mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2026-05-02 21:45:59 +00:00
Compare commits
3 Commits
404bd889d0
...
374ea049f5
| Author | SHA1 | Date | |
|---|---|---|---|
|
374ea049f5 | ||
|
|
6f4c1bb593 | ||
|
|
c22660aed5 |
@ -58,13 +58,7 @@ from .adn import (
|
||||
ADNSeasonIE,
|
||||
)
|
||||
from .adobeconnect import AdobeConnectIE
|
||||
from .adobetv import (
|
||||
AdobeTVChannelIE,
|
||||
AdobeTVEmbedIE,
|
||||
AdobeTVIE,
|
||||
AdobeTVShowIE,
|
||||
AdobeTVVideoIE,
|
||||
)
|
||||
from .adobetv import AdobeTVVideoIE
|
||||
from .adultswim import AdultSwimIE
|
||||
from .aenetworks import (
|
||||
AENetworksCollectionIE,
|
||||
@ -152,7 +146,6 @@ from .ard import (
|
||||
ARDBetaMediathekIE,
|
||||
ARDMediathekCollectionIE,
|
||||
)
|
||||
from .arkena import ArkenaIE
|
||||
from .arnes import ArnesIE
|
||||
from .art19 import (
|
||||
Art19IE,
|
||||
@ -1548,7 +1541,6 @@ from .pixivsketch import (
|
||||
PixivSketchIE,
|
||||
PixivSketchUserIE,
|
||||
)
|
||||
from .pladform import PladformIE
|
||||
from .planetmarathi import PlanetMarathiIE
|
||||
from .platzi import (
|
||||
PlatziCourseIE,
|
||||
@ -2313,10 +2305,6 @@ from .varzesh3 import Varzesh3IE
|
||||
from .vbox7 import Vbox7IE
|
||||
from .veo import VeoIE
|
||||
from .vesti import VestiIE
|
||||
from .vevo import (
|
||||
VevoIE,
|
||||
VevoPlaylistIE,
|
||||
)
|
||||
from .vgtv import (
|
||||
VGTVIE,
|
||||
BTArticleIE,
|
||||
|
||||
@ -1,297 +1,100 @@
|
||||
import functools
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ISO639Utils,
|
||||
OnDemandPagedList,
|
||||
clean_html,
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
parse_duration,
|
||||
str_or_none,
|
||||
str_to_int,
|
||||
unified_strdate,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class AdobeTVBaseIE(InfoExtractor):
|
||||
def _call_api(self, path, video_id, query, note=None):
|
||||
return self._download_json(
|
||||
'http://tv.adobe.com/api/v4/' + path,
|
||||
video_id, note, query=query)['data']
|
||||
|
||||
def _parse_subtitles(self, video_data, url_key):
|
||||
subtitles = {}
|
||||
for translation in video_data.get('translations', []):
|
||||
vtt_path = translation.get(url_key)
|
||||
if not vtt_path:
|
||||
continue
|
||||
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'ext': 'vtt',
|
||||
'url': vtt_path,
|
||||
})
|
||||
return subtitles
|
||||
|
||||
def _parse_video_data(self, video_data):
|
||||
video_id = str(video_data['id'])
|
||||
title = video_data['title']
|
||||
|
||||
s3_extracted = False
|
||||
formats = []
|
||||
for source in video_data.get('videos', []):
|
||||
source_url = source.get('url')
|
||||
if not source_url:
|
||||
continue
|
||||
f = {
|
||||
'format_id': source.get('quality_level'),
|
||||
'fps': int_or_none(source.get('frame_rate')),
|
||||
'height': int_or_none(source.get('height')),
|
||||
'tbr': int_or_none(source.get('video_data_rate')),
|
||||
'width': int_or_none(source.get('width')),
|
||||
'url': source_url,
|
||||
}
|
||||
original_filename = source.get('original_filename')
|
||||
if original_filename:
|
||||
if not (f.get('height') and f.get('width')):
|
||||
mobj = re.search(r'_(\d+)x(\d+)', original_filename)
|
||||
if mobj:
|
||||
f.update({
|
||||
'height': int(mobj.group(2)),
|
||||
'width': int(mobj.group(1)),
|
||||
})
|
||||
if original_filename.startswith('s3://') and not s3_extracted:
|
||||
formats.append({
|
||||
'format_id': 'original',
|
||||
'quality': 1,
|
||||
'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'),
|
||||
})
|
||||
s3_extracted = True
|
||||
formats.append(f)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': video_data.get('description'),
|
||||
'thumbnail': video_data.get('thumbnail'),
|
||||
'upload_date': unified_strdate(video_data.get('start_date')),
|
||||
'duration': parse_duration(video_data.get('duration')),
|
||||
'view_count': str_to_int(video_data.get('playcount')),
|
||||
'formats': formats,
|
||||
'subtitles': self._parse_subtitles(video_data, 'vtt'),
|
||||
}
|
||||
|
||||
|
||||
class AdobeTVEmbedIE(AdobeTVBaseIE):
|
||||
_WORKING = False
|
||||
IE_NAME = 'adobetv:embed'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://tv.adobe.com/embed/22/4153',
|
||||
'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
|
||||
'info_dict': {
|
||||
'id': '4153',
|
||||
'ext': 'flv',
|
||||
'title': 'Creating Graphics Optimized for BlackBerry',
|
||||
'description': 'md5:eac6e8dced38bdaae51cd94447927459',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'upload_date': '20091109',
|
||||
'duration': 377,
|
||||
'view_count': int,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
video_data = self._call_api(
|
||||
'episode/' + video_id, video_id, {'disclosure': 'standard'})[0]
|
||||
return self._parse_video_data(video_data)
|
||||
|
||||
|
||||
class AdobeTVIE(AdobeTVBaseIE):
|
||||
_WORKING = False
|
||||
class AdobeTVVideoIE(InfoExtractor):
|
||||
IE_NAME = 'adobetv'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
|
||||
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
