mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-25 08:41:28 +01:00
Compare commits
11 Commits
c832c46933
...
9f5ef16b3f
Author | SHA1 | Date | |
---|---|---|---|
|
9f5ef16b3f | ||
|
10fc719bc7 | ||
|
eb15fd5a32 | ||
|
7cecd299e4 | ||
|
aef78fdfa8 | ||
|
9768d62bf8 | ||
|
e569c03196 | ||
|
2e9c00649c | ||
|
d1175cf7a3 | ||
|
5f600dc613 | ||
|
79795b9502 |
|
@ -946,6 +946,10 @@ from .kaltura import KalturaIE
|
||||||
from .kankanews import KankaNewsIE
|
from .kankanews import KankaNewsIE
|
||||||
from .karaoketv import KaraoketvIE
|
from .karaoketv import KaraoketvIE
|
||||||
from .kelbyone import KelbyOneIE
|
from .kelbyone import KelbyOneIE
|
||||||
|
from .kenh14 import (
|
||||||
|
Kenh14PlaylistIE,
|
||||||
|
Kenh14VideoIE,
|
||||||
|
)
|
||||||
from .khanacademy import (
|
from .khanacademy import (
|
||||||
KhanAcademyIE,
|
KhanAcademyIE,
|
||||||
KhanAcademyUnitIE,
|
KhanAcademyUnitIE,
|
||||||
|
@ -1135,12 +1139,6 @@ from .microsoftembed import (
|
||||||
MicrosoftMediusIE,
|
MicrosoftMediusIE,
|
||||||
)
|
)
|
||||||
from .microsoftstream import MicrosoftStreamIE
|
from .microsoftstream import MicrosoftStreamIE
|
||||||
from .mildom import (
|
|
||||||
MildomClipIE,
|
|
||||||
MildomIE,
|
|
||||||
MildomUserVodIE,
|
|
||||||
MildomVodIE,
|
|
||||||
)
|
|
||||||
from .minds import (
|
from .minds import (
|
||||||
MindsChannelIE,
|
MindsChannelIE,
|
||||||
MindsGroupIE,
|
MindsGroupIE,
|
||||||
|
@ -1385,15 +1383,15 @@ from .nowness import (
|
||||||
)
|
)
|
||||||
from .noz import NozIE
|
from .noz import NozIE
|
||||||
from .npo import (
|
from .npo import (
|
||||||
NPOIE,
|
NPO3IE,
|
||||||
|
NTRIE,
|
||||||
VPROIE,
|
VPROIE,
|
||||||
WNLIE,
|
|
||||||
AndereTijdenIE,
|
AndereTijdenIE,
|
||||||
HetKlokhuisIE,
|
HetKlokhuisIE,
|
||||||
NPOLiveIE,
|
|
||||||
NPORadioFragmentIE,
|
|
||||||
NPORadioIE,
|
NPORadioIE,
|
||||||
|
NPOStartIE,
|
||||||
SchoolTVIE,
|
SchoolTVIE,
|
||||||
|
ZappIE,
|
||||||
)
|
)
|
||||||
from .npr import NprIE
|
from .npr import NprIE
|
||||||
from .nrk import (
|
from .nrk import (
|
||||||
|
@ -1559,10 +1557,6 @@ from .podbayfm import (
|
||||||
)
|
)
|
||||||
from .podchaser import PodchaserIE
|
from .podchaser import PodchaserIE
|
||||||
from .podomatic import PodomaticIE
|
from .podomatic import PodomaticIE
|
||||||
from .pokemon import (
|
|
||||||
PokemonIE,
|
|
||||||
PokemonWatchIE,
|
|
||||||
)
|
|
||||||
from .pokergo import (
|
from .pokergo import (
|
||||||
PokerGoCollectionIE,
|
PokerGoCollectionIE,
|
||||||
PokerGoIE,
|
PokerGoIE,
|
||||||
|
@ -2284,10 +2278,6 @@ from .utreon import UtreonIE
|
||||||
from .varzesh3 import Varzesh3IE
|
from .varzesh3 import Varzesh3IE
|
||||||
from .vbox7 import Vbox7IE
|
from .vbox7 import Vbox7IE
|
||||||
from .veo import VeoIE
|
from .veo import VeoIE
|
||||||
from .veoh import (
|
|
||||||
VeohIE,
|
|
||||||
VeohUserIE,
|
|
||||||
)
|
|
||||||
from .vesti import VestiIE
|
from .vesti import VestiIE
|
||||||
from .vevo import (
|
from .vevo import (
|
||||||
VevoIE,
|
VevoIE,
|
||||||
|
|
|
@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
|
||||||
'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
|
'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(
|
webpage = self._download_webpage(
|
||||||
f'https://chaturbate.{tld}/{video_id}/', video_id,
|
f'https://chaturbate.{tld}/{video_id}/', video_id,
|
||||||
headers=self.geo_verification_headers(), impersonate=True)
|
headers=self.geo_verification_headers(), impersonate=True)
|
||||||
|
@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id, tld = self._match_valid_url(url).group('id', 'tld')
|
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)
|
||||||
|
|
160
yt_dlp/extractor/kenh14.py
Normal file
160
yt_dlp/extractor/kenh14.py
Normal 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)})))
|
|
@ -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': 'あ',
|
|
||||||
'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"]}')
|
|
|
@ -1,606 +1,438 @@
|
||||||
import random
|
import json
|
||||||
import re
|
import re
|
||||||
import urllib.parse
|
|
||||||
|
from yt_dlp.utils._utils import ExtractorError
|
||||||
|
from yt_dlp.utils.traversal import traverse_obj
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
determine_ext,
|
determine_ext,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
merge_dicts,
|
|
||||||
orderedSet,
|
orderedSet,
|
||||||
str_or_none,
|
|
||||||
try_call,
|
|
||||||
unified_timestamp,
|
|
||||||
url_or_none,
|
|
||||||
urlencode_postdata,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class NPOIE(InfoExtractor):
|
class NPOBaseIE(InfoExtractor):
|
||||||
IE_NAME = 'npo'
|
def _extract_product_id_information(self, product_id):
|
||||||
IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
|
token = self._download_json(
|
||||||
_VALID_URL = r'''(?x)
|
f'https://npo.nl/start/api/domain/player-token?productId={product_id}', product_id,
|
||||||
(?:
|
'Downloading token')['token']
|
||||||
npo:|
|
return self._extract_info_from_token(product_id, token)
|
||||||
https?://
|
|
||||||
(?:www\.)?
