Compare commits

..

1 Commits

Author SHA1 Message Date
Florentin Le Moal
f992ad5372
Merge f36c8a726f into b83ca24eb7 2024-11-10 00:54:44 +01:00
3 changed files with 127 additions and 188 deletions

View File

@ -1939,7 +1939,9 @@ from .spotify import (
) )
from .spreaker import ( from .spreaker import (
SpreakerIE, SpreakerIE,
SpreakerPageIE,
SpreakerShowIE, SpreakerShowIE,
SpreakerShowPageIE,
) )
from .springboardplatform import SpringboardPlatformIE from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE from .sprout import SproutIE

View File

@ -2,18 +2,15 @@ import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
UnsupportedError,
bool_or_none, bool_or_none,
determine_ext, determine_ext,
int_or_none, int_or_none,
js_to_json,
parse_qs, parse_qs,
str_or_none, traverse_obj,
try_get, try_get,
unified_timestamp, unified_timestamp,
url_or_none, url_or_none,
) )
from ..utils.traversal import traverse_obj
class RutubeBaseIE(InfoExtractor): class RutubeBaseIE(InfoExtractor):
@ -22,7 +19,7 @@ class RutubeBaseIE(InfoExtractor):
query = {} query = {}
query['format'] = 'json' query['format'] = 'json'
return self._download_json( return self._download_json(
f'https://rutube.ru/api/video/{video_id}/', f'http://rutube.ru/api/video/{video_id}/',
video_id, 'Downloading video JSON', video_id, 'Downloading video JSON',
'Unable to download video JSON', query=query) 'Unable to download video JSON', query=query)
@ -64,21 +61,18 @@ class RutubeBaseIE(InfoExtractor):
query = {} query = {}
query['format'] = 'json' query['format'] = 'json'
return self._download_json( return self._download_json(
f'https://rutube.ru/api/play/options/{video_id}/', f'http://rutube.ru/api/play/options/{video_id}/',
video_id, 'Downloading options JSON', video_id, 'Downloading options JSON',
'Unable to download options JSON', 'Unable to download options JSON',
headers=self.geo_verification_headers(), query=query) headers=self.geo_verification_headers(), query=query)
def _extract_formats_and_subtitles(self, options, video_id): def _extract_formats(self, options, video_id):
formats = [] formats = []
subtitles = {}
for format_id, format_url in options['video_balancer'].items(): for format_id, format_url in options['video_balancer'].items():
ext = determine_ext(format_url) ext = determine_ext(format_url)
if ext == 'm3u8': if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles( formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False) format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif ext == 'f4m': elif ext == 'f4m':
formats.extend(self._extract_f4m_formats( formats.extend(self._extract_f4m_formats(
format_url, video_id, f4m_id=format_id, fatal=False)) format_url, video_id, f4m_id=format_id, fatal=False))
@ -88,19 +82,11 @@ class RutubeBaseIE(InfoExtractor):
'format_id': format_id, 'format_id': format_id,
}) })
for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})): for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles( formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4', fatal=False))
hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls') return formats
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
for caption in traverse_obj(options, ('captions', lambda _, v: url_or_none(v['file']))):
subtitles.setdefault(caption.get('code') or 'ru', []).append({
'url': caption['file'],
'name': caption.get('langTitle'),
})
return formats, subtitles
def _download_and_extract_formats_and_subtitles(self, video_id, query=None): def _download_and_extract_formats(self, video_id, query=None):
return self._extract_formats_and_subtitles( return self._extract_formats(
self._download_api_options(video_id, query=query), video_id) self._download_api_options(video_id, query=query), video_id)
@ -111,8 +97,8 @@ class RutubeIE(RutubeBaseIE):
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1'] _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
_TESTS = [{ _TESTS = [{
'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