|
||||
'info_dict': {
|
||||
'id': '10981',
|
||||
'ext': 'mp4',
|
||||
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
|
||||
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'upload_date': '20110914',
|
||||
'duration': 60,
|
||||
'view_count': int,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, show_urlname, urlname = self._match_valid_url(url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
|
||||
video_data = self._call_api(
|
||||
'episode/get', urlname, {
|
||||
'disclosure': 'standard',
|
||||
'language': language,
|
||||
'show_urlname': show_urlname,
|
||||
'urlname': urlname,
|
||||
})[0]
|
||||
return self._parse_video_data(video_data)
|
||||
|
||||
|
||||
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
|
||||
_PAGE_SIZE = 25
|
||||
|
||||
def _fetch_page(self, display_id, query, page):
|
||||
page += 1
|
||||
query['page'] = page
|
||||
for element_data in self._call_api(
|
||||
self._RESOURCE, display_id, query, f'Download Page {page}'):
|
||||
yield self._process_data(element_data)
|
||||
|
||||
def _extract_playlist_entries(self, display_id, query):
|
||||
return OnDemandPagedList(functools.partial(
|
||||
self._fetch_page, display_id, query), self._PAGE_SIZE)
|
||||
|
||||
|
||||
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
|
||||
_WORKING = False
|
||||
IE_NAME = 'adobetv:show'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
|
||||
'info_dict': {
|
||||
'id': '36',
|
||||
'title': 'The Complete Picture with Julieanne Kost',
|
||||
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
|
||||
},
|
||||
'playlist_mincount': 136,
|
||||
}]
|
||||
_RESOURCE = 'episode'
|
||||
_process_data = AdobeTVBaseIE._parse_video_data
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, show_urlname = self._match_valid_url(url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
query = {
|
||||
'disclosure': 'standard',
|
||||
'language': language,
|
||||
'show_urlname': show_urlname,
|
||||
}
|
||||
|
||||
show_data = self._call_api(
|
||||
'show/get', show_urlname, query)[0]
|
||||
|
||||
return self.playlist_result(
|
||||
self._extract_playlist_entries(show_urlname, query),
|
||||
str_or_none(show_data.get('id')),
|
||||
show_data.get('show_name'),
|
||||
show_data.get('show_description'))
|
||||
|
||||
|
||||
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
|
||||
_WORKING = False
|
||||
IE_NAME = 'adobetv:channel'
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
|
||||
_TESTS = [{
|
||||
'url': 'http://tv.adobe.com/channel/development',
|
||||
'info_dict': {
|
||||
'id': 'development',
|
||||
},
|
||||
'playlist_mincount': 96,
|
||||
}]
|
||||
_RESOURCE = 'show'
|
||||
|
||||
def _process_data(self, show_data):
|
||||
return self.url_result(
|
||||
show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id')))
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, channel_urlname, category_urlname = self._match_valid_url(url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
query = {
|
||||
'channel_urlname': channel_urlname,
|
||||
'language': language,
|
||||
}
|
||||
if category_urlname:
|
||||
query['category_urlname'] = category_urlname
|
||||
|
||||
return self.playlist_result(
|
||||
self._extract_playlist_entries(channel_urlname, query),
|
||||
channel_urlname)
|
||||
|
||||
|
||||
class AdobeTVVideoIE(AdobeTVBaseIE):
|
||||
IE_NAME = 'adobetv:video'
|
||||
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+)']
|
||||
_TESTS = [{
|
||||
# From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
|
||||
'url': 'https://video.tv.adobe.com/v/2456/',
|
||||
'url': 'https://video.tv.adobe.com/v/2456',
|
||||
'md5': '43662b577c018ad707a63766462b1e87',
|
||||
'info_dict': {
|
||||
'id': '2456',
|
||||
'ext': 'mp4',
|
||||
'title': 'New experience with Acrobat DC',
|
||||
'description': 'New experience with Acrobat DC',
|
||||
'duration': 248.667,
|
||||
'duration': 248.522,
|
||||
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://video.tv.adobe.com/v/3463980/adobe-acrobat',
|
||||
'info_dict': {
|
||||
'id': '3463980',
|
||||
'ext': 'mp4',
|
||||
'title': 'Adobe Acrobat: How to Customize the Toolbar for Faster PDF Editing',
|
||||
'description': 'md5:94368ab95ae24f9c1bee0cb346e03dc3',
|
||||
'duration': 97.514,
|
||||
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# FIXME: Invalid extension
|
||||
'url': 'https://www.adobe.com/learn/acrobat/web/customize-toolbar',
|
||||
# https://video.tv.adobe.com/v/3442499
|
||||
'url': 'https://business.adobe.com/dx-fragments/summit/2025/marquees/S335/ondemand.live.html',
|
||||
'info_dict': {
|
||||
'id': '3463980',
|
||||
'ext': 'm3u8',
|
||||
'title': 'Adobe Acrobat: How to Customize the Toolbar for Faster PDF Editing',
|
||||
'description': 'md5:94368ab95ae24f9c1bee0cb346e03dc3',
|
||||
'duration': 97.557,
|
||||
'id': '3442499',
|
||||
'ext': 'mp4',
|
||||
'title': 'S335 - Beyond Personalization: Creating Intent-Based Experiences at Scale',
|
||||
