2018-07-28 15:29:56 -04:00
|
|
|
|
import functools
|
2018-06-13 09:46:00 -04:00
|
|
|
|
import json
|
|
|
|
|
import re
|
2024-03-04 11:42:46 -05:00
|
|
|
|
import urllib.parse
|
2013-06-23 14:09:47 -04:00
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2023-07-09 03:53:02 -04:00
|
|
|
|
from ..networking.exceptions import HTTPError
|
2014-12-13 06:24:42 -05:00
|
|
|
|
from ..utils import (
|
2022-06-18 19:17:08 -04:00
|
|
|
|
ExtractorError,
|
|
|
|
|
OnDemandPagedList,
|
2019-11-26 16:01:34 -05:00
|
|
|
|
age_restricted,
|
|
|
|
|
clean_html,
|
2024-11-03 18:02:48 -05:00
|
|
|
|
extract_attributes,
|
2014-12-13 06:24:42 -05:00
|
|
|
|
int_or_none,
|
2022-06-18 19:17:08 -04:00
|
|
|
|
traverse_obj,
|
2018-10-04 15:02:58 -04:00
|
|
|
|
try_get,
|
2014-04-23 08:42:34 -04:00
|
|
|
|
unescapeHTML,
|
2022-06-18 19:17:08 -04:00
|
|
|
|
unsmuggle_url,
|
2024-11-03 18:02:48 -05:00
|
|
|
|
update_url,
|
|
|
|
|
url_or_none,
|
2018-07-28 15:29:56 -04:00
|
|
|
|
urlencode_postdata,
|
2013-06-23 14:09:47 -04:00
|
|
|
|
)
|
|
|
|
|
|
2014-11-23 14:41:03 -05:00
|
|
|
|
|
2013-09-29 06:44:02 -04:00
|
|
|
|
class DailymotionBaseInfoExtractor(InfoExtractor):
|
2019-11-26 16:01:34 -05:00
|
|
|
|
_FAMILY_FILTER = None
|
|
|
|
|
_HEADERS = {
|
|
|
|
|
'Content-Type': 'application/json',
|
|
|
|
|
'Origin': 'https://www.dailymotion.com',
|
|
|
|
|
}
|
|
|
|
|
_NETRC_MACHINE = 'dailymotion'
|
2013-08-07 12:59:11 -04:00
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
def _get_dailymotion_cookies(self):
|
|
|
|
|
return self._get_cookies('https://www.dailymotion.com/')
|
2015-07-24 09:29:44 -04:00
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _get_cookie_value(cookies, name):
|
2020-05-04 18:09:07 -04:00
|
|
|
|
cookie = cookies.get(name)
|
2019-11-26 16:01:34 -05:00
|
|
|
|
if cookie:
|
|
|
|
|
return cookie.value
|
|
|
|
|
|
|
|
|
|
def _set_dailymotion_cookie(self, name, value):
|
|
|
|
|
self._set_cookie('www.dailymotion.com', name, value)
|
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
cookies = self._get_dailymotion_cookies()
|
|
|
|
|
ff = self._get_cookie_value(cookies, 'ff')
|
2021-05-17 08:23:08 -04:00
|
|
|
|
self._FAMILY_FILTER = ff == 'on' if ff else age_restricted(18, self.get_param('age_limit'))
|
2019-11-26 16:01:34 -05:00
|
|
|
|
self._set_dailymotion_cookie('ff', 'on' if self._FAMILY_FILTER else 'off')
|
|
|
|
|
|
2024-03-04 11:42:46 -05:00
|
|
|
|
def _get_token(self, xid):
|
|
|
|
|
cookies = self._get_dailymotion_cookies()
|
|
|
|
|
token = self._get_cookie_value(cookies, 'access_token') or self._get_cookie_value(cookies, 'client_token')
|
|
|
|
|
if token:
|
|
|
|
|
return token
|
|
|
|
|
|
|
|
|
|