|
|
||||||
(?:
|
|
||||||
npo\.nl/(?:[^/]+/)*|
|
|
||||||
(?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
|
|
||||||
omroepwnl\.nl/video/fragment/[^/]+__|
|
|
||||||
(?:zapp|npo3)\.nl/(?:[^/]+/){2,}
|
|
||||||
)
|
|
||||||
)
|
|
||||||
(?P<id>[^/?#]+)
|
|
||||||
'''
|
|
||||||
|
|
||||||
_TESTS = [{
|
def _extract_info_from_token(self, video_id, token):
|
||||||
'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
|
data = {
|
||||||
'md5': '4b3f9c429157ec4775f2c9cb7b911016',
|
'id': video_id,
|
||||||
'info_dict': {
|
}
|
||||||
'id': 'VPWON_1220719',
|
|
||||||
'ext': 'm4v',
|
|
||||||
'title': 'Nieuwsuur',
|
|
||||||
'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
|
|
||||||
'upload_date': '20140622',
|
|
||||||
},
|
|
||||||
'skip': 'Video was removed',
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
|
|
||||||
'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'VARA_101191800',
|
|
||||||
'ext': 'm4v',
|
|
||||||
'title': 'De Mega Mike & Mega Thomas show: The best of.',
|
|
||||||
'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
|
|
||||||
'upload_date': '20090227',
|
|
||||||
'duration': 2400,
|
|
||||||
},
|
|
||||||
'skip': 'Video was removed',
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
|
|
||||||
'md5': '1b279c0547f6b270e014c576415268c5',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'VPWON_1169289',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Zwart geld: de toekomst komt uit Afrika',
|
|
||||||
'description': 'md5:dffaf3d628a9c36f78ca48d834246261',
|
|
||||||
'upload_date': '20130225',
|
|
||||||
'duration': 3000,
|
|
||||||
'creator': 'NED2',
|
|
||||||
'series': 'Tegenlicht',
|
|
||||||
'timestamp': 1361822340,
|
|
||||||
'thumbnail': 'https://images.npo.nl/tile/1280x720/142854.jpg',
|
|
||||||
'episode': 'Zwart geld: de toekomst komt uit Afrika',
|
|
||||||
'episode_number': 18,
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'WO_VPRO_043706',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'De nieuwe mens - Deel 1',
|
|
||||||
'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
|
|
||||||
'duration': 4680,
|
|
||||||
'episode': 'De nieuwe mens - Deel 1',
|
|
||||||
'thumbnail': 'https://images.npo.nl/tile/1280x720/6289.jpg',
|
|
||||||
'timestamp': 1279716057,
|
|
||||||
'series': 'De nieuwe mens - Deel 1',
|
|
||||||
'upload_date': '20100721',
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
# non asf in streams
|
|
||||||
'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'WO_NOS_762771',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Hoe gaat Europa verder na Parijs?',
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
'skip': 'Video was removed',
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'VPWON_1233944',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Aap, poot, pies',
|
|
||||||
'description': 'md5:4b46b1b9553b4c036a04d2a532a137e6',
|
|
||||||
'upload_date': '20150508',
|
|
||||||
'duration': 599,
|
|
||||||
'episode': 'Aap, poot, pies',
|
|
||||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1280/c1280x720/608118.jpg',
|
|
||||||
'timestamp': 1431064200,
|
|
||||||
'series': 'Aap, poot, pies',
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'POW_00996502',
|
|
||||||
'ext': 'm4v',
|
|
||||||
'title': '''"Dit is wel een 'landslide'..."''',
|
|
||||||
'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
|
|
||||||
'upload_date': '20150508',
|
|
||||||
'duration': 462,
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
'skip': 'Video was removed',
|
|
||||||
}, {
|
|
||||||
# audio
|
|
||||||
'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'RBX_FUNX_6683215',
|
|
||||||
'ext': 'mp3',
|
|
||||||
'title': 'Jouw Stad Rotterdam',
|
|
||||||
'description': 'md5:db251505244f097717ec59fabc372d9f',
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
'skip': 'Video was removed',
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
# live stream
|
|
||||||
'url': 'npo:LI_NL1_4188102',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://npo.nl/KN_1698996',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.npo3.nl/the-genius/21-11-2022/VPWON_1341105',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'VPWON_1341105',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'duration': 2658,
|
|
||||||
'series': 'The Genius',
|
|
||||||
'description': 'md5:db02f1456939ca63f7c408f858044e94',
|
|
||||||
'title': 'The Genius',
|
|
||||||
'timestamp': 1669062000,
|
|
||||||
'creator': 'NED3',
|
|
||||||
'episode': 'The Genius',
|
|
||||||
'thumbnail': 'https://images.npo.nl/tile/1280x720/1827650.jpg',
|
|
||||||
'episode_number': 8,
|
|
||||||
'upload_date': '20221121',
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
}]
|
|
||||||
|
|
||||||
@classmethod
|
|
||||||
def suitable(cls, url):
|
|
||||||