'description': 'Beyond Personalization: Creating Intent-Based Experiences at Scale',
|
||||
'duration': 2906.8,
|
||||
'thumbnail': r're:https?://images-tv\.adobe\.com/.+\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_data = self._parse_json(self._search_regex(
|
||||
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
|
||||
title = video_data['title']
|
||||
video_data = self._search_json(
|
||||
r'var\s+bridge\s*=', webpage, 'bridged data', video_id)
|
||||
|
||||
formats = []
|
||||
sources = video_data.get('sources') or []
|
||||
for source in sources:
|
||||
source_src = source.get('src')
|
||||
if not source_src:
|
||||
continue
|
||||
formats.append({
|
||||
'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000),
|
||||
'format_id': join_nonempty(source.get('format'), source.get('label')),
|
||||
'height': int_or_none(source.get('height') or None),
|
||||
'tbr': int_or_none(source.get('bitrate') or None),
|
||||
'width': int_or_none(source.get('width') or None),
|
||||
'url': source_src,
|
||||
})
|
||||
for source in traverse_obj(video_data, (
|
||||
'sources', lambda _, v: v['format'] != 'playlist' and url_or_none(v['src']),
|
||||
)):
|
||||
source_url = self._proto_relative_url(source['src'])
|
||||
if determine_ext(source_url) == 'm3u8':
|
||||
fmts = self._extract_m3u8_formats(
|
||||
source_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
|
||||
else:
|
||||
fmts = [{'url': source_url}]
|
||||
|
||||
# For both metadata and downloaded files the duration varies among
|
||||
# formats. I just pick the max one
|
||||
duration = max(filter(None, [
|
||||
float_or_none(source.get('duration'), scale=1000)
|
||||
for source in sources]))
|
||||
for fmt in fmts:
|
||||
fmt.update(traverse_obj(source, {
|
||||
'duration': ('duration', {float_or_none(scale=1000)}),
|
||||
'filesize': ('kilobytes', {float_or_none(invscale=1000)}),
|
||||
'format_id': (('format', 'label'), {str}, all, {lambda x: join_nonempty(*x)}),
|
||||
'height': ('height', {int_or_none}),
|
||||
'tbr': ('bitrate', {int_or_none}),
|
||||
'width': ('width', {int_or_none}),
|
||||
}))
|
||||
formats.extend(fmts)
|
||||
|
||||
subtitles = {}
|
||||
for translation in traverse_obj(video_data, (
|
||||
'translations', lambda _, v: url_or_none(v['vttPath']),
|
||||
)):
|
||||
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation.get('language_medium')) or 'und'
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'ext': 'vtt',
|
||||
'url': self._proto_relative_url(translation['vttPath']),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': video_data.get('description'),
|
||||
'thumbnail': video_data.get('video', {}).get('poster'),
|
||||
'duration': duration,
|
||||
'subtitles': self._parse_subtitles(video_data, 'vttPath'),
|
||||
'subtitles': subtitles,
|
||||
**traverse_obj(video_data, {
|
||||
'title': ('title', {clean_html}),
|
||||
'description': ('description', {clean_html}, filter),
|
||||
'thumbnail': ('video', 'poster', {self._proto_relative_url}, {url_or_none}),
|
||||
}),
|
||||
}
|
||||
|
||||
@ -1,150 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
parse_qs,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class ArkenaIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
video\.(?:arkena|qbrick)\.com/play2/embed/player\?|
|
||||
play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
|
||||
)
|
||||
'''
|
||||
# See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1']
|
||||
_TESTS = [{
|
||||
'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
|
||||
'md5': '97f117754e5f3c020f5f26da4a44ebaf',
|
||||
'info_dict': {
|
||||
'id': 'd8ab4607-00090107-aab86310',
|
||||
'ext': 'mp4',
|
||||
'title': 'EM_HT20_117_roslund_v2.mp4',
|
||||
'timestamp': 1608285912,
|
||||
'upload_date': '20201218',
|
||||
'duration': 1429.162667,
|
||||
'subtitles': {
|
||||
'sv': 'count:3',
|
||||
},
|
||||
},
|
||||
}, {
|
||||
'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
video_id = mobj.group('id')
|
||||
account_id = mobj.group('account_id')
|
||||
|
||||
# Handle http://video.arkena.com/play2/embed/player URL
|
||||
if not video_id:
|
||||
qs = parse_qs(url)
|
||||
video_id = qs.get('mediaId', [None])[0]
|
||||
account_id = qs.get('accountId', [None])[0]
|
||||
if not video_id or not account_id:
|
||||
raise ExtractorError('Invalid URL', expected=True)
|
||||
|
||||
media = self._download_json(
|
||||
f'https://video.qbrick.com/api/v1/public/accounts/{account_id}/medias/{video_id}',
|
||||
video_id, query={
|
||||
# https://video.qbrick.com/docs/api/examples/library-api.html
|
||||
'fields': 'asset/resources/*/renditions/*(height,id,language,links/*(href,mimeType),type,size,videos/*(audios/*(codec,sampleRate),bitrate,codec,duration,height,width),width),created,metadata/*(title,description),tags',
|
||||
})
|
||||
metadata = media.get('metadata') or {}
|
||||
title = metadata['title']
|
||||
|
||||
duration = None
|
||||
formats = []
|
||||
thumbnails = []
|
||||
subtitles = {}
|
||||
for resource in media['asset']['resources']:
|
||||