'md5': '3d73fdfe5bb81b9aef139e22ef3de26a', 'md5': 'e33ac625efca66aba86cbec9851f2692',
'info_dict': { 'info_dict': {
'id': '3eac3b4561676c17df9132a9a1e62e3e', 'id': '3eac3b4561676c17df9132a9a1e62e3e',
'ext': 'mp4', 'ext': 'mp4',
@ -125,25 +111,26 @@ class RutubeIE(RutubeBaseIE):
'upload_date': '20131016', 'upload_date': '20131016',
'age_limit': 0, 'age_limit': 0,
'view_count': int, 'view_count': int,
'thumbnail': 'https://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg', 'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
'categories': ['Новости и СМИ'], 'categories': ['Новости и СМИ'],
'chapters': [], 'chapters': [],
}, },
'expected_warnings': ['Unable to download f4m'],
}, { }, {
'url': 'https://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661', 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661', 'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252', 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source', 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg', 'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
'md5': '4fce7b4fcc7b1bcaa3f45eb1e1ad0dd7', 'md5': 'd106225f15d625538fe22971158e896f',
'info_dict': { 'info_dict': {
'id': '884fb55f07a97ab673c7d654553e0f48', 'id': '884fb55f07a97ab673c7d654553e0f48',
'ext': 'mp4', 'ext': 'mp4',
@ -156,10 +143,11 @@ class RutubeIE(RutubeBaseIE):
'upload_date': '20221210', 'upload_date': '20221210',
'age_limit': 0, 'age_limit': 0,
'view_count': int, 'view_count': int,
'thumbnail': 'https://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg', 'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
'categories': ['Видеоигры'], 'categories': ['Видеоигры'],
'chapters': [], 'chapters': [],
}, },
'expected_warnings': ['Unable to download f4m'],
}, { }, {
'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/', 'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
'info_dict': { 'info_dict': {
@ -168,16 +156,17 @@ class RutubeIE(RutubeBaseIE):
'chapters': 'count:4', 'chapters': 'count:4',
'categories': ['Бизнес и предпринимательство'], 'categories': ['Бизнес и предпринимательство'],
'description': 'md5:252feac1305257d8c1bab215cedde75d', 'description': 'md5:252feac1305257d8c1bab215cedde75d',
'thumbnail': 'https://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png', 'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
'duration': 782, 'duration': 782,
'age_limit': 0, 'age_limit': 0,
'uploader_id': '23491359', 'uploader_id': '23491359',
'timestamp': 1677153329, 'timestamp': 1677153329,
'view_count': int, 'view_count': int,
'upload_date': '20230223', 'upload_date': '20230223',
'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании #1', 'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
'uploader': 'Стас Быков', 'uploader': 'Стас Быков',
}, },
'expected_warnings': ['Unable to download f4m'],
}, { }, {
'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/', 'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/',
'info_dict': { 'info_dict': {
@ -185,7 +174,7 @@ class RutubeIE(RutubeBaseIE):
'ext': 'mp4', 'ext': 'mp4',
'categories': ['Телепередачи'], 'categories': ['Телепередачи'],
'description': '', 'description': '',
'thumbnail': 'https://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg', 'thumbnail': 'http://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
'live_status': 'is_live', 'live_status': 'is_live',
'age_limit': 0, 'age_limit': 0,
'uploader_id': '23460655', 'uploader_id': '23460655',
@ -195,24 +184,6 @@ class RutubeIE(RutubeBaseIE):
'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', 'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'uploader': 'Первый канал', 'uploader': 'Первый канал',
}, },
}, {
'url': 'https://rutube.ru/play/embed/03a9cb54bac3376af4c5cb0f18444e01/',
'info_dict': {
'id': '03a9cb54bac3376af4c5cb0f18444e01',
'ext': 'mp4',
'age_limit': 0,
'description': '',
'title': 'Церемония начала торгов акциями ПАО «ЕвроТранс»',
'chapters': [],
'upload_date': '20240829',
'duration': 293,
'uploader': 'MOEX - Московская биржа',
