Compare commits

...

20 Commits

Author SHA1 Message Date
Mozi
d789a1da44
Merge 98e034ff8c into 37cd7660ea 2024-11-17 19:46:31 +01:00
sepro
37cd7660ea
[ie/youtube:tab] Fix podcasts tab extraction (#11567)
Authored by: seproDev
2024-11-17 19:46:04 +01:00
ChocoLZS
d867f99622
[ie/PiaLive] Add extractor (#10811)
Authored by: ChocoLZS
2024-11-17 19:41:57 +01:00
doe1080
10fc719bc7
[cleanup] Remove dead extractors (#11566)
- Removes MildomClipIE, MildomIE, MildomUserVodIE, MildomVodIE
- Removes PokemonIE, PokemonWatchIE
- Removes VeohIE, VeohUserIE

Closes #3373, Closes #7059
Authored by: doe1080
2024-11-17 16:22:40 +00:00
krichbanana
eb15fd5a32
[ie/kenh14] Add extractor (#3996)
Closes #3937
Authored by: krichbanana, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
2024-11-17 14:12:26 +00:00
sepro
7cecd299e4
[ie/chaturbate] Don't break embed detection (#11565)
Bugfix for 720b3dc453

Authored by: seproDev
2024-11-17 13:32:12 +01:00
Mozi
98e034ff8c comment about DRM 2024-10-31 01:23:23 +00:00
Mozi
971bf92c06 code style 2024-10-31 01:12:57 +00:00
Mozi
aa512f8b45 merge 'master' 2024-10-31 01:09:27 +00:00
Mozi
81075d168e fix typo; compat code 2024-10-31 01:06:31 +00:00
Mozi
77debf548f FifaContent: no positive redirection detection 2024-10-30 17:42:19 +00:00
Mozi
7f94f2fceb merge 'master' 2024-10-30 17:37:36 +00:00
Mozi
5f6a442047 Rewrite code; DRM content is being only matching 2024-10-30 17:37:09 +00:00
Mozi
76111ea625 merge 'master' 2024-10-28 00:32:14 +00:00
Mozi
ac5c846921 fix usage of self._merge_subtitles 2024-10-28 00:31:56 +00:00
Mozi
3585397c7f add fatal to _call_api 2024-10-18 16:11:54 +00:00
Mozi
dcc4a1672b merge 'master' 2024-10-18 16:03:20 +00:00
Mozi
bb98db29a1 simplify _call_api 2024-10-18 16:03:03 +00:00
Mozi
4e649c6a28 use "getter" in playlist_from_matches() 2024-10-13 10:26:00 +00:00
Mozi
a29bfa3b0c [ie/Fifa] Add extractors 2024-09-30 17:14:06 +00:00
11 changed files with 749 additions and 773 deletions

View File

@ -646,7 +646,11 @@ from .fc2 import (
FC2LiveIE,
)
from .fczenit import FczenitIE
from .fifa import FifaIE
from .fifa import (
FifaArticleIE,
FifaContentIE,
FifaPlayerIE,
)
from .filmon import (
FilmOnChannelIE,
FilmOnIE,
@ -946,6 +950,10 @@ from .kaltura import KalturaIE
from .kankanews import KankaNewsIE
from .karaoketv import KaraoketvIE
from .kelbyone import KelbyOneIE
from .kenh14 import (
Kenh14PlaylistIE,
Kenh14VideoIE,
)
from .khanacademy import (
KhanAcademyIE,
KhanAcademyUnitIE,
@ -1135,12 +1143,6 @@ from .microsoftembed import (
MicrosoftMediusIE,
)
from .microsoftstream import MicrosoftStreamIE
from .mildom import (
MildomClipIE,
MildomIE,
MildomUserVodIE,
MildomVodIE,
)
from .minds import (
MindsChannelIE,
MindsGroupIE,
@ -1522,8 +1524,8 @@ from .pgatour import PGATourIE
from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .pialive import PiaLiveIE
from .piapro import PiaproIE
from .piaulizaportal import PIAULIZAPortalIE
from .picarto import (
PicartoIE,
PicartoVodIE,
@ -1559,10 +1561,6 @@ from .podbayfm import (
)
from .podchaser import PodchaserIE
from .podomatic import PodomaticIE
from .pokemon import (
PokemonIE,
PokemonWatchIE,
)
from .pokergo import (
PokerGoCollectionIE,
PokerGoIE,
@ -2256,6 +2254,10 @@ from .ufctv import (
)
from .ukcolumn import UkColumnIE
from .uktvplay import UKTVPlayIE
from .uliza import (
UlizaPlayerIE,
UlizaPortalIE,
)
from .umg import UMGDeIE
from .unistra import UnistraIE
from .unity import UnityIE
@ -2284,10 +2286,6 @@ from .utreon import UtreonIE
from .varzesh3 import Varzesh3IE
from .vbox7 import Vbox7IE
from .veo import VeoIE
from .veoh import (
VeohIE,
VeohUserIE,
)
from .vesti import VestiIE
from .vevo import (
VevoIE,

View File

@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
}
def _extract_from_webpage(self, video_id, tld):
def _extract_from_html(self, video_id, tld):
webpage = self._download_webpage(
f'https://chaturbate.{tld}/{video_id}/', video_id,
headers=self.geo_verification_headers(), impersonate=True)
@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
def _real_extract(self, url):
video_id, tld = self._match_valid_url(url).group('id', 'tld')
return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)