return (False if any(ie.suitable(url)
|
|
||||||
for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
|
|
||||||
else super().suitable(url))
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
video_id = self._match_id(url)
|
|
||||||
if urllib.parse.urlparse(url).netloc in ['www.ntr.nl', 'ntr.nl']:
|
|
||||||
player = self._download_json(
|
|
||||||
f'https://www.ntr.nl/ajax/player/embed/{video_id}', video_id,
|
|
||||||
'Downloading player JSON', query={
|
|
||||||
'parameters[elementId]': f'npo{random.randint(0, 999)}',
|
|
||||||
'parameters[sterReferralUrl]': url,
|
|
||||||
'parameters[autoplay]': 0,
|
|
||||||
})
|
|
||||||
else:
|
|
||||||
self._request_webpage(
|
|
||||||
'https://www.npostart.nl/api/token', video_id,
|
|
||||||
'Downloading token', headers={
|
|
||||||
'Referer': url,
|
|
||||||
'X-Requested-With': 'XMLHttpRequest',
|
|
||||||
})
|
|
||||||
player = self._download_json(
|
|
||||||
f'https://www.npostart.nl/player/{video_id}', video_id,
|
|
||||||
'Downloading player JSON', data=urlencode_postdata({
|
|
||||||
'autoplay': 0,
|
|
||||||
'share': 1,
|
|
||||||
'pageUrl': url,
|
|
||||||
'hasAdConsent': 0,
|
|
||||||
}), headers={
|
|
||||||
'x-xsrf-token': try_call(lambda: urllib.parse.unquote(
|
|
||||||
self._get_cookies('https://www.npostart.nl')['XSRF-TOKEN'].value)),
|
|
||||||
})
|
|
||||||
|
|
||||||
player_token = player['token']
|
|
||||||
|
|
||||||
drm = False
|
|
||||||
format_urls = set()
|
|
||||||
formats = []
|
formats = []
|
||||||
for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
|
thumbnails = []
|
||||||
streams = self._download_json(
|
subtitles = {}
|
||||||
f'https://start-player.npo.nl/video/{video_id}/streams',
|
for profile_name in ('dash', 'hls', 'smooth'):
|
||||||
video_id, f'Downloading {profile} profile JSON', fatal=False,
|
profile = self._download_json(
|
||||||
query={
|
'https://prod.npoplayer.nl/stream-link',
|
||||||
'profile': profile,
|
video_id,
|
||||||
'quality': 'npoplus',
|
f'Downloading profile {profile_name} JSON',
|
||||||
'tokenId': player_token,
|
data=json.dumps({'profileName': profile_name}).encode(),
|
||||||
'streamType': 'broadcast',
|
headers={'Authorization': token},
|
||||||
}, data=b'') # endpoint requires POST
|
fatal=False,
|
||||||
if not streams:
|
)
|
||||||
continue
|
metadata = profile.get('metadata')
|
||||||
stream = streams.get('stream')
|
if metadata is not None:
|
||||||
if not isinstance(stream, dict):
|
duration = metadata.get('duration')
|
||||||
continue
|
thumbnail = metadata.get('poster')
|
||||||
stream_url = url_or_none(stream.get('src'))
|
data['title'] = metadata.get('title')
|
||||||
if not stream_url or stream_url in format_urls:
|
data['description'] = metadata.get('description')
|
||||||
continue
|
data['channel_id'] = metadata.get('channel')
|
||||||
format_urls.add(stream_url)
|
data['uploader_id'] = metadata.get('channel')
|
||||||
if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
|
data['genres'] = metadata.get('genres')
|
||||||
drm = True
|
if duration:
|
||||||
continue
|
data['duration'] = duration / 1000
|
||||||
stream_type = stream.get('type')
|
if thumbnail and not any(thumb['url'] == thumbnail for thumb in thumbnails):
|
||||||
|
thumbnails.append({
|
||||||
|
'url': thumbnail,
|
||||||
|
})
|
||||||
|
raw_subtitles = traverse_obj(profile, ('assets', 'subtitles'))
|
||||||
|
stream_url = traverse_obj(profile, ('stream', 'streamURL'))
|
||||||
stream_ext = determine_ext(stream_url)
|
stream_ext = determine_ext(stream_url)
|
||||||
if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
|
if stream_ext == 'mpd':
|
||||||
formats.extend(self._extract_mpd_formats(
|
formats.extend(self._extract_mpd_formats(
|
||||||
stream_url, video_id, mpd_id='dash', fatal=False))
|
stream_url, video_id=video_id, mpd_id='dash', fatal=False))
|
||||||
elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
|
elif stream_ext == 'm3u8':
|
||||||
formats.extend(self._extract_m3u8_formats(
|
formats.extend(self._extract_m3u8_formats(
|
||||||
stream_url, video_id, ext='mp4',
|
stream_url, video_id=video_id, ext='mp4',
|
||||||
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
|
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
|
||||||
elif re.search(r'\.isml?/Manifest', stream_url):
|
elif re.search(r'\.isml?/Manifest', stream_url):
|
||||||
formats.extend(self._extract_ism_formats(
|
formats.extend(self._extract_ism_formats(
|
||||||
stream_url, video_id, ism_id='mss', fatal=False))
|
stream_url, video_id=video_id, ism_id='mss', fatal=False))
|
||||||
else:
|
else:
|
||||||
formats.append({
|
formats.append({
|
||||||
'url': stream_url,
|
'url': stream_url,
|
||||||
})
|
})
|
||||||
|
if (raw_subtitles):
|
||||||
if not formats:
|
for subtitle in raw_subtitles:
|
||||||
if not self.get_param('allow_unplayable_formats') and drm:
