}
}, {
'url': 'https://prankcast.com/despicabledogs/posts/6217-jake-the-work-crow-',
'info_dict': {
'id': '6217',
'ext': 'mp3',
'title': 'Jake the Work Crow!',
'display_id': 'jake-the-work-crow-',
'timestamp': 1704346592,
'uploader': 'despicabledogs',
'channel_id': '957',
'duration': 263.287,
'cast': ['despicabledogs'],
'description': 'https://imgur.com/a/vtxLvKU',
'categories': [],
'upload_date': '20240104'
}
}]
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
webpage = self._download_webpage(url, video_id)
post = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['ssr_data_posts']
content = self._parse_json(post['post_contents_json'], video_id)[0]
uploader = post.get('user_name')
guests_json = traverse_obj(content, ('guests_json', {json.loads}, {dict})) or {}
return {
'id': video_id,
'title': post.get('post_title') or self._og_search_title(webpage),
'display_id': display_id,
'url': content.get('url'),
'timestamp': parse_iso8601(content.get('start_date') or content.get('crdate'), ' '),
'uploader': uploader,
'channel_id': str_or_none(post.get('user_id')),
'duration': float_or_none(content.get('duration')),
'cast': list(filter(None, [uploader] + traverse_obj(guests_json, (..., 'name')))),
'description': post.get('post_body'),
'categories': list(filter(None, [content.get('category')])),
'tags': try_call(lambda: list(filter('', post['post_tags'].split(',')))),
'subtitles': {
'live_chat': [{
'url': f'https://prankcast.com/api/private/chat/select-broadcast?id={post["content_id"]}&cache=',
'ext': 'json',
}],
} if post.get('content_id') else None
}

View File

@ -12,7 +12,7 @@ from ..utils import (
class RedTubeIE(InfoExtractor): class RedTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com(?:\.br)?/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
_EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)'] _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)']
_TESTS = [{ _TESTS = [{
'url': 'https://www.redtube.com/38864951', 'url': 'https://www.redtube.com/38864951',
@ -35,6 +35,9 @@ class RedTubeIE(InfoExtractor):
}, { }, {
'url': 'http://it.redtube.com/66418', 'url': 'http://it.redtube.com/66418',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.redtube.com.br/103224331',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):