View File

@ -1,75 +1,315 @@
import functools
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
float_or_none,
int_or_none,
traverse_obj,
parse_iso8601,
strip_or_none,
unified_timestamp,
update_url_query,
)
from ..utils.traversal import traverse_obj
class FifaIE(InfoExtractor):
_VALID_URL = r'https?://www\.fifa\.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
class FifaBaseIE(InfoExtractor):
_HEADERS = {
'content-type': 'application/json; charset=UTF-8',
'x-chili-accept-language': 'en',
'x-chili-api-version': '1.1',
'x-chili-authenticated': 'false',
'x-chili-device-id': 'undefined',
'x-chili-device-profile': 'WEB',
'x-chili-device-store': 'CHILI',
'x-chili-user-country': 'US',
'x-chili-accept-stream-mode': 'multi/codec-compatibility;q=0.8, mono/strict;q=0.7',
'x-chili-avod-compatibility': 'free,free-ads',
'x-chili-manifest-properties': 'subtitles',
'x-chili-streaming-proto': 'https',
}
def _call_api(self, path, video_id, note=None, headers=None, query=None, data=None):
return self._download_json(
f'https://www.plus.fifa.com/{path}', video_id, note, headers={
**self._HEADERS,
**(headers or {}),
}, query=query, data=data)
def _real_initialize(self):
device_info = self._call_api(
'gatekeeper/api/v1/devices/', None, 'Getting device info',
data=json.dumps({
'appVersion': '2.6.93',
'displayName': None,
'model': 'Chrome',
'manufacturer': 'Google Inc.',
'osName': 'Windows',
'osVersion': '10',
'platform': 'Chrome',
'platformVersion': '129.0.0.0',
'architecture': 'unknown',
'profile': 'WEB',
'store': 'CHILI',
'screenWidth': '1920',
'screenHeight': '1080',
}).encode())
self._HEADERS['x-chili-device-id'] = device_info['id']
def _extract_video(self, video_info, video_id):
formats = []
subtitles = {}
for stream_type in [
'hls/cbcs+h265.sdr;q=0.9, hls/cbcs+h264;q=0.5, hls/clear+h264;q=0.4, mp4/;q=0.1',
'mpd/cenc+h264;q=0.9, mpd/clear+h264;q=0.7, mp4/;q=0.1',
]:
session_info = self._call_api(
'flux-capacitor/api/v1/streaming/session', video_id,
'Getting streaming session', headers={'x-chili-accept-stream': stream_type},
data=json.dumps({'videoAssetId': video_info['id'], 'autoPlay': False}).encode())
streams_info = self._call_api(
'flux-capacitor/api/v1/streaming/urls', video_id, 'Getting streaming urls',
headers={'x-chili-streaming-session': session_info['id']})
for playlist_url in traverse_obj(streams_info, (..., 'url')):
ext = determine_ext(playlist_url)
if ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(playlist_url, video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(playlist_url, video_id, m3u8_id='hls')
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
raise ExtractorError(f'Unknown playlist URL {playlist_url}', video_id=video_id)
self._remove_duplicate_formats(formats)
return {
'id': video_id,
'title': strip_or_none(video_info['title']),
'duration': float_or_none(video_info.get('duration'), scale=1000),
'formats': formats,
'subtitles': subtitles,
'age_limit': traverse_obj(video_info, ('parental', 'age', {int_or_none})),
'thumbnails': [{
'url': update_url_query(x, {'width': 1408}),
'width': 1408,
} for x in [video_info.get('posterUrl'), video_info.get('wideCoverUrl')] if x],
}
class FifaPlayerIE(FifaBaseIE):
_VALID_URL = r'https?://(www\.)?plus\.fifa\.com/(?:\w{2})/player/(?P<id>[\w-]+)/?\?(?:[^#]+&)?catalogId=(?P<catalog_id>[\w-]+)'
_TESTS = [{
'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
'url': 'https://www.plus.fifa.com/en/player/f67b9d46-38c3-4e38-bbf3-89cf14cbcc1a?catalogId=b9c32230-1426-46d0-8448-ca824ae48603&entryPoint=Slider',
'info_dict': {
'id': '7on10qPcnyLajDDU3ntg6y',
'title': 'Italy v France | Final | 2006 FIFA World Cup Germany™ | Full Match Replay',
'description': 'md5:f4520d0ee80529c8ba4134a7d692ff8b',
'id': 'f67b9d46-38c3-4e38-bbf3-89cf14cbcc1a',
'ext': 'mp4',
'categories': ['FIFA Tournaments'],
'thumbnail': 'https://digitalhub.fifa.com/transform/135e2656-3a51-407b-8810-6c34bec5b59b/FMR_2006_Italy_France_Final_Hero',
'duration': 8165,
'release_timestamp': 1152403200,
'release_date': '20060709',
'title': 'Trailer | HD Cutz',
'age_limit': 0,
'duration': 195.84,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/pt/watch/1cg5r5Qt6Qt12ilkDgb1sV',
'url': 'https://www.plus.fifa.com/en/player/af65939f-bbce-4b8f-8462-5140af533c5f?catalogId=fac6685c-a900-4e78-b5cd-192af5131ffe&entryPoint=Slider',
'md5': '2c4f5c591448d372f6ba85b8f3be37df',
'info_dict': {
'id': '1cg5r5Qt6Qt12ilkDgb1sV',
'title': 'Brazil v Germany | Semi-finals | 2014 FIFA World Cup Brazil™ | Extended Highlights',
'description': 'md5:d908c74ee66322b804ae2e521b02a855',
'id': 'af65939f-bbce-4b8f-8462-5140af533c5f',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Highlights'],
'thumbnail': 'https://digitalhub.fifa.com/transform/d8fe6f61-276d-4a73-a7fe-6878a35fd082/FIFAPLS_100EXTHL_2014BRAvGER_TMB',
'duration': 902,
'release_timestamp': 1404777600,
'release_date': '20140708',
'title': 'Trailer | Bravas de Juárez',
'age_limit': 0,
'duration': 73.984,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/fr/watch/3C6gQH9C2DLwzNx7BMRQdp',
'info_dict': {
'id': '3C6gQH9C2DLwzNx7BMRQdp',
'title': 'Josimar goal against Northern Ireland | Classic Goals',
'description': 'md5:cbe7e7bb52f603c9f1fe9a4780fe983b',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Goal'],
'duration': 28,
'thumbnail': 'https://digitalhub.fifa.com/transform/f9301391-f8d9-48b5-823e-c093ac5e3e11/CG_MEN_1986_JOSIMAR',
},
'params': {'skip_download': 'm3u8'},
'url': 'https://plus.fifa.com/en/player/eeebdd38-5d51-4891-8307-ab5dd62c2c32?catalogId=ed3b2dcb-6886-4b34-8ba7-c8800027f7dd',
'only_matching': True,
}]
def _real_extract(self, url):
video_id, locale = self._match_valid_url(url).group('id', 'locale')
webpage = self._download_webpage(url, video_id)
video_id, catalog_id = self._match_valid_url(url).group('id', 'catalog_id')
video_asset = self._call_api(
'flux-capacitor/api/v1/videoasset', video_id,
'Downloading video asset', query={'catalog': catalog_id})
video_info = traverse_obj(video_asset, (lambda _, v: v['id'] == video_id), get_all=False)
if not video_info:
raise ExtractorError('Unable to extract video info')
return self._extract_video(video_info, video_id)
preconnect_link = self._search_regex(
r'<link\b[^>]+\brel\s*=\s*"preconnect"[^>]+href\s*=\s*"([^"]+)"', webpage, 'Preconnect Link')
video_details = self._download_json(
f'{preconnect_link}/sections/videoDetails/{video_id}', video_id, 'Downloading Video Details', fatal=False)
class FifaContentIE(FifaBaseIE):
_VALID_URL = r'https?://(www\.)?plus\.fifa\.com/(?:\w{2})/content/(?P<display_id>[\w-]+)/(?P<id>[\w-]+)/?(?:[#?]|$)'
_TESTS = [{
# from https://www.fifa.com/fifaplus/en/watch/series/48PQFX2J4TiDJcxWOxUPho/2ka5yomq8MBvfxe205zdQ9/6H72309PLWXafBIavvPzPQ#ReadMore
'url': 'https://www.plus.fifa.com/en/content/kariobangi/6f3be63f-76d9-4290-9e60-fd62afa95ed7',
'info_dict': {
'id': '6f3be63f-76d9-4290-9e60-fd62afa95ed7',
'title': 'Kariobangi',