|
tag = subtitle.get('iso')
|
||||||
self.report_drm(video_id)
|
if tag not in subtitles:
|
||||||
|
subtitles[tag] = []
|
||||||
info = {
|
if not any(sub['url'] == subtitle['location'] for sub in subtitles[tag]):
|
||||||
'id': video_id,
|
subtitles[tag].append({
|
||||||
'title': video_id,
|
'url': subtitle.get('location'),
|
||||||
'formats': formats,
|
'name': subtitle.get('name'),
|
||||||
}
|
|
||||||
|
|
||||||
embed_url = url_or_none(player.get('embedUrl'))
|
|
||||||
if embed_url:
|
|
||||||
webpage = self._download_webpage(
|
|
||||||
embed_url, video_id, 'Downloading embed page', fatal=False)
|
|
||||||
if webpage:
|
|
||||||
video = self._parse_json(
|
|
||||||
self._search_regex(
|
|
||||||
r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
|
|
||||||
default='{}'), video_id)
|
|
||||||
if video:
|
|
||||||
title = video.get('episodeTitle')
|
|
||||||
subtitles = {}
|
|
||||||
subtitles_list = video.get('subtitles')
|
|
||||||
if isinstance(subtitles_list, list):
|
|
||||||
for cc in subtitles_list:
|
|
||||||
cc_url = url_or_none(cc.get('src'))
|
|
||||||
if not cc_url:
|
|
||||||
continue
|
|
||||||
lang = str_or_none(cc.get('language')) or 'nl'
|
|
||||||
subtitles.setdefault(lang, []).append({
|
|
||||||
'url': cc_url,
|
|
||||||
})
|
})
|
||||||
return merge_dicts({
|
data['formats'] = formats
|
||||||
'title': title,
|
data['subtitles'] = subtitles
|
||||||
'description': video.get('description'),
|
data['thumbnails'] = thumbnails
|
||||||
'thumbnail': url_or_none(
|
return data
|
||||||
video.get('still_image_url') or video.get('orig_image_url')),
|
|
||||||
'duration': int_or_none(video.get('duration')),
|
|
||||||
'timestamp': unified_timestamp(video.get('broadcastDate')),
|
|
||||||
'creator': video.get('channel'),
|
|
||||||
'series': video.get('title'),
|
|
||||||
'episode': title,
|
|
||||||
'episode_number': int_or_none(video.get('episodeNumber')),
|
|
||||||
'subtitles': subtitles,
|
|
||||||
}, info)
|
|
||||||
|
|
||||||
return info
|
|
||||||
|
|
||||||
|
|
||||||
class NPOLiveIE(InfoExtractor):
|
class NPOStartIE(NPOBaseIE):
|
||||||
IE_NAME = 'npo.nl:live'
|
IE_NAME = 'npo.nl:start'
|
||||||
_VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
|
_VALID_URL = r'https?://(?:www\.)?npo\.nl/start/serie/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.npo.nl/live/npo-1',
|
'url': 'https://npo.nl/start/serie/vpro-tegenlicht/seizoen-11/zwart-geld-de-toekomst-komt-uit-afrika/afspelen',
|
||||||
|
'md5': '8c30593a81ac80d65b531eaf2a92ac02',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'LI_NL1_4188102',
|
'id': 'VPWON_1169289',
|
||||||
'display_id': 'npo-1',
|
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
'title': 'Zwart geld: de toekomst komt uit Afrika',
|
||||||
'is_live': True,
|
'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
|
||||||
|
'duration': 3000,
|
||||||
|
'uploader_id': 'NED2',
|
||||||
|
'series': 'VPRO Tegenlicht',
|
||||||
|
'timestamp': 1361822340,
|
||||||
|
'thumbnail': 'https://assets-start.npo.nl/resources/2023/06/30/d9879593-1944-4249-990c-1561dac14d8e.jpg',
|
||||||
|
'episode': 'Zwart geld: de toekomst komt uit Afrika',
|
||||||
|
'episode_number': 18,
|
||||||
|
'channel_id': 'NED2',
|
||||||
|
'genres': [],
|
||||||
|
'release_date': '20130225',
|
||||||
|
'release_timestamp': 1361822340,
|
||||||
|
'season': 'Season 11',
|
||||||
|
'season_id': 'df5e2334-e07a-4301-b3d3-8e224d8c1f07',
|
||||||
|
'season_number': 11,
|
||||||
|
'series_id': '6727dcdf-4bd2-477c-bf96-1ead69fad6c9',
|
||||||
|
'upload_date': '20130225',
|
||||||
},
|
},
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.npo.nl/live',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.npostart.nl/live/npo-1',
|
|
||||||
'only_matching': True,
|
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url) or 'npo-1'
|
slug = self._match_id(url)
|
||||||
|
metadata = self._download_json(f'https://npo.nl/start/api/domain/program-detail?slug={slug}', video_id=slug, note='Downloading program details JSON')
|
||||||
|
video_id = metadata['productId']
|
||||||
|
data = self._extract_product_id_information(video_id)
|
||||||
|
thumbnails = []
|
||||||
|
for image in metadata.get('images'):
|
||||||
|
thumbnails.append({
|
||||||
|
'id': image.get('guid'),
|
||||||
|
'url': image.get('url'),
|
||||||
|
})
|
||||||
|
break
|
||||||
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
data['title'] = metadata.get('title') or data.get('title')
|
||||||
|
data['episode'] = metadata.get('title') or data.get('title')
|
||||||
live_id = self._search_regex(
|
data['episode_number'] = int_or_none(metadata.get('programKey'))
|
||||||
[r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
|
data['duration'] = int_or_none(metadata.get('durationInSeconds'), default=data.get('duration'))