data = {
|
|
|
|
|
'client_id': 'f1a362d288c1b98099c7',
|
|
|
|
|
'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5',
|
|
|
|
|
}
|
|
|
|
|
username, password = self._get_login_info()
|
|
|
|
|
if username:
|
|
|
|
|
data.update({
|
|
|
|
|
'grant_type': 'password',
|
|
|
|
|
'password': password,
|
|
|
|
|
'username': username,
|
|
|
|
|
})
|
|
|
|
|
else:
|
|
|
|
|
data['grant_type'] = 'client_credentials'
|
|
|
|
|
try:
|
|
|
|
|
token = self._download_json(
|
|
|
|
|
'https://graphql.api.dailymotion.com/oauth/token',
|
|
|
|
|
None, 'Downloading Access Token',
|
|
|
|
|
data=urlencode_postdata(data))['access_token']
|
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
|
|
|
|
|
raise ExtractorError(self._parse_json(
|
|
|
|
|
e.cause.response.read().decode(), xid)['error_description'], expected=True)
|
|
|
|
|
raise
|
|
|
|
|
self._set_dailymotion_cookie('access_token' if username else 'client_token', token)
|
|
|
|
|
return token
|
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
def _call_api(self, object_type, xid, object_fields, note, filter_extra=None):
|
|
|
|
|
if not self._HEADERS.get('Authorization'):
|
2024-03-04 11:42:46 -05:00
|
|
|
|
self._HEADERS['Authorization'] = f'Bearer {self._get_token(xid)}'
|
2019-11-26 16:01:34 -05:00
|
|
|
|
|
|
|
|
|
resp = self._download_json(
|
|
|
|
|
'https://graphql.api.dailymotion.com/', xid, note, data=json.dumps({
|
|
|
|
|
'query': '''{
|
|
|
|
|
%s(xid: "%s"%s) {
|
|
|
|
|
%s
|
|
|
|
|
}
|
2024-06-11 19:09:58 -04:00
|
|
|
|
}''' % (object_type, xid, ', ' + filter_extra if filter_extra else '', object_fields), # noqa: UP031
|
2019-11-26 16:01:34 -05:00
|
|
|
|
}).encode(), headers=self._HEADERS)
|
|
|
|
|
obj = resp['data'][object_type]
|
|
|
|
|
if not obj:
|
|
|
|
|
raise ExtractorError(resp['errors'][0]['message'], expected=True)
|
|
|
|
|
return obj
|
2014-11-23 14:41:03 -05:00
|
|
|
|
|
2013-06-23 14:09:47 -04:00
|
|
|
|
|
2015-07-23 12:04:47 -04:00
|
|
|
|
class DailymotionIE(DailymotionBaseInfoExtractor):
|
2019-08-29 12:08:19 -04:00
|
|
|
|
_VALID_URL = r'''(?ix)
|
|
|
|
|
https?://
|
2024-11-03 18:27:54 -05:00
|
|
|
|
(?:
|
|
|
|
|
dai\.ly/|
|
2019-08-29 12:08:19 -04:00
|
|
|
|
(?:
|
2024-11-03 18:02:48 -05:00
|
|
|
|
(?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}|
|
|
|
|
|
(?:www\.)?lequipe\.fr
|
|
|
|
|
)/
|
|
|
|
|
(?:
|
|
|
|
|
swf/(?!video)|
|
|
|
|
|
(?:(?:crawler|embed|swf)/)?video/|
|
|
|
|
|
player(?:/[\da-z]+)?\.html\?(?:video|(?P<is_playlist>playlist))=
|
2019-08-29 12:08:19 -04:00
|
|
|
|
)
|
2024-11-03 18:27:54 -05:00
|
|
|
|
)
|
2024-11-03 18:02:48 -05:00
|
|
|
|
(?P<id>[^/?_&#]+)(?:[\w-]*\?playlist=(?P<playlist_id>x[0-9a-z]+))?