'timestamp': 1724946628,
'thumbnail': 'https://pic.rutubelist.ru/video/2e/24/2e241fddb459baf0fa54acfca44874f4.jpg',
'view_count': int,
'uploader_id': '38420507',
'categories': ['Интервью'],
},
}, { }, {
'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/', 'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/',
'only_matching': True, 'only_matching': True,
@ -221,46 +192,40 @@ class RutubeIE(RutubeBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
@classmethod
def suitable(cls, url):
return False if RutubePlaylistIE.suitable(url) else super().suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
query = parse_qs(url) query = parse_qs(url)
info = self._download_and_extract_info(video_id, query) info = self._download_and_extract_info(video_id, query)
formats, subtitles = self._download_and_extract_formats_and_subtitles(video_id, query) info['formats'] = self._download_and_extract_formats(video_id, query)
return { return info
**info,
'formats': formats,
'subtitles': subtitles,
}
class RutubeEmbedIE(RutubeBaseIE): class RutubeEmbedIE(RutubeBaseIE):
IE_NAME = 'rutube:embed' IE_NAME = 'rutube:embed'
IE_DESC = 'Rutube embedded videos' IE_DESC = 'Rutube embedded videos'
_VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)(?:[?#/]|$)' _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
'info_dict': { 'info_dict': {
'id': 'a10e53b86e8f349080f718582ce4c661', 'id': 'a10e53b86e8f349080f718582ce4c661',
'ext': 'mp4', 'ext': 'mp4',
'timestamp': 1387830582, 'timestamp': 1387830582,
'upload_date': '20131223', 'upload_date': '20131223',
'uploader_id': '297833', 'uploader_id': '297833',
'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
'uploader': 'subziro89 ILya', 'uploader': 'subziro89 ILya',
'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89', 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
'age_limit': 0,
'duration': 1395,
'chapters': [],
'description': 'md5:a5acea57bbc3ccdc3cacd1f11a014b5b',
'view_count': int,
'thumbnail': 'https://pic.rutubelist.ru/video/d3/03/d3031f4670a6e6170d88fb3607948418.jpg',
'categories': ['Сериалы'],
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}, { }, {
'url': 'https://rutube.ru/play/embed/8083783', 'url': 'http://rutube.ru/play/embed/8083783',
'only_matching': True, 'only_matching': True,
}, { }, {
# private video # private video
@ -275,12 +240,11 @@ class RutubeEmbedIE(RutubeBaseIE):
query = parse_qs(url) query = parse_qs(url)
options = self._download_api_options(embed_id, query) options = self._download_api_options(embed_id, query)
video_id = options['effective_video'] video_id = options['effective_video']
formats, subtitles = self._extract_formats_and_subtitles(options, video_id) formats = self._extract_formats(options, video_id)
info = self._download_and_extract_info(video_id, query) info = self._download_and_extract_info(video_id, query)
info.update({ info.update({
'extractor_key': 'Rutube', 'extractor_key': 'Rutube',
'formats': formats, 'formats': formats,
'subtitles': subtitles,
}) })
return info return info
@ -331,14 +295,14 @@ class RutubeTagsIE(RutubePlaylistBaseIE):
IE_DESC = 'Rutube tags' IE_DESC = 'Rutube tags'
_VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)' _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://rutube.ru/tags/video/1800/', 'url': 'http://rutube.ru/tags/video/1800/',
'info_dict': { 'info_dict': {
'id': '1800', 'id': '1800',
}, },
'playlist_mincount': 68, 'playlist_mincount': 68,
}] }]
_PAGE_TEMPLATE = 'https://rutube.ru/api/tags/video/%s/?page=%s&format=json' _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
class RutubeMovieIE(RutubePlaylistBaseIE): class RutubeMovieIE(RutubePlaylistBaseIE):
@ -346,8 +310,8 @@ class RutubeMovieIE(RutubePlaylistBaseIE):
IE_DESC = 'Rutube movies' IE_DESC = 'Rutube movies'
_VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)' _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
_MOVIE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/?format=json' _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