|
||||||
|
data['description'] = traverse_obj(metadata, ('synopsis', 'long')) or traverse_obj(metadata, ('synopsis', 'short')) or traverse_obj(metadata, ('synopsis', 'brief')) or data.get('description')
|
||||||
return {
|
data['thumbnails'] = thumbnails
|
||||||
'_type': 'url_transparent',
|
data['genres'] = metadata.get('genres') or data.get('genres')
|
||||||
'url': f'npo:{live_id}',
|
data['series'] = traverse_obj(metadata, ('series', 'title'))
|
||||||
'ie_key': NPOIE.ie_key(),
|
data['series_id'] = traverse_obj(metadata, ('series', 'guid'))
|
||||||
'id': live_id,
|
data['season_number'] = int_or_none(traverse_obj(metadata, ('season', 'seasonKey')))
|
||||||
'display_id': display_id,
|
data['season_id'] = traverse_obj(metadata, ('season', 'guid'))
|
||||||
}
|
data['release_timestamp'] = int_or_none(metadata.get('firstBroadcastDate'))
|
||||||
|
data['timestamp'] = int_or_none(metadata.get('publishedDateTime'))
|
||||||
|
return data
|
||||||
|
|
||||||
|
|
||||||
class NPORadioIE(InfoExtractor):
|
class NPORadioIE(NPOBaseIE):
|
||||||
IE_NAME = 'npo.nl:radio'
|
IE_NAME = 'npo.nl:radio'
|
||||||
_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
|
_VALID_URL = r'https?://(?:www\.)?nporadio(?P<n>\d)\.nl(?:/[^/]+)*/(?P<id>[^/]+)?'
|
||||||
|
|
||||||
_TEST = {
|
_TESTS = [{
|
||||||
'url': 'http://www.npo.nl/radio/radio-1',
|
'url': 'https://www.nporadio1.nl/',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'radio-1',
|
'id': 'live',
|
||||||
'ext': 'mp3',
|
'ext': 'mp4',
|
||||||
'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
'title': r're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||||
|
'live_status': 'is_live',
|
||||||
|
'thumbnail': r're:^https?://.*\.jpg',
|
||||||
|
'description': 'Live programmering',
|
||||||
'is_live': True,
|
'is_live': True,
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
}
|
},
|
||||||
|
{
|
||||||
@classmethod
|
'url': 'https://www.nporadio1.nl/nieuws/binnenland/15bcad75-22c5-4226-a3fe-d54a76175da3/utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid',
|
||||||
def suitable(cls, url):
|
'md5': '8ad04123febc07716f45e324d7fb792d',
|
||||||
return False if NPORadioFragmentIE.suitable(url) else super().suitable(url)
|
'info_dict': {
|
||||||
|
'id': 'utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid',
|
||||||
@staticmethod
|
'ext': 'mp4',
|
||||||
def _html_get_attribute_regex(attribute):
|
'duration': 262,
|
||||||
return rf'{attribute}\s*=\s*\'([^\']+)\''
|
'channel_id': 'RAD1',
|
||||||
|
'description': 'md5:7d36b72407e757e6c748a6cdf27c7628',
|
||||||
|
'title': 'Utrecht zet rolmodellen in voor bewustzijn mentale gezondheid ',
|
||||||
|
'genres': ['Informatief'],
|
||||||
|
'uploader_id': 'RAD1',
|
||||||
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2217026',
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
'url': 'https://www.nporadio2.nl/fragmenten/janwillemstartop/9d35b8fb-a07b-41f9-9cc5-a9c89dd60dbb/2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje',
|
||||||
|
'md5': '432b0e106082ffaa0e31c4549db09b0c',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'genres': ['Muziek'],
|
||||||
|
'title': 'Nancy zet zich in voor daklozen: "Voor mij was het op het randje" ',
|
||||||
|
'duration': 235,
|
||||||
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2216783',
|
||||||
|
'description': 'md5:26925e8bd2c715b160cc864efa731583',
|
||||||
|
'uploader_id': 'RAD2',
|
||||||
|
'channel_id': 'RAD2',
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
'url': 'https://www.nporadio2.nl/uitzendingen/dit-is-tannaz/9bc1ab7e-77f6-4444-986b-1cd7c25ff4bf/2024-10-11-dit-is-tannaz',
|
||||||
|
'md5': 'a1212f4d2fe361aafcced5bcd3cf939b',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '2024-10-11-dit-is-tannaz',
|
||||||
|
'ext': 'mp3',
|
||||||
|
'uploader_id': 'RAD2',
|
||||||
|
'genres': ['Muziek'],
|
||||||
|
'title': 'Dit is Tannaz',
|
||||||
|
'channel_id': 'RAD2',
|
||||||
|
'description': 'md5:3f2b5dad3e965ae7915a5f9a5a2decc5',
|
||||||
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2190854',
|
||||||
|
'duration': 7200.026,
|
||||||
|
},
|
||||||
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
parsed = self._match_valid_url(url)
|
||||||
|
video_id = parsed.group('id') or 'live'
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
if video_id == 'live':
|
||||||
|
radio_number = parsed.group('n')
|
||||||
title = self._html_search_regex(
|
token_url = self._download_json(f'https://www.nporadio{radio_number}.nl/api/player/npo-radio-{radio_number}', video_id)['tokenUrl']
|
||||||
self._html_get_attribute_regex('data-channel'), webpage, 'title')
|
else:
|
||||||
|
props = self._search_nextjs_data(self._download_webpage(url, video_id), video_id)['props']['pageProps']
|
||||||
stream = self._parse_json(
|