'description': 'md5:b57eb012db2b84d482adedda82faf1c8',
'display_id': 'kariobangi',
'thumbnails': 'count:2',
},
'playlist_count': 0,
}, {
# from https://www.fifa.com/fifaplus/en/watch/series/5Ja1dDLuudkFF95OVHcYBG/5epcWav73zMbjTJh2RxIOt/1NIHdDxPlYodbNobjS1iX5
'url': 'https://www.plus.fifa.com/en/content/hd-cutz/b9c32230-1426-46d0-8448-ca824ae48603',
'info_dict': {
'id': 'b9c32230-1426-46d0-8448-ca824ae48603',
'title': 'HD Cutz',
'description': 'md5:86dd1e6d9b4463b3ccc2063ab3180c44',
'display_id': 'hd-cutz',
'thumbnails': 'count:2',
},
'playlist': [{
'info_dict': {
'id': 'b9c32230-1426-46d0-8448-ca824ae48603',
'ext': 'mp4',
'title': 'Trailer | HD Cutz',
'age_limit': 0,
'duration': 195.840,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
}],
'params': {'skip_download': 'm3u8'},
}, {
# from https://www.fifa.com/fifaplus/en/watch/movie/2OFuZ9TGyPH6x7nZsgnVBN
'url': 'https://www.plus.fifa.com/en/content/bravas-de-juarez/fac6685c-a900-4e78-b5cd-192af5131ffe',
'info_dict': {
'id': 'fac6685c-a900-4e78-b5cd-192af5131ffe',
'title': 'Bravas de Juárez',
'description': 'md5:e48e0f56fb27ac334e616976e0e62362',
'display_id': 'bravas-de-juarez',
},
'playlist': [{
'info_dict': {
'id': 'fac6685c-a900-4e78-b5cd-192af5131ffe',
'ext': 'mp4',
'title': 'Trailer | Bravas de Juárez',
'age_limit': 0,
'duration': 73.984,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
}],
}]
_WEBPAGE_TESTS = [{
# https://www.plus.fifa.com/en/content/le-moment-the-official-film-of-the-2019-fifa-womens-world-cup/68a89002-0182-4cc7-b858-e548de0fb9cc
'url': 'https://www.fifa.com/fifaplus/en/watch/movie/01ioUo8QHiajSisrvP3ES2',
'info_dict': {
'id': '68a89002-0182-4cc7-b858-e548de0fb9cc',
'title': 'Le Moment',
'description': 'md5:155f0c28ea9de733668d7eb1f7dbcb52',
'display_id': 'le-moment-the-official-film-of-the-2019-fifa-womens-world-cup',
},
'playlist_count': 0,
}, {
# https://www.plus.fifa.com/en/content/dreams-2018-fifa-world-cup-official-film/ebdce1da-ab82-4c0b-a7d3-b4fc71030339
'url': 'https://www.fifa.com/fifaplus/en/watch/movie/69GbI9lVcwhOeBvea5eKUB',
'info_dict': {
'id': 'ebdce1da-ab82-4c0b-a7d3-b4fc71030339',
'title': 'Dreams',
'description': 'md5:b795d218d5c2b88bff3c1569cb617acb',
'display_id': 'dreams-2018-fifa-world-cup-official-film',
},
'playlist_count': 0,
}]
preplay_parameters = self._download_json(
f'{preconnect_link}/videoPlayerData/{video_id}', video_id, 'Downloading Preplay Parameters')['preplayParameters']
def _entries(self, video_asset, video_id):
# trailers are non-DRM'd
for video_info in traverse_obj(video_asset, (lambda _, v: v['type'] == 'TRAILER', {dict})):
yield self._extract_video(video_info, video_id)
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
video_content = self._call_api(
f'entertainment/api/v1/contents/{video_id}', video_id, 'Downloading video content')
video_asset = self._call_api(
'flux-capacitor/api/v1/videoasset', video_id,
'Downloading video asset', query={'catalog': video_id})
thumbnails = []
for key, width in [('coverUrl', 330), ('wideCoverUrl', 1408)]:
if thumbnail_url := video_content.get(key):
thumbnails.append({
'url': update_url_query(thumbnail_url, {'width': width}),
'width': width,
})
return self.playlist_result(
self._entries(video_asset, video_id), video_id,
strip_or_none(video_content['title']), strip_or_none(video_content.get('storyLine')),
display_id=display_id, thumbnails=thumbnails)
class FifaArticleIE(InfoExtractor):
_VALID_URL = r'https?://(www\.)?fifa\.com/(fifaplus/)?(?P<locale>\w{2})/articles/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://www.fifa.com/en/articles/foord-talks-2023-and-battling-kerr-for-the-wsl-title',
'info_dict': {
'id': 'foord-talks-2023-and-battling-kerr-for-the-wsl-title',
'title': 'Foord talks 2023 and battling Kerr for the WSL title',
'timestamp': 1651136400,
'upload_date': '20220428',
},
'playlist': [{
'info_dict': {
'id': '6B2xtOT2SDMB4JeF3i9n2y',
'ext': 'mp4',
'title': 'Foord & Kerr: Friends and rivals',
'description': 'md5:756e14e1814196948ec4d2a9663f7214',
'duration': 82,
'categories': ['News', 'Interview'],
'thumbnail': r're:https://digitalhub\.fifa\.com/transform/[^/]+/\w+',
},
}, {
'info_dict': {
'id': 'R2Y1vbwvggrlSr02Cfr99',
'ext': 'mp4',
'title': 'Foord: 2023 will be the best Women\'s World Cup yet',
'description': 'Matildas star Caitlin Foord looks ahead to the FIFA Women\'s World Cup Australia & New Zealand 2023™.',
'duration': 44,
'categories': ['News', 'Interview'],
'thumbnail': r're:https://digitalhub\.fifa\.com/transform/[^/]+/\w+',
},
}],
'params': {'skip_download': 'm3u8'},
}, {
# https://www.fifa.com/en/articles/stars-set-to-collide-in-uwcl-final
'url': 'https://www.fifa.com/fifaplus/en/articles/stars-set-to-collide-in-uwcl-final',
'only_matching': True,
}]
@functools.cached_property
def _preconnect_link(self):
return self._search_regex(
r'<link\b[^>]+\brel\s*=\s*"preconnect"[^>]+href\s*=\s*"([^"]+)"',
self._download_webpage('https://fifa.com/', None), 'Preconnect Link')
def _call_api(self, path, video_id, note=None, query=None, fatal=True):
return self._download_json(
f'{self._preconnect_link}/{path}', video_id, note, query=query, fatal=fatal)
def _entries(self, video_ids, article_id):
for video_id in video_ids:
video_details = self._call_api(
f'sections/videoDetails/{video_id}', article_id,
'Downloading Video Details', fatal=False)
preplay_parameters = self._call_api(
f'videoPlayerData/{video_id}', article_id,
'Downloading Preplay Parameters')['preplayParameters']
content_data = self._download_json(
'https://content.uplynk.com/preplay/{contentId}/multiple.json?{queryStr}&sig={signature}'.format(**preplay_parameters),
video_id, 'Downloading Content Data')
'https://content.uplynk.com/preplay/{contentId}/multiple.json?{queryStr}&sig={signature}'.format(
**preplay_parameters), article_id, 'Downloading Content Data')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(content_data['playURL'], article_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(content_data['playURL'], video_id)
return {
yield {
'id': video_id,
'title': video_details.get('title'),
'description': video_details.get('description'),
@ -80,3 +320,20 @@ class FifaIE(InfoExtractor):
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
article_id, locale = self._match_valid_url(url).group('id', 'locale')
page_id = self._call_api(f'pages/en/articles/{article_id}', article_id)['pageId']
page_info = self._call_api(f'sections/article/{page_id}', article_id, query={'locale': locale})
video_ids = []
if hero_video_entry_id := page_info.get('heroVideoEntryId'):
video_ids.append(hero_video_entry_id)
video_ids.extend(traverse_obj(page_info, (
'richtext', 'content', lambda _, v: v['data']['target']['contentTypesCheckboxValue'] == 'Video',
'data', 'target', 'sys', 'id')))
return self.playlist_result(
self._entries(video_ids, article_id), article_id, page_info.get('articleTitle'),
timestamp=parse_iso8601(page_info.get('articlePublishedDate')))