for rendition in (resource.get('renditions') or []):
|
||||
rendition_type = rendition.get('type')
|
||||
for i, link in enumerate(rendition.get('links') or []):
|
||||
href = link.get('href')
|
||||
if not href:
|
||||
continue
|
||||
if rendition_type == 'image':
|
||||
thumbnails.append({
|
||||
'filesize': int_or_none(rendition.get('size')),
|
||||
'height': int_or_none(rendition.get('height')),
|
||||
'id': rendition.get('id'),
|
||||
'url': href,
|
||||
'width': int_or_none(rendition.get('width')),
|
||||
})
|
||||
elif rendition_type == 'subtitle':
|
||||
subtitles.setdefault(rendition.get('language') or 'en', []).append({
|
||||
'url': href,
|
||||
})
|
||||
elif rendition_type == 'video':
|
||||
f = {
|
||||
'filesize': int_or_none(rendition.get('size')),
|
||||
'format_id': rendition.get('id'),
|
||||
'url': href,
|
||||
}
|
||||
video = try_get(rendition, lambda x: x['videos'][i], dict)
|
||||
if video:
|
||||
if not duration:
|
||||
duration = float_or_none(video.get('duration'))
|
||||
f.update({
|
||||
'height': int_or_none(video.get('height')),
|
||||
'tbr': int_or_none(video.get('bitrate'), 1000),
|
||||
'vcodec': video.get('codec'),
|
||||
'width': int_or_none(video.get('width')),
|
||||
})
|
||||
audio = try_get(video, lambda x: x['audios'][0], dict)
|
||||
if audio:
|
||||
f.update({
|
||||
'acodec': audio.get('codec'),
|
||||
'asr': int_or_none(audio.get('sampleRate')),
|
||||
})
|
||||
formats.append(f)
|
||||
elif rendition_type == 'index':
|
||||
mime_type = link.get('mimeType')
|
||||
if mime_type == 'application/smil+xml':
|
||||
formats.extend(self._extract_smil_formats(
|
||||
href, video_id, fatal=False))
|
||||
elif mime_type == 'application/x-mpegURL':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
href, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif mime_type == 'application/hds+xml':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
href, video_id, f4m_id='hds', fatal=False))
|
||||
elif mime_type == 'application/dash+xml':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
href, video_id, mpd_id='dash', fatal=False))
|
||||
elif mime_type == 'application/vnd.ms-sstr+xml':
|
||||
formats.extend(self._extract_ism_formats(
|
||||
href, video_id, ism_id='mss', fatal=False))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': metadata.get('description'),
|
||||
'timestamp': parse_iso8601(media.get('created')),
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
'duration': duration,
|
||||
'tags': media.get('tags'),
|
||||
'formats': formats,
|
||||
}
|
||||
@ -3107,7 +3107,6 @@ class InfoExtractor:
|
||||
else:
|
||||
# $Number*$ or $Time$ in media template with S list available
|
||||
# Example $Number*$: http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg
|
||||
# Example $Time$: https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411
|
||||
representation_ms_info['fragments'] = []
|
||||
segment_time = 0
|
||||
segment_d = None
|
||||
|
||||
@ -171,17 +171,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'view_count': int,
|
||||
},
|
||||
'skip': 'video gone',
|
||||
}, {
|
||||
# Vevo video
|
||||
'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
|
||||
'info_dict': {
|
||||
'title': 'Roar (Official)',
|
||||
'id': 'USUV71301934',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'Katy Perry',
|
||||
'upload_date': '20130905',
|
||||
},
|
||||
'skip': 'Invalid URL',
|
||||
}, {
|
||||
# age-restricted video
|
||||
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
|
||||
|
||||
@ -90,10 +90,6 @@ class DisneyIE(InfoExtractor):
|
||||
webpage, 'embed data'), video_id)
|
||||
video_data = page_data['video']
|
||||
|
||||
for external in video_data.get('externals', []):
|
||||
if external.get('source') == 'vevo':
|
||||
return self.url_result('vevo:' + external['data_id'], 'Vevo')
|
||||
|
||||
video_id = video_data['id']
|
||||
title = video_data['title']
|
||||
|
||||
|
||||
@ -1,8 +1,8 @@
|
||||
from .arkena import ArkenaIE
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class LcpPlayIE(ArkenaIE): # XXX: Do not subclass from concrete IE
|
||||
class LcpPlayIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'https?://play\.lcp\.fr/embed/(?P<id>[^/]+)/(?P<account_id>[^/]+)/[^/]+/[^/]+'
|
||||
_TESTS = [{
|
||||
'url': 'http://play.lcp.fr/embed/327336/131064/darkmatter/0',
|
||||
@ -21,24 +21,9 @@ class LcpPlayIE(ArkenaIE): # XXX: Do not subclass from concrete IE
|
||||
|
||||
|
||||
class LcpIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
_VALID_URL = r'https?://(?:www\.)?lcp\.fr/(?:[^/]+/)*(?P<id>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
# arkena embed
|
||||
'url': 'http://www.lcp.fr/la-politique-en-video/schwartzenberg-prg-preconise-francois-hollande-de-participer-une-primaire',
|
||||
'md5': 'b8bd9298542929c06c1c15788b1f277a',
|
||||
'info_dict': {
|
||||
'id': 'd56d03e9',
|
||||
'ext': 'mp4',
|
||||
'title': 'Schwartzenberg (PRG) préconise à François Hollande de participer à une primaire à gauche',
|
||||