token_url = traverse_obj(props, ('article', 'content', 0, 'value', 'player', 'tokenUrl')) or traverse_obj(props, ('fragmentDetail', 'bodyContent', 0, 'payload', 'player', 'tokenUrl')) or traverse_obj(props, ('radioBroadcast', 'showAssets', 0, 'player', 'tokenUrl'))
|
||||||
self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
|
if token_url is None:
|
||||||
video_id)
|
raise ExtractorError('Token url not found')
|
||||||
|
data = self._extract_info_from_token(video_id, self._download_json(token_url, video_id, 'Downloading token JSON')['playerToken'])
|
||||||
codec = stream.get('codec')
|
data['is_live'] = video_id == 'live'
|
||||||
|
return data
|
||||||
return {
|
|
||||||
'id': video_id,
|
|
||||||
'url': stream['url'],
|
|
||||||
'title': title,
|
|
||||||
'acodec': codec,
|
|
||||||
'ext': codec,
|
|
||||||
'is_live': True,
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
class NPORadioFragmentIE(InfoExtractor):
|
class NPO3IE(NPOBaseIE):
|
||||||
IE_NAME = 'npo.nl:radio:fragment'
|
IE_NAME = 'npo.nl:npo3'
|
||||||
_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
|
_VALID_URL = r'https?://(?:www\.)?npo\.nl/npo3/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
|
||||||
|
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
|
'url': 'https://npo.nl/npo3/vlees-smakelijk/11-10-2024/WO_KN_20222563',
|
||||||
'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
|
'md5': 'e0cd5b96c712edea2e7f0700d348bc98',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '174356',
|
'id': 'WO_KN_20222563',
|
||||||
'ext': 'mp3',
|
'ext': 'mp4',
|
||||||
'title': 'Jubileumconcert Willeke Alberti',
|
'description': 'md5:31f5ffff8c70af1635cbb93a8205e0c4',
|
||||||
|
'duration': 1021.994,
|
||||||
|
'title': 'Vlees smakelijk',
|
||||||
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2215940',
|
||||||
|
'genres': ['Human Interest', 'Reality TV'],
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
audio_id = self._match_id(url)
|
return self._extract_product_id_information(self._match_id(url))
|
||||||
|
|
||||||
webpage = self._download_webpage(url, audio_id)
|
|
||||||
|
|
||||||
title = self._html_search_regex(
|
|
||||||
rf'href="/radio/[^/]+/fragment/{audio_id}" title="([^"]+)"',
|
|
||||||
webpage, 'title')
|
|
||||||
|
|
||||||
audio_url = self._search_regex(
|
|
||||||
r"data-streams='([^']+)'", webpage, 'audio url')
|
|
||||||
|
|
||||||
return {
|
|
||||||
'id': audio_id,
|
|
||||||
'url': audio_url,
|
|
||||||
'title': title,
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
class NPODataMidEmbedIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
|
class SchoolTVIE(NPOBaseIE):
|
||||||
def _real_extract(self, url):
|
|
||||||
display_id = self._match_id(url)
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
|
||||||
video_id = self._search_regex(
|
|
||||||
r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
|
|
||||||
return {
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'ie_key': 'NPO',
|
|
||||||
'url': f'npo:{video_id}',
|
|
||||||
'display_id': display_id,
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
class SchoolTVIE(NPODataMidEmbedIE):
|
|
||||||
IE_NAME = 'schooltv'
|
IE_NAME = 'schooltv'
|
||||||
_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video-item/(?P<id>[^/?#&]+)'
|
||||||
|
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
|
'url': 'https://schooltv.nl/video-item/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'WO_NTR_429477',
|
'id': 'WO_NTR_429477',
|
||||||
'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
|
|
||||||
'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
|
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'description': 'md5:abfa0ff690adb73fd0297fd033aaa631',
|
'duration': 51.0,
|
||||||
},
|
'genres': ['Jeugd'],
|
||||||
'params': {
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/242560',
|
||||||
# Skip because of m3u8 download
|
'title': 'Ademhaling',
|
||||||
'skip_download': True,
|
'description': 'md5:db41d874d9ebe597686dda69e892ba49',
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
video_id = self._search_regex(r'id=([a-zA-Z0-9_]+)', self._html_search_meta(('og:video', 'og:video:secure_url'), self._download_webpage(url, self._match_id(url))), 'video id')
|
||||||
|
return self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
|
||||||
|
|
||||||
class HetKlokhuisIE(NPODataMidEmbedIE):
|
|
||||||
|
class HetKlokhuisIE(NPOBaseIE):
|
||||||
IE_NAME = 'hetklokhuis'
|
IE_NAME = 'hetklokhuis'
|
||||||
_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||||
|
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
|
'url': 'https://hetklokhuis.nl/dossier/142/zoek-het-uit/tv-uitzending/2987/aliens',
|
||||||
|
'md5': '679d610017689ecc798b316b8daa34e7',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'VPWON_1260528',