160
yt_dlp/extractor/kenh14.py Normal file
View File

@ -0,0 +1,160 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_attribute,
get_elements_html_by_class,
int_or_none,
parse_duration,
parse_iso8601,
remove_start,
strip_or_none,
unescapeHTML,
update_url,
url_or_none,
)
from ..utils.traversal import traverse_obj
class Kenh14VideoIE(InfoExtractor):
_VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
_TESTS = [{
'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
'md5': '1ed67f9c3a1e74acf15db69590cf6210',
'info_dict': {
'id': '316173',
'ext': 'mp4',
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
'tags': [],
'uploader': 'Unbox Therapy',
'upload_date': '20220517',
'view_count': int,
'duration': 722.86,
'timestamp': 1652764468,
},
}, {
'url': 'https://video.kenh14.vn/video-316174.chn',
'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
'info_dict': {
'id': '316174',
'ext': 'mp4',
'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
'tags': [],
'upload_date': '20220517',
'view_count': int,
'duration': 70.04,
'timestamp': 1652766021,
},
}, {
'url': 'https://video.kenh14.vn/0-344740.chn',
'md5': 'b843495d5e728142c8870c09b46df2a9',
'info_dict': {
'id': '344740',
'ext': 'mov',
'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
'uploader': 'Quang Vũ',
'upload_date': '20241024',
'view_count': int,
'duration': 198.88,
'timestamp': 1729741590,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
direct_url = attrs['data-vid']
metadata = self._download_json(
'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
subtitles = {}
video_data = self._download_json(
f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
fmts, subs = self._extract_mpd_formats_and_subtitles(
dash_url, video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
**traverse_obj(metadata, {
'duration': ('duration', {parse_duration}),
'uploader': ('author', {strip_or_none}),
'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
'view_count': ('views', {int_or_none}),
}),
'id': video_id,
'title': (
traverse_obj(metadata, ('title', {strip_or_none}))
or clean_html(self._og_search_title(webpage))
or clean_html(get_element_by_class('vdbw-title', webpage))),
'formats': formats,
'subtitles': subtitles,
'description': (
clean_html(self._og_search_description(webpage))
or clean_html(get_element_by_class('vdbw-sapo', webpage))),
'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
{lambda x: x.split(';')}, ..., filter)),
}
class Kenh14PlaylistIE(InfoExtractor):
_VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
_TESTS = [{
'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
'info_dict': {
'id': '71',
'title': 'Trần Tình (Naked love) mùa 2',
'description': 'md5:e9522339304956dea931722dd72eddb2',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
},
'playlist_count': 9,
}, {
'url': 'https://video.kenh14.vn/playlist/0-72.chn',
'info_dict': {
'id': '72',
'title': 'Lau Lại Đầu Từ',
'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
},
'playlist_count': 6,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
category_detail = get_element_by_class('category-detail', webpage) or ''
embed_info = traverse_obj(
self._yield_json_ld(webpage, playlist_id),
(lambda _, v: v['name'] and v['alternateName'], any)) or {}
return self.playlist_from_matches(
get_elements_html_by_class('video-item', webpage), playlist_id,
(clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
ie=Kenh14VideoIE, playlist_description=(
clean_html(get_element_by_class('description', category_detail))
or unescapeHTML(embed_info.get('alternateName'))),
thumbnail=traverse_obj(
self._og_search_thumbnail(webpage),
({url_or_none}, {update_url(query=None)})))