'description': 'md5:96ad55009548da9dea19f4120c6c16a8',
|
||||
'timestamp': 1456488895,
|
||||
'upload_date': '20160226',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# dailymotion live stream
|
||||
'url': 'http://www.lcp.fr/le-direct',
|
||||
'info_dict': {
|
||||
|
||||
@ -111,12 +111,8 @@ class MySpaceIE(InfoExtractor):
|
||||
search_data('stream-url'), search_data('hls-stream-url'),
|
||||
search_data('http-stream-url'))
|
||||
if not formats:
|
||||
vevo_id = search_data('vevo-id')
|
||||
youtube_id = search_data('youtube-id')
|
||||
if vevo_id:
|
||||
self.to_screen(f'Vevo video detected: {vevo_id}')
|
||||
return self.url_result(f'vevo:{vevo_id}', ie='Vevo')
|
||||
elif youtube_id:
|
||||
if youtube_id:
|
||||
self.to_screen(f'Youtube video detected: {youtube_id}')
|
||||
return self.url_result(youtube_id, ie='Youtube')
|
||||
else:
|
||||
|
||||
@ -873,39 +873,67 @@ class NiconicoLiveIE(NiconicoBaseIE):
|
||||
IE_DESC = 'ニコニコ生放送'
|
||||
_VALID_URL = r'https?://(?:sp\.)?live2?\.nicovideo\.jp/(?:watch|gate)/(?P<id>lv\d+)'
|
||||
_TESTS = [{
|
||||
'note': 'this test case includes invisible characters for title, pasting them as-is',
|
||||
'url': 'https://live.nicovideo.jp/watch/lv339533123',
|
||||
'url': 'https://live.nicovideo.jp/watch/lv329299587',
|
||||
'info_dict': {
|
||||
'id': 'lv339533123',
|
||||
'title': '激辛ペヤング食べます\u202a( ;ᯅ; )\u202c（歌枠オーディション参加中）',
|
||||
'view_count': 1526,
|
||||
'comment_count': 1772,
|
||||
'description': '初めましてもかって言います❕\nのんびり自由に適当に暮らしてます',
|
||||
'uploader': 'もか',
|
||||
'channel': 'ゲストさんのコミュニティ',
|
||||
'channel_id': 'co5776900',
|
||||
'channel_url': 'https://com.nicovideo.jp/community/co5776900',
|
||||
'timestamp': 1670677328,
|
||||
'is_live': True,
|
||||
'id': 'lv329299587',
|
||||
'ext': 'mp4',
|
||||
'title': str,
|
||||
'channel': 'ニコニコエンタメチャンネル',
|
||||
'channel_id': 'ch2640322',
|
||||
'channel_url': 'https://ch.nicovideo.jp/channel/ch2640322',
|
||||
'comment_count': int,
|
||||
'description': 'md5:281edd7f00309e99ec46a87fb16d7033',
|
||||
'live_status': 'is_live',
|
||||
'thumbnail': r're:https?://.+',
|
||||
'timestamp': 1608803400,
|
||||
'upload_date': '20201224',
|
||||
'uploader': '株式会社ドワンゴ',
|
||||
'view_count': int,
|
||||
},
|
||||
'skip': 'livestream',
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
'url': 'https://live2.nicovideo.jp/watch/lv339533123',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://sp.live.nicovideo.jp/watch/lv339533123',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://sp.live2.nicovideo.jp/watch/lv339533123',
|
||||
'only_matching': True,
|
||||
'url': 'https://live.nicovideo.jp/watch/lv331050399',
|
||||
'info_dict': {
|
||||
'id': 'lv331050399',
|
||||
'ext': 'mp4',
|
||||
'title': str,
|
||||
'age_limit': 18,
|
||||
'channel': 'みんなのおもちゃ REBOOT',
|
||||
'channel_id': 'ch2642088',
|
||||
'channel_url': 'https://ch.nicovideo.jp/channel/ch2642088',
|
||||
'comment_count': int,
|
||||
'description': 'md5:8d0bb5beaca73b911725478a1e7c7b91',
|
||||
'live_status': 'is_live',
|
||||
'thumbnail': r're:https?://.+',
|
||||
'timestamp': 1617029400,
|
||||
'upload_date': '20210329',
|
||||
'uploader': '株式会社ドワンゴ',
|
||||
'view_count': int,
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id, expected_status=404)
|
||||
webpage, urlh = self._download_webpage_handle(url, video_id, expected_status=404)
|
||||
if err_msg := traverse_obj(webpage, ({find_element(cls='message')}, {clean_html})):
|
||||
raise ExtractorError(err_msg, expected=True)
|
||||
|
||||
age_limit = 18 if 'age_auth' in urlh.url else None
|
||||
if age_limit:
|
||||
if not self.is_logged_in:
|
||||
self.raise_login_required('Login is required to access age-restricted content')
|
||||
|
||||
my = self._download_webpage('https://www.nicovideo.jp/my', None, 'Checking age verification')
|
||||
if traverse_obj(my, (
|
||||
{find_element(id='js-initial-userpage-data', html=True)}, {extract_attributes},
|
||||
'data-environment', {json.loads}, 'allowSensitiveContents', {bool},
|
||||
)):
|
||||
self._set_cookie('.nicovideo.jp', 'age_auth', '1')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
else:
|
||||
raise ExtractorError('Sensitive content setting must be enabled', expected=True)
|
||||
|
||||
embedded_data = traverse_obj(webpage, (
|
||||
{find_element(tag='script', id='embedded-data', html=True)},
|
||||
{extract_attributes}, 'data-props', {json.loads}))
|
||||
@ -1008,6 +1036,7 @@ class NiconicoLiveIE(NiconicoBaseIE):
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'age_limit': age_limit,
|
||||
'downloader_options': {
|
||||
'max_quality': traverse_obj(embedded_data, ('program', 'stream', 'maxQuality', {str})) or 'normal',
|
||||
'ws': ws,
|
||||
|
||||
@ -352,14 +352,6 @@ class OdnoklassnikiIE(InfoExtractor):
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
# pladform
|
||||
if provider == 'OPEN_GRAPH':
|
||||
info.update({
|
||||
'_type': 'url_transparent',
|
||||
'url': movie['contentId'],
|
||||
})
|
||||
return info
|
||||
|
||||
if provider == 'USER_YOUTUBE':