_PAGE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
def _real_extract(self, url): def _real_extract(self, url):
movie_id = self._match_id(url) movie_id = self._match_id(url)
@ -363,82 +327,62 @@ class RutubePersonIE(RutubePlaylistBaseIE):
IE_DESC = 'Rutube person videos' IE_DESC = 'Rutube person videos'
_VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)' _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://rutube.ru/video/person/313878/', 'url': 'http://rutube.ru/video/person/313878/',
'info_dict': { 'info_dict': {
'id': '313878', 'id': '313878',
}, },
'playlist_mincount': 36, 'playlist_mincount': 37,
}] }]
_PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json' _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
class RutubePlaylistIE(RutubePlaylistBaseIE): class RutubePlaylistIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:playlist' IE_NAME = 'rutube:playlist'
IE_DESC = 'Rutube playlists' IE_DESC = 'Rutube playlists'
_VALID_URL = r'https?://rutube\.ru/plst/(?P<id>\d+)' _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://rutube.ru/plst/308547/', 'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
'info_dict': { 'info_dict': {
'id': '308547', 'id': '3097',
}, },
'playlist_mincount': 22, 'playlist_count': 27,
}, {
'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
'only_matching': True,
}] }]
_PAGE_TEMPLATE = 'https://rutube.ru/api/playlist/custom/%s/videos?page=%s&format=json'
_PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
@classmethod
def suitable(cls, url):
from ..utils import int_or_none, parse_qs
if not super().suitable(url):
return False
params = parse_qs(url)
return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
def _next_page_url(self, page_num, playlist_id, item_kind):
return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
def _real_extract(self, url):
qs = parse_qs(url)
playlist_kind = qs['pl_type'][0]
playlist_id = qs['pl_id'][0]
return self._extract_playlist(playlist_id, item_kind=playlist_kind)
class RutubeChannelIE(RutubePlaylistBaseIE): class RutubeChannelIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:channel' IE_NAME = 'rutube:channel'
IE_DESC = 'Rutube channel' IE_DESC = 'Rutube channel'
_VALID_URL = r'https?://rutube\.ru/(?:channel/(?P<id>\d+)|u/(?P<slug>\w+))(?:/(?P<section>videos|shorts|playlists))?' _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
_TESTS = [{ _TESTS = [{
'url': 'https://rutube.ru/channel/639184/videos/', 'url': 'https://rutube.ru/channel/639184/videos/',
'info_dict': { 'info_dict': {
'id': '639184_videos', 'id': '639184',
}, },
'playlist_mincount': 129, 'playlist_mincount': 133,
}, {
'url': 'https://rutube.ru/channel/25902603/shorts/',
'info_dict': {
'id': '25902603_shorts',
},
'playlist_mincount': 277,
}, {
'url': 'https://rutube.ru/channel/25902603/',
'info_dict': {
'id': '25902603',
},
'playlist_mincount': 406,
}, {
'url': 'https://rutube.ru/u/rutube/videos/',
'info_dict': {
'id': '23704195_videos',
},
'playlist_mincount': 113,
}] }]
_PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json&origin__type=%s' _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
def _next_page_url(self, page_num, playlist_id, section):
origin_type = {
'videos': 'rtb,rst,ifrm,rspa',
'shorts': 'rshorts',
None: '',
}.get(section)
return self._PAGE_TEMPLATE % (playlist_id, page_num, origin_type)
def _real_extract(self, url):
playlist_id, slug, section = self._match_valid_url(url).group('id', 'slug', 'section')
if section == 'playlists':
raise UnsupportedError(url)
if slug:
webpage = self._download_webpage(url, slug)
redux_state = self._search_json(
r'window\.reduxState\s*=', webpage, 'redux state', slug, transform_source=js_to_json)
playlist_id = traverse_obj(redux_state, (
'api', 'queries', lambda k, _: k.startswith('channelIdBySlug'),
'data', 'channel_id', {int}, {str_or_none}, any))
playlist = self._extract_playlist(playlist_id, section=section)
if section:
playlist['id'] = f'{playlist_id}_{section}'
return playlist