View File

@ -1,291 +0,0 @@
import functools
import json
import uuid
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
determine_ext,
dict_get,
float_or_none,
traverse_obj,
)
class MildomBaseIE(InfoExtractor):
_GUEST_ID = None
def _call_api(self, url, video_id, query=None, note='Downloading JSON metadata', body=None):
if not self._GUEST_ID:
self._GUEST_ID = f'pc-gp-{uuid.uuid4()}'
content = self._download_json(
url, video_id, note=note, data=json.dumps(body).encode() if body else None,
headers={'Content-Type': 'application/json'} if body else {},
query={
'__guest_id': self._GUEST_ID,
'__platform': 'web',
**(query or {}),
})
if content['code'] != 0:
raise ExtractorError(
f'Mildom says: {content["message"]} (code {content["code"]})',
expected=True)
return content['body']
class MildomIE(MildomBaseIE):
IE_NAME = 'mildom'
IE_DESC = 'Record ongoing live by specific user in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/(?P<id>\d+)'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(f'https://www.mildom.com/{video_id}', video_id)
enterstudio = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
note='Downloading live metadata', query={'user_id': video_id})
result_video_id = enterstudio.get('log_id', video_id)
servers = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', result_video_id,
note='Downloading live server list', query={
'user_id': video_id,
'live_server_type': 'hls',
})
playback_token = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/token', result_video_id,
note='Obtaining live playback token', body={'host_id': video_id, 'type': 'hls'})
playback_token = traverse_obj(playback_token, ('data', ..., 'token'), get_all=False)
if not playback_token:
raise ExtractorError('Failed to obtain live playback token')
formats = self._extract_m3u8_formats(
f'{servers["stream_server"]}/{video_id}_master.m3u8?{playback_token}',
result_video_id, 'mp4', headers={
'Referer': 'https://www.mildom.com/',
'Origin': 'https://www.mildom.com',
})
for fmt in formats:
fmt.setdefault('http_headers', {})['Referer'] = 'https://www.mildom.com/'
return {
'id': result_video_id,
'title': self._html_search_meta('twitter:description', webpage, default=None) or traverse_obj(enterstudio, 'anchor_intro'),
'description': traverse_obj(enterstudio, 'intro', 'live_intro', expected_type=str),
'timestamp': float_or_none(enterstudio.get('live_start_ms'), scale=1000),
'uploader': self._html_search_meta('twitter:title', webpage, default=None) or traverse_obj(enterstudio, 'loginname'),
'uploader_id': video_id,
'formats': formats,
'is_live': True,
}
class MildomVodIE(MildomBaseIE):
IE_NAME = 'mildom:vod'
IE_DESC = 'VOD in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+-?[0-9]*)'
_TESTS = [{
'url': 'https://www.mildom.com/playback/10882672/10882672-1597662269',
'info_dict': {
'id': '10882672-1597662269',
'ext': 'mp4',
'title': '始めてのミルダム配信じゃぃ!',
'thumbnail': r're:^https?://.*\.(png|jpg)$',
'upload_date': '20200817',
'duration': 4138.37,
'description': 'ゲームをしたくて!',
'timestamp': 1597662269.0,
'uploader_id': '10882672',
'uploader': 'kson組長(けいそん)',
},
}, {
'url': 'https://www.mildom.com/playback/10882672/10882672-1597758589870-477',
'info_dict': {
'id': '10882672-1597758589870-477',
'ext': 'mp4',
'title': '【kson】感染メイズ麻酔銃で無双する',
'thumbnail': r're:^https?://.*\.(png|jpg)$',
'timestamp': 1597759093.0,
'uploader': 'kson組長(けいそん)',
'duration': 4302.58,
'uploader_id': '10882672',
'description': 'このステージ絶対乗り越えたい',
'upload_date': '20200818',
},
}, {
'url': 'https://www.mildom.com/playback/10882672/10882672-buha9td2lrn97fk2jme0',
'info_dict': {
'id': '10882672-buha9td2lrn97fk2jme0',
'ext': 'mp4',
'title': '【kson組長】CART RACER!!!',
'thumbnail': r're:^https?://.*\.(png|jpg)$',
'uploader_id': '10882672',
'uploader': 'kson組長(けいそん)',
'upload_date': '20201104',
'timestamp': 1604494797.0,
'duration': 4657.25,
'description': 'WTF',
},
}]
def _real_extract(self, url):
user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
webpage = self._download_webpage(f'https://www.mildom.com/playback/{user_id}/{video_id}', video_id)
autoplay = self._call_api(
'https://cloudac.mildom.com/nonolive/videocontent/playback/getPlaybackDetail', video_id,
note='Downloading playback metadata', query={
'v_id': video_id,
})['playback']
formats = [{
'url': autoplay['audio_url'],
'format_id': 'audio',
'protocol': 'm3u8_native',
'vcodec': 'none',
'acodec': 'aac',
'ext': 'm4a',
}]
for fmt in autoplay['video_link']:
formats.append({
'format_id': 'video-{}'.format(fmt['name']),
'url': fmt['url'],
'protocol': 'm3u8_native',
'width': fmt['level'] * autoplay['video_width'] // autoplay['video_height'],
'height': fmt['level'],
'vcodec': 'h264',
'acodec': 'aac',
'ext': 'mp4',
})
return {
'id': video_id,
'title': self._html_search_meta(('og:description', 'description'), webpage, default=None) or autoplay.get('title'),
'description': traverse_obj(autoplay, 'video_intro'),
'timestamp': float_or_none(autoplay.get('publish_time'), scale=1000),
'duration': float_or_none(autoplay.get('video_length'), scale=1000),
'thumbnail': dict_get(autoplay, ('upload_pic', 'video_pic')),
'uploader': traverse_obj(autoplay, ('author_info', 'login_name')),
'uploader_id': user_id,
'formats': formats,
}
class MildomClipIE(MildomBaseIE):
IE_NAME = 'mildom:clip'
IE_DESC = 'Clip in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/clip/(?P<id>(?P<user_id>\d+)-[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://www.mildom.com/clip/10042245-63921673e7b147ebb0806d42b5ba5ce9',
'info_dict': {
'id': '10042245-63921673e7b147ebb0806d42b5ba5ce9',
'title': '全然違ったよ',
'timestamp': 1619181890,
'duration': 59,
'thumbnail': r're:https?://.+',
'uploader': 'ざきんぽ',
'uploader_id': '10042245',
},
}, {
'url': 'https://www.mildom.com/clip/10111524-ebf4036e5aa8411c99fb3a1ae0902864',
'info_dict': {
'id': '10111524-ebf4036e5aa8411c99fb3a1ae0902864',
'title': 'かっこいい',
'timestamp': 1621094003,
'duration': 59,
'thumbnail': r're:https?://.+',
'uploader': '(ルーキー',
'uploader_id': '10111524',
},
}, {
'url': 'https://www.mildom.com/clip/10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
'info_dict': {
'id': '10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
'title': '',
'timestamp': 1614769431,
'duration': 31,
'thumbnail': r're:https?://.+',
'uploader': 'ドルゴルスレンギーン=ダグワドルジ',
'uploader_id': '10660174',
},
}]
def _real_extract(self, url):
user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
webpage = self._download_webpage(f'https://www.mildom.com/clip/{video_id}', video_id)
clip_detail = self._call_api(
'https://cloudac-cf-jp.mildom.com/nonolive/videocontent/clip/detail', video_id,
note='Downloading playback metadata', query={
'clip_id': video_id,
})
return {
'id': video_id,
'title': self._html_search_meta(
('og:description', 'description'), webpage, default=None) or clip_detail.get('title'),
'timestamp': float_or_none(clip_detail.get('create_time')),
'duration': float_or_none(clip_detail.get('length')),
'thumbnail': clip_detail.get('cover'),
'uploader': traverse_obj(clip_detail, ('user_info', 'loginname')),
'uploader_id': user_id,
'url': clip_detail['url'],
'ext': determine_ext(clip_detail.get('url'), 'mp4'),
}
class MildomUserVodIE(MildomBaseIE):
IE_NAME = 'mildom:user:vod'
IE_DESC = 'Download all VODs from specific user in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/profile/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.mildom.com/profile/10093333',
'info_dict': {
'id': '10093333',
'title': 'Uploads from ねこばたけ',
},
'playlist_mincount': 732,
}, {
'url': 'https://www.mildom.com/profile/10882672',
'info_dict': {
'id': '10882672',
'title': 'Uploads from kson組長(けいそん)',
},
'playlist_mincount': 201,
}]
def _fetch_page(self, user_id, page):
page += 1
reply = self._call_api(
'https://cloudac.mildom.com/nonolive/videocontent/profile/playbackList',
user_id, note=f'Downloading page {page}', query={
'user_id': user_id,
'page': page,
'limit': '30',
})
if not reply:
return
for x in reply:
v_id = x.get('v_id')
if not v_id:
continue
yield self.url_result(f'https://www.mildom.com/playback/{user_id}/{v_id}')
def _real_extract(self, url):
user_id = self._match_id(url)
self.to_screen(f'This will download all VODs belonging to user. To download ongoing live video, use "https://www.mildom.com/{user_id}" instead')
profile = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/user/profileV2', user_id,
query={'user_id': user_id}, note='Downloading user profile')['user_info']
return self.playlist_result(
OnDemandPagedList(functools.partial(self._fetch_page, user_id), 30),
user_id, f'Uploads from {profile["loginname"]}')