|
'id': 'VPWON_1225126',
|
||||||
'display_id': 'Zwaartekrachtsgolven',
|
'ext': 'mp4',
|
||||||
'ext': 'm4v',
|
'duration': 852.27,
|
||||||
'title': 'Het Klokhuis: Zwaartekrachtsgolven',
|
'channel_id': 'NED3',
|
||||||
'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
|
'description': 'md5:17681c9644521344a0573e04c78912d7',
|
||||||
'upload_date': '20170223',
|
'title': 'Aliens',
|
||||||
},
|
'genres': ['Jeugd', 'Informatief'],
|
||||||
'params': {
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/624824',
|
||||||
'skip_download': True,
|
'uploader_id': 'NED3',
|
||||||
|
'series': 'Zoek Het Uit!',
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
webpage = self._download_webpage(url, self._match_id(url))
|
||||||
|
series, title = self._og_search_title(webpage).split(' - ')
|
||||||
|
video_id = self._html_search_regex(r'data-mid="([a-zA-Z0-9_]+)"', webpage, 'video id')
|
||||||
|
data = self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
|
||||||
|
data['series'] = series
|
||||||
|
data['title'] = title
|
||||||
|
return data
|
||||||
|
|
||||||
|
|
||||||
|
class ZappIE(NPOBaseIE):
|
||||||
|
IE_NAME = 'zapp.nl'
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?zapp\.nl/programmas/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
|
||||||
|
|
||||||
|
_TEST = {
|
||||||
|
'url': 'https://www.zapp.nl/programmas/zappsport/gemist/POMS_AT_811523',
|
||||||
|
'md5': 'faf6811abea03ba8a52298c97bd0146b',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'POMS_AT_811523',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'genres': [],
|
||||||
|
'uploader_id': 'NED3',
|
||||||
|
'description': 'Kindersportprogramma waarin alle takken van sport voorbijkomen.',
|
||||||
|
'channel_id': 'NED3',
|
||||||
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/586056',
|
||||||
|
'duration': 900.0,
|
||||||
|
'title': 'Running Team 2015 - aflevering 1',
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
return self._extract_product_id_information(self._match_id(url))
|
||||||
|
|
||||||
|
|
||||||
|
class NPOPlaylistBaseIE(NPOBaseIE):
|
||||||
|
def _mid_result(self, mid, title, url):
|
||||||
|
token = self._download_token(mid, url)
|
||||||
|
data = self._extract_info_from_token(mid, token)
|
||||||
|
# The API returns the same title for every video so overwrite it with the video title
|
||||||
|
data['title'] = title
|
||||||
|
return data
|
||||||
|
|
||||||
class NPOPlaylistBaseIE(NPOIE): # XXX: Do not subclass from concrete IE
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
playlist_id = self._match_id(url)
|
playlist_id = self._match_id(url)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, playlist_id)
|
webpage = self._download_webpage(url, playlist_id)
|
||||||
|
|
||||||
entries = [
|
|
||||||
self.url_result(f'npo:{video_id}' if not video_id.startswith('http') else video_id)
|
|
||||||
for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
|
|
||||||
]
|
|
||||||
|
|
||||||
playlist_title = self._html_search_regex(
|
playlist_title = self._html_search_regex(
|
||||||
self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
|
self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
|
||||||
default=None) or self._og_search_title(webpage)
|
default=None) or self._og_search_title(webpage)
|
||||||
|
|
||||||
|
entries = [
|
||||||
|
self._mid_result(video_id, playlist_title, url)
|
||||||
|
for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
|
||||||
|
]
|
||||||
|
|
||||||
return self.playlist_result(entries, playlist_id, playlist_title)
|
return self.playlist_result(entries, playlist_id, playlist_title)
|
||||||
|
|
||||||
|
|
||||||
class VPROIE(NPOPlaylistBaseIE):
|
class VPROIE(NPOPlaylistBaseIE):
|
||||||
IE_NAME = 'vpro'
|
IE_NAME = 'vpro'
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
|
_VALID_URL = r'https?://(?:www\.)?(?:vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/.]+)'
|
||||||
_PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
|
_PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)')
|
||||||
r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
|
|
||||||
_PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
|
_PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
|
||||||
|
|
||||||
_TESTS = [
|
_TESTS = [
|
||||||
{
|
{
|
||||||
'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
|
'url': 'https://www.vpro.nl/programmas/3doc/2015/sergio-herman.html',
|
||||||
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'VPWON_1169289',
|
|
||||||
'ext': 'm4v',
|
|
||||||
'title': 'De toekomst komt uit Afrika',
|
|
||||||
'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
|
|
||||||
'upload_date': '20130225',
|
|
||||||
},
|
|
||||||
'skip': 'Video gone',
|
|
||||||
},
|
|
||||||
{
|
|
||||||