|
||||
info.update({
|
||||
'_type': 'url_transparent',
|
||||
|
||||
@ -1,135 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
parse_qs,
|
||||
qualities,
|
||||
xpath_text,
|
||||
)
|
||||
|
||||
|
||||
class PladformIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:
|
||||
out\.pladform\.ru/player|
|
||||
static\.pladform\.ru/player\.swf
|
||||
)
|
||||
\?.*\bvideoid=|
|
||||
video\.pladform\.ru/catalog/video/videoid/
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1']
|
||||
_TESTS = [{
|
||||
'url': 'http://out.pladform.ru/player?pl=18079&type=html5&videoid=100231282',
|
||||
'info_dict': {
|
||||
'id': '6216d548e755edae6e8280667d774791',
|
||||
'ext': 'mp4',
|
||||
'timestamp': 1406117012,
|
||||
'title': 'Гарик Мартиросян и Гарик Харламов - Кастинг на концерт ко Дню милиции',
|
||||
'age_limit': 0,
|
||||
'upload_date': '20140723',
|
||||
'thumbnail': str,
|
||||
'view_count': int,
|
||||
'description': str,
|
||||
'uploader_id': '12082',
|
||||
'uploader': 'Comedy Club',
|
||||
'duration': 367,
|
||||
},
|
||||
'expected_warnings': ['HTTP Error 404: Not Found'],
|
||||
}, {
|
||||
'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
|
||||
'md5': '53362fac3a27352da20fa2803cc5cd6f',
|
||||
'info_dict': {
|
||||
'id': '3777899',
|
||||
'ext': 'mp4',
|
||||
'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
|
||||
'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 3190,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
qs = parse_qs(url)
|
||||
pl = qs.get('pl', ['1'])[0]
|
||||
|
||||
video = self._download_xml(
|
||||
'http://out.pladform.ru/getVideo', video_id, query={
|
||||
'pl': pl,
|
||||
'videoid': video_id,
|
||||
}, fatal=False)
|
||||
|
||||
def fail(text):
|
||||
raise ExtractorError(
|
||||
f'{self.IE_NAME} returned error: {text}',
|
||||
expected=True)
|
||||
|
||||
if not video:
|
||||
target_url = self._request_webpage(url, video_id, note='Resolving final URL').url
|
||||
if target_url == url:
|
||||
raise ExtractorError('Can\'t parse page')
|
||||
return self.url_result(target_url)
|
||||
|
||||
if video.tag == 'error':
|
||||
fail(video.text)
|
||||
|
||||
quality = qualities(('ld', 'sd', 'hd'))
|
||||
|
||||
formats = []
|
||||
for src in video.findall('./src'):
|
||||
if src is None:
|
||||
continue
|
||||
format_url = src.text
|
||||
if not format_url:
|
||||
continue
|
||||
if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'url': src.text,
|
||||
'format_id': src.get('quality'),
|
||||
'quality': quality(src.get('quality')),
|
||||
})
|
||||
|
||||
if not formats:
|
||||
error = xpath_text(video, './cap', 'error', default=None)
|
||||
if error:
|
||||
fail(error)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
f'http://video.pladform.ru/catalog/video/videoid/{video_id}',
|
||||
video_id)
|
||||
|
||||
title = self._og_search_title(webpage, fatal=False) or xpath_text(
|
||||
video, './/title', 'title', fatal=True)
|
||||
description = self._search_regex(
|
||||
r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
|
||||
thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
|
||||
video, './/cover', 'cover')
|
||||
|
||||
duration = int_or_none(xpath_text(video, './/time', 'duration'))
|
||||
age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'age_limit': age_limit,
|
||||
'formats': formats,
|
||||
}
|
||||
@ -1,352 +0,0 @@
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
parse_qs,
|
||||
)
|
||||
|
||||
|
||||
class VevoBaseIE(InfoExtractor):
|
||||
def _extract_json(self, webpage, video_id):
|
||||
return self._parse_json(
|
||||
self._search_regex(
|
||||
r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>',
|
||||
webpage, 'initial store'),
|
||||
video_id)
|
||||
|
||||
|
||||
class VevoIE(VevoBaseIE):
|
||||
"""
|
||||
Accepts urls from vevo.com or in the format 'vevo:{id}'
|
||||
(currently used by MTVIE and MySpaceIE)
|
||||
"""
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:https?://(?:www\.)?vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?|
|
||||
https?://cache\.vevo\.com/m/html/embed\.html\?video=|
|
||||
https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
|
||||
https?://embed\.vevo\.com/.*?[?&]isrc=|
|
||||
https?://tv\.vevo\.com/watch/artist/(?:[^/]+)/|
|
||||
vevo:)
|
||||
(?P<id>[^&?#]+)'''
|
||||
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1']
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
|
||||
'md5': '95ee28ee45e70130e3ab02b0f579ae23',
|
||||
'info_dict': {
|
||||
'id': 'GB1101300280',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hurts - Somebody to Die For',
|
||||
'timestamp': 1372057200,
|
||||
'upload_date': '20130624',
|
||||
'uploader': 'Hurts',
|
||||
'track': 'Somebody to Die For',
|
||||
'artist': 'Hurts',
|
||||
'genre': 'Pop',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'v3 SMIL format',
|
||||
'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
|
||||
'md5': 'f6ab09b034f8c22969020b042e5ac7fc',
|
||||
'info_dict': {
|
||||
'id': 'USUV71302923',
|
||||
'ext': 'mp4',