122
yt_dlp/extractor/pialive.py Normal file
View File

@ -0,0 +1,122 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_class,
multipart_encode,
str_or_none,
unified_timestamp,
url_or_none,
)
from ..utils.traversal import traverse_obj
class PiaLiveIE(InfoExtractor):
_VALID_URL = r'https?://player\.pia-live\.jp/stream/(?P<id>[\w-]+)'
_PLAYER_ROOT_URL = 'https://player.pia-live.jp/'
_PIA_LIVE_API_URL = 'https://api.pia-live.jp'
_API_KEY = 'kfds)FKFps-dms9e'
_TESTS = [{
'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krUDqGOwN4d61dCWQYOd6CTxl4hjya9dsfEZGsM4uGOUdax60lEI4twsXGXf7crmz8Gk__GhupTrWxA7RFRVt76',
'info_dict': {
'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
'display_id': '2431867_001',
'title': 'こながめでたい日2024の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
'live_status': 'was_live',
'comment_count': int,
},
'params': {
'getcomments': True,
'skip_download': True,
'ignore_no_formats_error': True,
},
'skip': 'The video is no longer available',
}, {
'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krJdu0GVBVbVy01IwpJ6J3qBEm3d9TCTt1d0eWpsZGj7DrOjVOmS7GAWGwyscMgiThopJvzgWC4H5b-7XQjAfRZ',
'info_dict': {
'id': '9ce8b8ba-f6d1-4d1f-83a0-18c3148ded93',
'display_id': '2431867_002',
'title': 'こながめでたい日2024の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
'live_status': 'was_live',
'comment_count': int,
},
'params': {
'getcomments': True,
'skip_download': True,
'ignore_no_formats_error': True,
},
'skip': 'The video is no longer available',
}]
def _extract_var(self, variable, html):
return self._search_regex(
rf'(?:var|const|let)\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
html, f'variable {variable}', group='value')
def _real_extract(self, url):
video_key = self._match_id(url)
webpage = self._download_webpage(url, video_key)
program_code = self._extract_var('programCode', webpage)
article_code = self._extract_var('articleCode', webpage)
title = self._html_extract_title(webpage)
if get_element_html_by_class('play-end', webpage):
raise ExtractorError('The video is no longer available', expected=True, video_id=program_code)
if start_info := clean_html(get_element_by_class('play-waiting__date', webpage)):
date, time = self._search_regex(
r'(?P<date>\d{4}/\d{1,2}/\d{1,2})\([月火水木金土日]\)(?P<time>\d{2}:\d{2})',
start_info, 'start_info', fatal=False, group=('date', 'time'))
if date and time:
release_timestamp_str = f'{date} {time} +09:00'
release_timestamp = unified_timestamp(release_timestamp_str)
self.raise_no_formats(f'The video will be available after {release_timestamp_str}', expected=True)
return {
'id': program_code,
'title': title,
'live_status': 'is_upcoming',
'release_timestamp': release_timestamp,
}
payload, content_type = multipart_encode({
'play_url': video_key,
'api_key': self._API_KEY,
})
api_data_and_headers = {
'data': payload,
'headers': {'Content-Type': content_type, 'Referer': self._PLAYER_ROOT_URL},
}
player_tag_list = self._download_json(
f'{self._PIA_LIVE_API_URL}/perf/player-tag-list/{program_code}', program_code,
'Fetching player tag list', 'Unable to fetch player tag list', **api_data_and_headers)
return self.url_result(
extract_attributes(player_tag_list['data']['movie_one_tag'])['src'],
url_transparent=True, title=title, display_id=program_code,
__post_extractor=self.extract_comments(program_code, article_code, api_data_and_headers))
def _get_comments(self, program_code, article_code, api_data_and_headers):
chat_room_url = traverse_obj(self._download_json(
f'{self._PIA_LIVE_API_URL}/perf/chat-tag-list/{program_code}/{article_code}', program_code,
'Fetching chat info', 'Unable to fetch chat info', fatal=False, **api_data_and_headers),
('data', 'chat_one_tag', {extract_attributes}, 'src', {url_or_none}))
if not chat_room_url:
return
comment_page = self._download_webpage(
chat_room_url, program_code, 'Fetching comment page', 'Unable to fetch comment page',
fatal=False, headers={'Referer': self._PLAYER_ROOT_URL})
if not comment_page:
return
yield from traverse_obj(self._search_json(
r'var\s+_history\s*=', comment_page, 'comment list',
program_code, contains_pattern=r'\[(?s:.+)\]', fatal=False), (..., {
'timestamp': (0, {int}),
'author_is_uploader': (1, {lambda x: x == 2}),
'author': (2, {str}),
'text': (3, {str}),
'id': (4, {str_or_none}),
}))

View File

@ -1,70 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_qs,
time_seconds,
traverse_obj,
)
class PIAULIZAPortalIE(InfoExtractor):
IE_DESC = 'ulizaportal.jp - PIA LIVE STREAM'
_VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
'info_dict': {
'id': '005f18b7-e810-5618-cb82-0987c5755d44',
'title': 'プレゼンテーションプレイヤーのサンプル',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}, {
'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
'info_dict': {
'id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
'title': '【確認用】視聴サンプルページULIZA',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
if expires and expires <= time_seconds():
raise ExtractorError('The link is expired.', video_id=video_id, expected=True)
webpage = self._download_webpage(url, video_id)
player_data = self._download_webpage(
self._search_regex(
r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
webpage, 'player data url'),
video_id, headers={'Referer': 'https://ulizaportal.jp/'},
note='Fetching player data', errnote='Unable to fetch player data')
formats = self._extract_m3u8_formats(
self._search_regex(
r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data,
'm3u8 url', default=None),
video_id, fatal=False)
m3u8_type = self._search_regex(
r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
return {
'id': video_id,
'title': self._html_extract_title(webpage),
'formats': formats,
'live_status': {
'video': 'is_live',
'dvr': 'was_live', # short-term archives
}.get(m3u8_type, 'not_live'), # VOD or long-term archives
}