View File

@ -2,16 +2,13 @@ import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
filter_dict,
float_or_none, float_or_none,
int_or_none, int_or_none,
parse_qs,
str_or_none, str_or_none,
try_get, try_get,
unified_timestamp, unified_timestamp,
url_or_none, url_or_none,
) )
from ..utils.traversal import traverse_obj
def _extract_episode(data, episode_id=None): def _extract_episode(data, episode_id=None):
@ -61,10 +58,15 @@ def _extract_episode(data, episode_id=None):
class SpreakerIE(InfoExtractor): class SpreakerIE(InfoExtractor):
_VALID_URL = [ _VALID_URL = r'''(?x)
r'https?://api\.spreaker\.com/(?:(?:download/)?episode|v2/episodes)/(?P<id>\d+)', https?://
r'https?://(?:www\.)?spreaker\.com/episode/[^#?/]*?(?P<id>\d+)/?(?:[?#]|$)', api\.spreaker\.com/
] (?:
(?:download/)?episode|
v2/episodes
)/
(?P<id>\d+)
'''
_TESTS = [{ _TESTS = [{
'url': 'https://api.spreaker.com/episode/12534508', 'url': 'https://api.spreaker.com/episode/12534508',
'info_dict': { 'info_dict': {
@ -81,9 +83,7 @@ class SpreakerIE(InfoExtractor):
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
'comment_count': int, 'comment_count': int,
'series': 'Success With Music | SWM', 'series': 'Success With Music (SWM)',
'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/777ce4f96b71b0e1b7c09a5e625210e3.jpg',
'creators': ['SWM'],
}, },
}, { }, {
'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3', 'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3',
@ -91,75 +91,52 @@ class SpreakerIE(InfoExtractor):
}, { }, {
'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments', 'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
'only_matching': True, 'only_matching': True,
}, {
'note': 'episode',
'url': 'https://www.spreaker.com/episode/grunge-music-origins-the-raw-sound-that-defined-a-generation--60269615',
'info_dict': {
'id': '60269615',
'display_id': 'grunge-music-origins-the-raw-sound-that-',
'ext': 'mp3',
'title': 'Grunge Music Origins - The Raw Sound that Defined a Generation',
'description': str,
'timestamp': 1717468905,
'upload_date': '20240604',
'uploader': 'Katie Brown 2',
'uploader_id': '17733249',
'duration': 818.83,
'view_count': int,
'like_count': int,
'comment_count': int,
'series': '90s Grunge',
'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/bb0d4178f7cf57cc8786dedbd9c5d969.jpg',
'creators': ['Katie Brown 2'],
},
}, {
'url': 'https://www.spreaker.com/episode/60269615',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
episode_id = self._match_id(url) episode_id = self._match_id(url)
data = self._download_json( data = self._download_json(
f'https://api.spreaker.com/v2/episodes/{episode_id}', episode_id, f'https://api.spreaker.com/v2/episodes/{episode_id}',
query=traverse_obj(parse_qs(url), {'key': ('key', 0)}))['response']['episode'] episode_id)['response']['episode']
return _extract_episode(data, episode_id) return _extract_episode(data, episode_id)
class SpreakerPageIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
episode_id = self._search_regex(
(r'data-episode_id=["\'](?P<id>\d+)',
r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
return self.url_result(
f'https://api.spreaker.com/episode/{episode_id}',
ie=SpreakerIE.ie_key(), video_id=episode_id)
class SpreakerShowIE(InfoExtractor): class SpreakerShowIE(InfoExtractor):
_VALID_URL = [ _VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
r'https?://api\.spreaker\.com/show/(?P<id>\d+)',
r'https?://(?:www\.)?spreaker\.com/podcast/[\w-]+--(?P<id>[\d]+)',
r'https?://(?:www\.)?spreaker\.com/show/(?P<id>\d+)/episodes/feed',
]
_TESTS = [{ _TESTS = [{
'url': 'https://api.spreaker.com/show/4652058', 'url': 'https://api.spreaker.com/show/4652058',
'info_dict': { 'info_dict': {
'id': '4652058', 'id': '4652058',
}, },
'playlist_mincount': 118, 'playlist_mincount': 118,
}, {
'url': 'https://www.spreaker.com/podcast/health-wealth--5918323',
'info_dict': {
'id': '5918323',
},
'playlist_mincount': 60,
}, {
'url': 'https://www.spreaker.com/show/5887186/episodes/feed',
'info_dict': {
'id': '5887186',
},
'playlist_mincount': 290,
}] }]
def _entries(self, show_id, key=None): def _entries(self, show_id):
for page_num in itertools.count(1): for page_num in itertools.count(1):
episodes = self._download_json( episodes = self._download_json(
f'https://api.spreaker.com/show/{show_id}/episodes', f'https://api.spreaker.com/show/{show_id}/episodes',
show_id, note=f'Downloading JSON page {page_num}', query=filter_dict({ show_id, note=f'Downloading JSON page {page_num}', query={
'page': page_num, 'page': page_num,
'max_per_page': 100, 'max_per_page': 100,
'key': key, })
}))
pager = try_get(episodes, lambda x: x['response']['pager'], dict) pager = try_get(episodes, lambda x: x['response']['pager'], dict)
if not pager: if not pager:
break break
@ -175,5 +152,21 @@ class SpreakerShowIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
show_id = self._match_id(url) show_id = self._match_id(url)
key = traverse_obj(parse_qs(url), ('key', 0)) return self.playlist_result(self._entries(show_id), playlist_id=show_id)
return self.playlist_result(self._entries(show_id, key), playlist_id=show_id)
class SpreakerShowPageIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.spreaker.com/show/success-with-music',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
show_id = self._search_regex(
r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
return self.url_result(
f'https://api.spreaker.com/show/{show_id}',
ie=SpreakerShowIE.ie_key(), video_id=show_id)