|
||||
'title': 'Cassadee Pope - I Wish I Could Break Your Heart',
|
||||
'timestamp': 1392796919,
|
||||
'upload_date': '20140219',
|
||||
'uploader': 'Cassadee Pope',
|
||||
'track': 'I Wish I Could Break Your Heart',
|
||||
'artist': 'Cassadee Pope',
|
||||
'genre': 'Country',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'Age-limited video',
|
||||
'url': 'https://www.vevo.com/watch/justin-timberlake/tunnel-vision-explicit/USRV81300282',
|
||||
'info_dict': {
|
||||
'id': 'USRV81300282',
|
||||
'ext': 'mp4',
|
||||
'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
|
||||
'age_limit': 18,
|
||||
'timestamp': 1372888800,
|
||||
'upload_date': '20130703',
|
||||
'uploader': 'Justin Timberlake',
|
||||
'track': 'Tunnel Vision (Explicit)',
|
||||
'artist': 'Justin Timberlake',
|
||||
'genre': 'Pop',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'No video_info',
|
||||
'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000',
|
||||
'md5': '8b83cc492d72fc9cf74a02acee7dc1b0',
|
||||
'info_dict': {
|
||||
'id': 'USUV71503000',
|
||||
'ext': 'mp4',
|
||||
'title': 'K Camp ft. T.I. - Till I Die',
|
||||
'age_limit': 18,
|
||||
'timestamp': 1449468000,
|
||||
'upload_date': '20151207',
|
||||
'uploader': 'K Camp',
|
||||
'track': 'Till I Die',
|
||||
'artist': 'K Camp',
|
||||
'genre': 'Hip-Hop',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'Featured test',
|
||||
'url': 'https://www.vevo.com/watch/lemaitre/Wait/USUV71402190',
|
||||
'md5': 'd28675e5e8805035d949dc5cf161071d',
|
||||
'info_dict': {
|
||||
'id': 'USUV71402190',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lemaitre ft. LoLo - Wait',
|
||||
'age_limit': 0,
|
||||
'timestamp': 1413432000,
|
||||
'upload_date': '20141016',
|
||||
'uploader': 'Lemaitre',
|
||||
'track': 'Wait',
|
||||
'artist': 'Lemaitre',
|
||||
'genre': 'Electronic',
|
||||
},
|
||||
'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
|
||||
}, {
|
||||
'note': 'Only available via webpage',
|
||||
'url': 'http://www.vevo.com/watch/GBUV71600656',
|
||||
'md5': '67e79210613865b66a47c33baa5e37fe',
|
||||
'info_dict': {
|
||||
'id': 'GBUV71600656',
|
||||
'ext': 'mp4',
|
||||
'title': 'ABC - Viva Love',
|
||||
'age_limit': 0,
|
||||
'timestamp': 1461830400,
|
||||
'upload_date': '20160428',
|
||||
'uploader': 'ABC',
|
||||
'track': 'Viva Love',
|
||||
'artist': 'ABC',
|
||||
'genre': 'Pop',
|
||||
},
|
||||
'expected_warnings': ['Failed to download video versions info'],
|
||||
}, {
|
||||
# no genres available
|
||||
'url': 'http://www.vevo.com/watch/INS171400764',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Another case available only via the webpage; using streams/streamsV3 formats
|
||||
# Geo-restricted to Netherlands/Germany
|
||||
'url': 'http://www.vevo.com/watch/boostee/pop-corn-clip-officiel/FR1A91600909',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://embed.vevo.com/?isrc=USH5V1923499&partnerId=4d61b777-8023-4191-9ede-497ed6c24647&partnerAdCode=',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://tv.vevo.com/watch/artist/janet-jackson/US0450100550',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_VERSIONS = {
|
||||
0: 'youtube', # only in AuthenticateVideo videoVersions
|
||||
1: 'level3',
|
||||
2: 'akamai',
|
||||
3: 'level3',
|
||||
4: 'amazon',
|
||||
}
|
||||
|
||||
def _initialize_api(self, video_id):
|
||||
webpage = self._download_webpage(
|
||||
'https://accounts.vevo.com/token', None,
|
||||
note='Retrieving oauth token',
|
||||
errnote='Unable to retrieve oauth token',
|
||||
data=json.dumps({
|
||||
'client_id': 'SPupX1tvqFEopQ1YS6SS',
|
||||
'grant_type': 'urn:vevo:params:oauth:grant-type:anonymous',
|
||||
}).encode(),
|
||||
headers={
|
||||
'Content-Type': 'application/json',
|
||||
})
|
||||
|
||||
if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
|
||||
self.raise_geo_restricted(
|
||||
f'{self.IE_NAME} said: This page is currently unavailable in your region')
|
||||
|
||||
auth_info = self._parse_json(webpage, video_id)
|
||||
self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['legacy_token']
|
||||
|
||||
def _call_api(self, path, *args, **kwargs):
|
||||
try:
|
||||
data = self._download_json(self._api_url_template % path, *args, **kwargs)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError):
|
||||
errors = self._parse_json(e.cause.response.read().decode(), None)['errors']
|
||||
error_message = ', '.join([error['message'] for error in errors])
|
||||
raise ExtractorError(f'{self.IE_NAME} said: {error_message}', expected=True)
|
||||
raise
|
||||
return data
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
self._initialize_api(video_id)
|
||||
|
||||
video_info = self._call_api(
|
||||
f'video/{video_id}', video_id, 'Downloading api video info',
|
||||
'Failed to download video info')
|
||||
|
||||
video_versions = self._call_api(
|
||||
f'video/{video_id}/streams', video_id,
|
||||
'Downloading video versions info',
|
||||
'Failed to download video versions info',
|
||||
fatal=False)