View File

@ -1,136 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
extract_attributes,
int_or_none,
js_to_json,
merge_dicts,
)
class PokemonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/(?:[^/]+/)+(?P<display_id>[^/?#&]+))'
_TESTS = [{
'url': 'https://www.pokemon.com/us/pokemon-episodes/20_30-the-ol-raise-and-switch/',
'md5': '2fe8eaec69768b25ef898cda9c43062e',
'info_dict': {
'id': 'afe22e30f01c41f49d4f1d9eab5cd9a4',
'ext': 'mp4',
'title': 'The Ol Raise and Switch!',
'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
},
'add_id': ['LimelightMedia'],
}, {
# no data-video-title
'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
'info_dict': {
'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
'ext': 'mp4',
'title': "Pokémon : L'ascension de Darkrai",
'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
},
'add_id': ['LimelightMedia'],
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, video_id or display_id)
video_data = extract_attributes(self._search_regex(
r'(<[^>]+data-video-id="{}"[^>]*>)'.format(video_id if video_id else '[a-z0-9]{32}'),
webpage, 'video data element'))
video_id = video_data['data-video-id']
title = video_data.get('data-video-title') or self._html_search_meta(
'pkm-title', webpage, ' title', default=None) or self._search_regex(
r'<h1[^>]+\bclass=["\']us-title[^>]+>([^<]+)', webpage, 'title')
return {
'_type': 'url_transparent',
'id': video_id,
'url': f'limelight:media:{video_id}',
'title': title,
'description': video_data.get('data-video-summary'),
'thumbnail': video_data.get('data-video-poster'),
'series': 'Pokémon',
'season_number': int_or_none(video_data.get('data-video-season')),
'episode': title,
'episode_number': int_or_none(video_data.get('data-video-episode')),
'ie_key': 'LimelightMedia',
}
class PokemonWatchIE(InfoExtractor):
_VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
_API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
_TESTS = [{
'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
'md5': '62833938a31e61ab49ada92f524c42ff',
'info_dict': {
'id': '8309a40969894a8e8d5bc1311e9c5667',
'ext': 'mp4',
'title': 'Lillier and the Staff!',
'description': 'md5:338841b8c21b283d24bdc9b568849f04',
},
}, {
'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
'only_matching': True,
}, {
'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
'only_matching': True,
}]
def _extract_media(self, channel_array, video_id):
for channel in channel_array:
for media in channel.get('media'):
if media.get('id') == video_id:
return media
return None
def _real_extract(self, url):
video_id = self._match_id(url)
info = {
'_type': 'url',
'id': video_id,
'url': f'limelight:media:{video_id}',
'ie_key': 'LimelightMedia',
}
# API call can be avoided entirely if we are listing formats
if self.get_param('listformats', False):
return info
webpage = self._download_webpage(url, video_id)
build_vars = self._parse_json(self._search_regex(
r'(?s)buildVars\s*=\s*({.*?})', webpage, 'build vars'),
video_id, transform_source=js_to_json)
region = build_vars.get('region')
channel_array = self._download_json(self._API_URL.format(region), video_id)
video_data = self._extract_media(channel_array, video_id)
if video_data is None:
raise ExtractorError(
f'Video {video_id} does not exist', expected=True)
info['_type'] = 'url_transparent'
images = video_data.get('images')
return merge_dicts(info, {
'title': video_data.get('title'),
'description': video_data.get('description'),
'thumbnail': images.get('medium') or images.get('small'),
'series': 'Pokémon',
'season_number': int_or_none(video_data.get('season')),
'episode': video_data.get('title'),
'episode_number': int_or_none(video_data.get('episode')),
})

113
yt_dlp/extractor/uliza.py Normal file
View File

@ -0,0 +1,113 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
make_archive_id,
parse_qs,
time_seconds,
)
from ..utils.traversal import traverse_obj
class UlizaPlayerIE(InfoExtractor):
_VALID_URL = r'https://player-api\.p\.uliza\.jp/v1/players/[^?#]+\?(?:[^#]*&)?name=(?P<id>[^#&]+)'
_TESTS = [{
'url': 'https://player-api.p.uliza.jp/v1/players/timeshift-disabled/pia/admin?type=normal&playerobjectname=ulizaPlayer&name=livestream01_dvr&repeatable=true',
'info_dict': {
'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
'ext': 'mp4',
'title': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
'live_status': 'was_live',
'_old_archive_ids': ['piaulizaportal 88f3109a-f503-4d0f-a9f7-9f39ac745d84'],
},
}, {
'url': 'https://player-api.p.uliza.jp/v1/players/uliza_jp_gallery_normal/promotion/admin?type=presentation&name=cookings&targetid=player1',
'info_dict': {
'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
'ext': 'mp4',
'title': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
},
}, {
'url': 'https://player-api.p.uliza.jp/v1/players/default-player/pia/admin?type=normal&name=pia_movie_uliza_fix&targetid=ulizahtml5&repeatable=true',
'info_dict': {
'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
'ext': 'mp4',
'title': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
player_data = self._download_webpage(
url, display_id, headers={'Referer': 'https://player-api.p.uliza.jp/'},
note='Fetching player data', errnote='Unable to fetch player data')
m3u8_url = self._search_regex(
r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data, 'm3u8 url')
video_id = parse_qs(m3u8_url).get('ss', [display_id])[0]
formats = self._extract_m3u8_formats(m3u8_url, video_id)
m3u8_type = self._search_regex(
r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
return {
'id': video_id,
'title': video_id,
'formats': formats,
'live_status': {
'video': 'is_live',
'dvr': 'was_live', # short-term archives
}.get(m3u8_type, 'not_live'), # VOD or long-term archives
'_old_archive_ids': [make_archive_id('PIAULIZAPortal', video_id)],
}
class UlizaPortalIE(InfoExtractor):
IE_DESC = 'ulizaportal.jp'
_VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
'info_dict': {
'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
'display_id': '005f18b7-e810-5618-cb82-0987c5755d44',
'title': 'プレゼンテーションプレイヤーのサンプル',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}, {
'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
'info_dict': {
'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
'display_id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
'title': '【確認用】視聴サンプルページULIZA',
'live_status': 'not_live',
'_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
if expires and expires <= time_seconds():
raise ExtractorError('The link is expired', video_id=video_id, expected=True)
webpage = self._download_webpage(url, video_id)
player_data_url = self._search_regex(
r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
webpage, 'player data url')
return self.url_result(
player_data_url, UlizaPlayerIE, url_transparent=True,
display_id=video_id, video_title=self._html_extract_title(webpage))