|
|
|
|
|
'''
|
2014-08-27 13:20:20 -04:00
|
|
|
|
IE_NAME = 'dailymotion'
|
2022-07-31 21:23:25 -04:00
|
|
|
|
_EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
|
2017-05-13 22:55:40 -04:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
|
|
|
|
|
'md5': '074b95bdee76b9e3654137aee9c79dfe',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x5kesuj',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
|
2023-11-15 18:19:34 -05:00
|
|
|
|
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'duration': 187,
|
|
|
|
|
'timestamp': 1493651285,
|
|
|
|
|
'upload_date': '20170501',
|
|
|
|
|
'uploader': 'Deadline',
|
|
|
|
|
'uploader_id': 'x1xm8ri',
|
|
|
|
|
'age_limit': 0,
|
2023-11-15 18:19:34 -05:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'tags': ['hollywood', 'celeb', 'celebrity', 'movies', 'red carpet'],
|
2024-11-03 18:27:54 -05:00
|
|
|
|
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1cmt4ZcZ9KiM/x1080',
|
2017-05-01 14:37:23 -04:00
|
|
|
|
},
|
2022-03-30 06:04:00 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://geo.dailymotion.com/player.html?video=x89eyek&mute=true',
|
|
|
|
|
'md5': 'e2f9717c6604773f963f069ca53a07f8',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x89eyek',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': "En quête d'esprit du 27/03/2022",
|
|
|
|
|
'description': 'md5:66542b9f4df2eb23f314fc097488e553',
|
|
|
|
|
'duration': 2756,
|
|
|
|
|
'timestamp': 1648383669,
|
|
|
|
|
'upload_date': '20220327',
|
|
|
|
|
'uploader': 'CNEWS',
|
|
|
|
|
'uploader_id': 'x24vth',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'tags': ['en_quete_d_esprit'],
|
2024-11-03 18:27:54 -05:00
|
|
|
|
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1clTH6StrxMP/x1080',
|
2024-06-11 19:09:58 -04:00
|
|
|
|
},
|
2017-05-13 22:55:40 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
|
|
|
|
|
'md5': '2137c41a8e78554bb09225b8eb322406',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x2iuewm',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
|
|
|
|
|
'description': 'Several come bundled with the Steam Controller.',
|
|
|
|
|
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
|
|
|
|
|
'duration': 74,
|
|
|
|
|
'timestamp': 1425657362,
|
|
|
|
|
'upload_date': '20150306',
|
|
|
|
|
'uploader': 'IGN',
|
|
|
|
|
'uploader_id': 'xijv66',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'view_count': int,
|
2013-10-01 09:05:41 -04:00
|
|
|
|
},
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'skip': 'video gone',
|
|
|
|
|
}, {
|
2013-10-01 09:05:41 -04:00
|
|
|
|
# Vevo video
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'Roar (Official)',
|
|
|
|
|
'id': 'USUV71301934',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader': 'Katy Perry',
|
|
|
|
|
'upload_date': '20130905',
|
2013-10-01 09:05:41 -04:00
|
|
|
|
},
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
'skip': 'VEVO is only available in some countries',
|
|
|
|
|
}, {
|
2013-10-30 19:20:49 -04:00
|
|
|
|
# age-restricted video
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
|
|
|
|
|
'md5': '0d667a7b9cebecc3c89ee93099c4159d',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'xyh2zz',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
|
|
|
|
|
'uploader': 'HotWaves1012',
|
|
|
|
|
'age_limit': 18,
|
2015-10-17 13:26:30 -04:00
|
|
|
|
},
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'skip': 'video gone',
|
|
|
|
|
}, {
|
2015-10-17 13:26:30 -04:00
|
|
|
|
# geo-restricted, player v5
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'url': 'http://www.dailymotion.com/video/xhza0o',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