|
||||
|
||||
# Some videos are only available via webpage (e.g.
|
||||
# https://github.com/ytdl-org/youtube-dl/issues/9366)
|
||||
if not video_versions:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
json_data = self._extract_json(webpage, video_id)
|
||||
if 'streams' in json_data.get('default', {}):
|
||||
video_versions = json_data['default']['streams'][video_id][0]
|
||||
else:
|
||||
video_versions = [
|
||||
value
|
||||
for key, value in json_data['apollo']['data'].items()
|
||||
if key.startswith(f'{video_id}.streams')]
|
||||
|
||||
uploader = None
|
||||
artist = None
|
||||
featured_artist = None
|
||||
artists = video_info.get('artists')
|
||||
for curr_artist in artists:
|
||||
if curr_artist.get('role') == 'Featured':
|
||||
featured_artist = curr_artist['name']
|
||||
else:
|
||||
artist = uploader = curr_artist['name']
|
||||
|
||||
formats = []
|
||||
for video_version in video_versions:
|
||||
version = self._VERSIONS.get(video_version.get('version'), 'generic')
|
||||
version_url = video_version.get('url')
|
||||
if not version_url:
|
||||
continue
|
||||
|
||||
if '.ism' in version_url:
|
||||
continue
|
||||
elif '.mpd' in version_url:
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
version_url, video_id, mpd_id=f'dash-{version}',
|
||||
note=f'Downloading {version} MPD information',
|
||||
errnote=f'Failed to download {version} MPD information',
|
||||
fatal=False))
|
||||
elif '.m3u8' in version_url:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
version_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id=f'hls-{version}',
|
||||
note=f'Downloading {version} m3u8 information',
|
||||
errnote=f'Failed to download {version} m3u8 information',
|
||||
fatal=False))
|
||||
else:
|
||||
m = re.search(r'''(?xi)
|
||||
_(?P<quality>[a-z0-9]+)
|
||||
_(?P<width>[0-9]+)x(?P<height>[0-9]+)
|
||||
_(?P<vcodec>[a-z0-9]+)
|
||||
_(?P<vbr>[0-9]+)
|
||||
_(?P<acodec>[a-z0-9]+)
|
||||
_(?P<abr>[0-9]+)
|
||||
\.(?P<ext>[a-z0-9]+)''', version_url)
|
||||
if not m:
|
||||
continue
|
||||
|
||||
formats.append({
|
||||
'url': version_url,
|
||||
'format_id': f'http-{version}-{video_version.get("quality") or m.group("quality")}',
|
||||
'vcodec': m.group('vcodec'),
|
||||
'acodec': m.group('acodec'),
|
||||
'vbr': int(m.group('vbr')),
|
||||
'abr': int(m.group('abr')),
|
||||
'ext': m.group('ext'),
|
||||
'width': int(m.group('width')),
|
||||
'height': int(m.group('height')),
|
||||
})
|
||||
|
||||
track = video_info['title']
|
||||
if featured_artist:
|
||||
artist = f'{artist} ft. {featured_artist}'
|
||||
title = f'{artist} - {track}' if artist else track
|
||||
|
||||
genres = video_info.get('genres')
|
||||
genre = (
|
||||
genres[0] if genres and isinstance(genres, list)
|
||||
and isinstance(genres[0], str) else None)
|
||||
|
||||
is_explicit = video_info.get('isExplicit')
|
||||
if is_explicit is True:
|
||||
age_limit = 18
|
||||
elif is_explicit is False:
|
||||
age_limit = 0
|
||||
else:
|
||||
age_limit = None
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': video_info.get('imageUrl') or video_info.get('thumbnailUrl'),
|
||||
'timestamp': parse_iso8601(video_info.get('releaseDate')),
|
||||
'uploader': uploader,
|
||||
'duration': int_or_none(video_info.get('duration')),
|
||||
'view_count': int_or_none(video_info.get('views', {}).get('total')),
|
||||
'age_limit': age_limit,
|
||||
'track': track,
|
||||
'artist': uploader,
|
||||
'genre': genre,
|
||||
}
|
||||
|
||||
|
||||
class VevoPlaylistIE(VevoBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?vevo\.com/watch/(?P<kind>playlist|genre)/(?P<id>[^/?#&]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.vevo.com/watch/genre/rock',
|
||||
'info_dict': {
|
||||
'id': 'rock',
|
||||
'title': 'Rock',
|
||||
},
|
||||
'playlist_count': 20,
|
||||
}, {
|
||||
'url': 'http://www.vevo.com/watch/genre/rock?index=0',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
playlist_id = mobj.group('id')
|
||||
playlist_kind = mobj.group('kind')
|
||||
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
qs = parse_qs(url)
|
||||
index = qs.get('index', [None])[0]
|
||||
|
||||
if index:
|
||||
video_id = self._search_regex(
|
||||
r'<meta[^>]+content=(["\'])vevo://video/(?P<id>.+?)\1[^>]*>',
|
||||
webpage, 'video id', default=None, group='id')
|
||||
if video_id:
|
||||
return self.url_result(f'vevo:{video_id}', VevoIE.ie_key())
|
||||
|
||||
playlists = self._extract_json(webpage, playlist_id)['default'][f'{playlist_kind}s']
|
||||
|
||||
playlist = (next(iter(playlists.values()))
|
||||
if playlist_kind == 'playlist' else playlists[playlist_id])
|
||||
|
||||
entries = [
|
||||
self.url_result(f'vevo:{src}', VevoIE.ie_key())
|
||||
for src in playlist['isrcs']]
|
||||
|
||||
return self.playlist_result(
|
||||
entries, playlist.get('playlistId') or playlist_id,
|
||||
playlist.get('name'), playlist.get('description'))
|
||||
@ -5,7 +5,6 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from .dailymotion import DailymotionIE
|
||||
from .odnoklassniki import OdnoklassnikiIE
|
||||
from .pladform import PladformIE
|
||||
from .sibnet import SibnetEmbedIE
|
||||
from .vimeo import VimeoIE
|
||||
from .youtube import YoutubeIE
|
||||
@ -334,11 +333,6 @@ class VKIE(VKBaseIE):
|
||||
'url': 'https://vk.com/video205387401_164765225',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# pladform embed
|
||||
'url': 'https://vk.com/video-76116461_171554880',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'http://new.vk.com/video205387401_165548505',
|
||||
'only_matching': True,
|
||||
@ -456,10 +450,6 @@ class VKIE(VKBaseIE):
|
||||
if vimeo_url is not None:
|
||||
return self.url_result(vimeo_url, VimeoIE.ie_key())
|
||||
|
||||
pladform_url = PladformIE._extract_url(info_page)
|
||||
if pladform_url:
|
||||
return self.url_result(pladform_url, PladformIE.ie_key())
|
||||
|
||||
m_rutube = re.search(
|
||||
r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
|
||||
if m_rutube is not None:
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user