View File

@ -1,189 +0,0 @@
import functools
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
int_or_none,
parse_duration,
qualities,
remove_start,
strip_or_none,
)
class VeohIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|videos|embed|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
'md5': '620e68e6a3cff80086df3348426c9ca3',
'info_dict': {
'id': 'v56314296nk7Zdmz3',
'ext': 'mp4',
'title': 'Straight Backs Are Stronger',
'description': 'md5:203f976279939a6dc664d4001e13f5f4',
'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th56314296\\.jpg(\\?.*)?',
'uploader': 'LUMOback',
'duration': 46,
'view_count': int,
'average_rating': int,
'comment_count': int,
'age_limit': 0,
'categories': ['technology_and_gaming'],
'tags': ['posture', 'posture', 'sensor', 'back', 'pain', 'wearable', 'tech', 'lumo'],
},
}, {
'url': 'http://www.veoh.com/embed/v56314296nk7Zdmz3',
'only_matching': True,
}, {
'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
'info_dict': {
'id': '27701988',
'ext': 'mp4',
'title': 'Chile workers cover up to avoid skin damage',
'description': 'md5:2bd151625a60a32822873efc246ba20d',
'uploader': 'afp-news',
'duration': 123,
},
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
'md5': '4fde7b9e33577bab2f2f8f260e30e979',
'note': 'Embedded ooyala video',
'info_dict': {
'id': '69525809',
'ext': 'mp4',
'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
'uploader': 'newsy-videos',
},
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
'only_matching': True,
}, {
'url': 'https://www.veoh.com/videos/v16374379WA437rMH',
'md5': 'cceb73f3909063d64f4b93d4defca1b3',
'info_dict': {
'id': 'v16374379WA437rMH',
'ext': 'mp4',
'title': 'Phantasmagoria 2, pt. 1-3',
'description': 'Phantasmagoria: a Puzzle of Flesh',
'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th16374379\\.jpg(\\?.*)?',
'uploader': 'davidspackage',
'duration': 968,
'view_count': int,
'average_rating': int,
'comment_count': int,
'age_limit': 18,
'categories': ['technology_and_gaming', 'gaming'],
'tags': ['puzzle', 'of', 'flesh'],
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
metadata = self._download_json(
'https://www.veoh.com/watch/getVideo/' + video_id,
video_id)
video = metadata['video']
title = video['title']
thumbnail_url = None
q = qualities(['Regular', 'HQ'])
formats = []
for f_id, f_url in video.get('src', {}).items():
if not f_url:
continue
if f_id == 'poster':
thumbnail_url = f_url
else:
formats.append({
'format_id': f_id,
'quality': q(f_id),
'url': f_url,
})
categories = metadata.get('categoryPath')
if not categories:
category = remove_start(strip_or_none(video.get('category')), 'category_')
categories = [category] if category else None
tags = video.get('tags')
return {
'id': video_id,
'title': title,
'description': video.get('description'),
'thumbnail': thumbnail_url,
'uploader': video.get('author', {}).get('nickname'),
'duration': int_or_none(video.get('lengthBySec')) or parse_duration(video.get('length')),
'view_count': int_or_none(video.get('views')),
'formats': formats,
'average_rating': int_or_none(video.get('rating')),
'comment_count': int_or_none(video.get('numOfComments')),
'age_limit': 18 if video.get('contentRatingId') == 2 else 0,
'categories': categories,
'tags': tags.split(', ') if tags else None,
}
class VeohUserIE(VeohIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:www\.)?veoh\.com/users/(?P<id>[\w-]+)'
IE_NAME = 'veoh:user'
_TESTS = [
{
'url': 'https://www.veoh.com/users/valentinazoe',
'info_dict': {
'id': 'valentinazoe',
'title': 'valentinazoe (Uploads)',
},
'playlist_mincount': 75,
},
{
'url': 'https://www.veoh.com/users/PiensaLibre',
'info_dict': {
'id': 'PiensaLibre',
'title': 'PiensaLibre (Uploads)',
},
'playlist_mincount': 2,
}]
_PAGE_SIZE = 16
def _fetch_page(self, uploader, page):
response = self._download_json(
'https://www.veoh.com/users/published/videos', uploader,
note=f'Downloading videos page {page + 1}',
headers={
'x-csrf-token': self._TOKEN,
'content-type': 'application/json;charset=UTF-8',
},
data=json.dumps({
'username': uploader,
'maxResults': self._PAGE_SIZE,
'page': page + 1,
'requestName': 'userPage',
}).encode())
if not response.get('success'):
raise ExtractorError(response['message'])
for video in response['videos']:
yield self.url_result(f'https://www.veoh.com/watch/{video["permalinkId"]}', VeohIE,
video['permalinkId'], video.get('title'))
def _real_initialize(self):
webpage = self._download_webpage(
'https://www.veoh.com', None, note='Downloading authorization token')
self._TOKEN = self._search_regex(
r'csrfToken:\s*(["\'])(?P<token>[0-9a-zA-Z]{40})\1', webpage,
'request token', group='token')
def _real_extract(self, url):
uploader = self._match_id(url)
return self.playlist_result(OnDemandPagedList(
functools.partial(self._fetch_page, uploader),
self._PAGE_SIZE), uploader, f'{uploader} (Uploads)')

View File

@ -5087,7 +5087,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
def _rich_entries(self, rich_grid_renderer):
renderer = traverse_obj(
rich_grid_renderer,
('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel'), any)) or {}
('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel', 'lockupViewModel'), any)) or {}
video_id = renderer.get('videoId')
if video_id:
yield self._extract_video(renderer)
@ -5114,6 +5114,18 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
})),
thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources'))
return
# lockupViewModel extraction
content_id = renderer.get('contentId')
if content_id and renderer.get('contentType') == 'LOCKUP_CONTENT_TYPE_PODCAST':
yield self.url_result(
f'https://www.youtube.com/playlist?list={content_id}',
ie=YoutubeTabIE, video_id=content_id,
**traverse_obj(renderer, {
'title': ('metadata', 'lockupMetadataViewModel', 'title', 'content', {str}),
}),
thumbnails=self._extract_thumbnails(renderer, (
'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel', 'image'), final_key='sources'))
return
def _video_entry(self, video_renderer):
video_id = video_renderer.get('videoId')
@ -6706,22 +6718,22 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
},
'playlist_count': 0,
}, {
# Podcasts tab, with rich entry playlistRenderers
# Podcasts tab, with rich entry lockupViewModel
'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
'info_dict': {
'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
'title': '99 Percent Invisible - Podcasts',
'uploader': '99 Percent Invisible',
'title': '99% Invisible - Podcasts',
'uploader': '99% Invisible',
'channel_follower_count': int,
'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
'tags': [],
'channel': '99 Percent Invisible',
'channel': '99% Invisible',
'uploader_id': '@99percentinvisiblepodcast',
},
'playlist_count': 0,
'playlist_count': 5,
}, {
# Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
'url': 'https://www.youtube.com/@AHimitsu/releases',