2015-12-10 10:54:48 -05:00
|
|
|
|
# with subtitles
|
2017-05-13 22:55:40 -04:00
|
|
|
|
'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.dailymotion.com/swf/x3ss1m_funny-magic-trick-barry-and-stuart_fun',
|
|
|
|
|
'only_matching': True,
|
2019-08-29 12:08:19 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.lequipe.fr/video/x791mem',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.lequipe.fr/video/k7MtHciueyTcrFtFKA2',
|
|
|
|
|
'only_matching': True,
|
2019-11-26 16:01:34 -05:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.dailymotion.com/video/x3z49k?playlist=xv4bw',
|
|
|
|
|
'only_matching': True,
|
2023-11-15 18:19:34 -05:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://geo.dailymotion.com/player/x86gw.html?video=k46oCapRs4iikoz9DWy',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://geo.dailymotion.com/player/xakln.html?video=x8mjju4&customConfig%5BcustomParams%5D=%2Ffr-fr%2Ftennis%2Fwimbledon-mens-singles%2Farticles-video',
|
|
|
|
|
'only_matching': True,
|
2024-11-03 18:02:48 -05:00
|
|
|
|
}, { # playlist-only
|
|
|
|
|
'url': 'https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://geo.dailymotion.com/player/xmyye.html?video=x93blhi',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.dailymotion.com/crawler/video/x8u4owg',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.dailymotion.com/embed/video/x8u4owg',
|
|
|
|
|
'only_matching': True,
|
2024-11-03 18:27:54 -05:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://dai.ly/x94cnnk',
|
|
|
|
|
'only_matching': True,
|
2024-11-03 18:02:48 -05:00
|
|
|
|
}]
|
|
|
|
|
_WEBPAGE_TESTS = [{
|
|
|
|
|
# https://geo.dailymotion.com/player/xmyye.html?video=x93blhi
|
|
|
|
|
'url': 'https://www.financialounge.com/video/2024/08/01/borse-europee-in-rosso-dopo-la-fed-a-milano-volano-mediobanca-e-tim-edizione-del-1-agosto/',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x93blhi',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'OnAir - 01/08/24',
|
|
|
|
|
'description': '',
|
|
|
|
|
'duration': 217,
|
|
|
|
|
'timestamp': 1722505658,
|
|
|
|
|
'upload_date': '20240801',
|
|
|
|
|
'uploader': 'Financialounge',
|
|
|
|
|
'uploader_id': 'x2vtgmm',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'like_count': int,
|
2024-11-23 13:51:51 -05:00
|
|
|
|
'thumbnail': r're:https://\w+.dmcdn.net/v/WnEY61cmvMxt2Fi6d/x1080',
|
2024-11-03 18:02:48 -05:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
# https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj
|
|
|
|
|
'url': 'https://www.cycleworld.com/blogs/ask-kevin/ducati-continues-to-evolve-with-v4/',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x7wdsj',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 50,
|
|
|
|
|
}, {
|
|
|
|
|
# https://www.dailymotion.com/crawler/video/x8u4owg
|
|
|
|
|
'url': 'https://www.leparisien.fr/environnement/video-le-veloto-la-voiture-a-pedales-qui-aimerait-se-faire-une-place-sur-les-routes-09-03-2024-KCYMCPM4WFHJXMSKBUI66UNFPU.php',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x8u4owg',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'uploader': 'Le Parisien',
|
|
|
|
|
'thumbnail': 'https://www.leparisien.fr/resizer/ho_GwveeYftNkLwg_cEta--5Bv4=/1200x675/cloudfront-eu-central-1.images.arcpublishing.com/leparisien/BFXJNEBN75EUNHGYJLORUC3TX4.jpg',
|
|
|
|
|
'upload_date': '20240309',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'timestamp': 1709997866,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'uploader_id': 'x32f7b',