'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'sergio-herman',
|
'id': 'sergio-herman',
|
||||||
'title': 'sergio herman: fucking perfect',
|
'title': 'Sergio Herman: Fucking Perfect',
|
||||||
},
|
|
||||||
'playlist_count': 2,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
# playlist with youtube embed
|
|
||||||
'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'education-education',
|
|
||||||
'title': 'education education',
|
|
||||||
},
|
},
|
||||||
'playlist_count': 2,
|
'playlist_count': 2,
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
|
'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
|
||||||
|
'md5': '87a4cc5a62da942ca9270e4da1d2b8b5',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'de-tegenprestatie',
|
'id': 'VPWON_1223413',
|
||||||
|
'ext': 'mp4',
|
||||||
'title': 'De Tegenprestatie',
|
'title': 'De Tegenprestatie',
|
||||||
|
'duration': 2992.45,
|
||||||
|
'genres': ['Documentaire'],
|
||||||
|
'channel_id': 'NED2',
|
||||||
|
'description': 'Er wordt van burgers steeds meer eigen verantwoordelijkheid en zelfredzaamheid gevraagd.',
|
||||||
|
'uploader_id': 'NED2',
|
||||||
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/663342',
|
||||||
},
|
},
|
||||||
'playlist_count': 2,
|
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
|
'url': 'https://www.2doc.nl/documentaires/2018/07/het-verdriet-van-nederland.html',
|
||||||
|
'md5': '9ae67f6bdcb16a62f99e01198674fe10',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'VARA_101375237',
|
'id': 'VARA_101375237',
|
||||||
'ext': 'm4v',
|
'ext': 'mp4',
|
||||||
'title': 'MH17: Het verdriet van Nederland',
|
'uploader_id': 'NED1',
|
||||||
'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
|
'channel_id': 'NED1',
|
||||||
'upload_date': '20150716',
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/1608566',
|
||||||
},
|
'duration': 4259.63,
|
||||||
'params': {
|
'genres': ['Documentaire'],
|
||||||
# Skip because of m3u8 download
|
'title': 'Het verdriet van Nederland',
|
||||||
'skip_download': True,
|
'description': 'md5:d19b745af196f6cb98daf50ac7cb01fc',
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
]
|
]
|
||||||
|
|
||||||
|
def _download_token(self, mid, url):
|
||||||
|
return self._download_json('https://rs.vpro.nl/v3/api/npoplayer/token', mid, 'Downloading token JSON', data=json.dumps({'mid': mid}).encode(), headers={
|
||||||
|
'Content-Type': 'application/json',
|
||||||
|
'Referer': url,
|
||||||
|
})['token']
|
||||||
|
|
||||||
class WNLIE(NPOPlaylistBaseIE):
|
|
||||||
IE_NAME = 'wnl'
|
class NTRIE(NPOPlaylistBaseIE):
|
||||||
_VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
|
IE_NAME = 'ntr'
|
||||||
_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
|
_VALID_URL = r'https?://(?:www\.)?ntr\.nl/(?:[^/]+/)+(?P<id>[^/?#&]+)'
|
||||||
_PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
|
_PLAYLIST_TITLE_RE = r'<h2[^>]*>\s*(.+)\s*</h2>'
|
||||||
|
_PLAYLIST_ENTRY_RE = r'<div[^>]+class=["\']npo_wrapper["\'][^>]+data-mid=["\'](.+?)["\']'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
|
'url': 'https://ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944',
|
||||||
|
'md5': '5b7b45c15750c9a74f8b70ea69f0b55a',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'vandaag-de-dag-6-mei',
|
'id': 'VPWON_1233944',
|
||||||
'title': 'Vandaag de Dag 6 mei',
|
'ext': 'mp4',
|
||||||
|
'duration': 599.98,
|
||||||
|
'channel_id': 'NED3',
|
||||||
|
'genres': ['Jeugd', 'Serie'],
|
||||||
|
'description': 'Appie en Aisia mogen beurtelings mee met hun vader Luc, die in de dierentuin werkt.',
|
||||||
|
'uploader_id': 'NED3',
|
||||||
|
'title': 'Aap, poot, pies',
|
||||||
|
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/608116',
|
||||||
},
|
},
|
||||||
'playlist_count': 4,
|
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
def _download_token(self, mid, url):
|
||||||
|
return self._download_json(f'https://ntr.nl/ajax/player/embed/{mid}', mid, 'Downloading token JSON')['jwt']
|
||||||
|
|
||||||
class AndereTijdenIE(NPOPlaylistBaseIE):
|
|
||||||
|
class AndereTijdenIE(NTRIE):
|
||||||
IE_NAME = 'anderetijden'
|
IE_NAME = 'anderetijden'
|
||||||
_VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
|
||||||
_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
|
_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
|
||||||
_PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
|
_PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container\s+episode-page["\'][^>]+data-mid=["\'](.+?)["\']'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
|
'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
|
||||||
|
|
|
@ -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')),
|
|
||||||
})
|
|
|
@ -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)')
|
|
Loading…
Reference in New Issue
Block a user