|
|
|
|
|
'title': 'VIDÉO. Le «\xa0véloto\xa0», la voiture à pédales qui aimerait se faire une place sur les routes',
|
|
|
|
|
'duration': 428.0,
|
|
|
|
|
'description': 'À bord du « véloto », l’alternative à la voiture pour la campagne',
|
|
|
|
|
'tags': ['biclou', 'vélo', 'véloto', 'campagne', 'voiture', 'environnement', 'véhicules intermédiaires'],
|
|
|
|
|
},
|
2024-11-23 13:51:51 -05:00
|
|
|
|
}, {
|
|
|
|
|
# https://geo.dailymotion.com/player/xry80.html?video=x8vu47w
|
|
|
|
|
'url': 'https://www.metatube.com/en/videos/546765/This-frogs-decorates-Christmas-tree/',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x8vu47w',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'uploader': 'Metatube',
|
|
|
|
|
'thumbnail': r're:https://\w+.dmcdn.net/v/W1G_S1coGSFTfkTeR/x1080',
|
|
|
|
|
'upload_date': '20240326',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'timestamp': 1711496732,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'uploader_id': 'x2xpy74',
|
|
|
|
|
'title': 'Está lindas ranitas ponen su arbolito',
|
|
|
|
|
'duration': 28,
|
|
|
|
|
'description': 'Que lindura',
|
|
|
|
|
'tags': [],
|
|
|
|
|
},
|
2017-05-13 22:55:40 -04:00
|
|
|
|
}]
|
2019-11-26 16:01:34 -05:00
|
|
|
|
_GEO_BYPASS = False
|
|
|
|
|
_COMMON_MEDIA_FIELDS = '''description
|
|
|
|
|
geoblockedCountries {
|
|
|
|
|
allowed
|
|
|
|
|
}
|
|
|
|
|
xid'''
|
2013-06-23 14:09:47 -04:00
|
|
|
|
|
2022-07-31 21:23:25 -04:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_embed_urls(cls, url, webpage):
|
2019-07-01 03:37:21 -04:00
|
|
|
|
# https://developer.dailymotion.com/player#player-parameters
|
2022-07-31 21:23:25 -04:00
|
|
|
|
yield from super()._extract_embed_urls(url, webpage)
|
2019-07-01 03:37:21 -04:00
|
|
|
|
for mobj in re.finditer(
|
|
|
|
|
r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
|
2024-11-23 13:51:51 -05:00
|
|
|
|
yield 'https://www.dailymotion.com/embed/video/' + mobj.group('id')
|
2024-11-03 18:02:48 -05:00
|
|
|
|
for mobj in re.finditer(
|
|
|
|
|
r'(?s)<script [^>]*\bsrc=(["\'])(?:https?:)?//[\w-]+\.dailymotion\.com/player/(?:(?!\1).)+\1[^>]*>', webpage):
|
|
|
|
|
attrs = extract_attributes(mobj.group(0))
|
|
|
|
|
player_url = url_or_none(attrs.get('src'))
|
|
|
|
|
if not player_url:
|
|
|
|
|
continue
|
|
|
|
|
player_url = player_url.replace('.js', '.html')
|
|
|
|
|
if player_url.startswith('//'):
|
|
|
|
|
player_url = f'https:{player_url}'
|
|
|
|
|
if video_id := attrs.get('data-video'):
|
|
|
|
|
query_string = f'video={video_id}'
|
|
|
|
|
elif playlist_id := attrs.get('data-playlist'):
|
|
|
|
|
query_string = f'playlist={playlist_id}'
|
|
|
|
|
else:
|
|
|
|
|
continue
|
|
|
|
|
yield update_url(player_url, query=query_string)
|
2016-07-06 11:37:54 -04:00
|
|
|
|
|
2013-06-23 14:09:47 -04:00
|
|
|
|
def _real_extract(self, url):
|
2022-06-18 19:17:08 -04:00
|
|
|
|
url, smuggled_data = unsmuggle_url(url)
|
2024-11-03 18:02:48 -05:00
|
|
|
|
video_id, is_playlist, playlist_id = self._match_valid_url(url).group('id', 'is_playlist', 'playlist_id')
|
|
|
|
|
|
|
|
|
|
if is_playlist: # We matched the playlist query param as video_id
|
|
|
|
|
playlist_id = video_id
|
|
|
|
|
video_id = None
|
2019-11-26 16:01:34 -05:00
|
|
|
|
|
2024-11-03 18:02:48 -05:00
|
|
|
|
if self._yes_playlist(playlist_id, video_id):
|
|
|
|
|
return self.url_result(
|
|
|
|
|
f'http://www.dailymotion.com/playlist/{playlist_id}',
|
|
|
|
|
'DailymotionPlaylist', playlist_id)
|
2019-11-26 16:01:34 -05:00
|
|
|
|
|
2021-05-17 08:23:08 -04:00
|
|
|
|
password = self.get_param('videopassword')
|
2019-11-26 16:01:34 -05:00
|
|
|
|
media = self._call_api(
|
|
|
|
|
'media', video_id, '''... on Video {
|
|
|
|
|
%s
|
|
|
|
|
stats {
|
|
|
|
|
likes {
|
|
|
|
|
total
|
|
|
|
|
}
|
|
|
|
|
views {
|
|
|
|
|
total
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
... on Live {
|
|
|
|
|
%s
|
|
|
|
|
audienceCount
|
|
|
|
|
isOnAir
|
2024-06-11 19:09:58 -04:00
|
|
|
|
}''' % (self._COMMON_MEDIA_FIELDS, self._COMMON_MEDIA_FIELDS), 'Downloading media JSON metadata', # noqa: UP031
|
|
|
|
|
'password: "{}"'.format(self.get_param('videopassword')) if password else None)
|
2019-11-26 16:01:34 -05:00
|
|
|
|
xid = media['xid']
|
|
|
|
|
|
|
|
|
|
metadata = self._download_json(
|
|
|
|
|
'https://www.dailymotion.com/player/metadata/video/' + xid,
|
|
|
|
|
xid, 'Downloading metadata JSON',
|
2022-06-18 19:17:08 -04:00
|
|
|
|
query=traverse_obj(smuggled_data, 'query') or {'app': 'com.dailymotion.neon'})
|
2019-11-26 16:01:34 -05:00
|
|
|
|
|
|
|
|
|
error = metadata.get('error')
|
|
|
|
|
if error:
|
|
|
|
|
title = error.get('title') or error['raw_message']
|
|
|
|
|
# See https://developer.dailymotion.com/api#access-error
|
|
|
|
|
if error.get('code') == 'DM007':
|
|
|
|
|
allowed_countries = try_get(media, lambda x: x['geoblockedCountries']['allowed'], list)
|
|
|
|
|
self.raise_geo_restricted(msg=title, countries=allowed_countries)
|
|
|
|
|
raise ExtractorError(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'{self.IE_NAME} said: {title}', expected=True)
|
2013-07-05 08:15:26 -04:00
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
title = metadata['title']
|
|
|
|
|
is_live = media.get('isOnAir')
|
2013-10-23 11:33:38 -04:00
|
|
|
|
formats = []
|
2024-11-03 18:02:48 -05:00
|
|
|
|
subtitles = {}
|
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
for quality, media_list in metadata['qualities'].items():
|
|
|
|
|
for m in media_list:
|
|
|
|
|
media_url = m.get('url')
|
|
|
|
|
media_type = m.get('type')
|
|
|
|
|
if not media_url or media_type == 'application/vnd.lumberjack.manifest':
|
|
|
|
|
continue
|
|
|
|
|
if media_type == 'application/x-mpegURL':
|
2024-11-03 18:02:48 -05:00
|
|
|
|
fmt, subs = self._extract_m3u8_formats_and_subtitles(
|
|
|
|
|
media_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False)
|
|
|
|
|
formats.extend(fmt)
|
|
|
|
|
self._merge_subtitles(subs, target=subtitles)
|
2013-10-23 11:33:38 -04:00
|
|
|
|
else:
|
2019-11-26 16:01:34 -05:00
|
|
|
|
f = {
|
|
|
|
|
'url': media_url,
|
|
|
|
|
'format_id': 'http-' + quality,
|
|
|
|
|
}
|
|
|
|
|
m = re.search(r'/H264-(\d+)x(\d+)(?:-(60)/)?', media_url)
|
|
|
|
|
if m:
|
|
|
|
|
width, height, fps = map(int_or_none, m.groups())
|
|
|
|
|
f.update({
|
|
|
|
|
'fps': fps,
|
|
|
|
|
'height': height,
|
|
|
|
|
'width': width,
|
|
|
|
|
})
|
|
|
|
|
formats.append(f)
|
|
|
|
|
for f in formats:
|
|
|
|
|
f['url'] = f['url'].split('#')[0]
|
|
|
|
|
if not f.get('fps') and f['format_id'].endswith('@60'):
|
|
|
|
|
f['fps'] = 60
|
2013-07-05 08:15:26 -04:00
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
subtitles_data = try_get(metadata, lambda x: x['subtitles']['data'], dict) or {}
|
|
|
|
|
for subtitle_lang, subtitle in subtitles_data.items():
|
|
|
|
|
subtitles[subtitle_lang] = [{
|
|
|
|
|
'url': subtitle_url,
|
|
|
|
|
} for subtitle_url in subtitle.get('urls', [])]
|
|
|
|
|
|
2024-11-03 18:27:54 -05:00
|
|
|
|
thumbnails = traverse_obj(metadata, (
|
|
|
|
|
('posters', 'thumbnails'), {dict.items}, lambda _, v: url_or_none(v[1]), {
|
|
|
|
|
'height': (0, {int_or_none}),
|
|
|
|
|
'id': (0, {str}),
|
|
|
|
|
'url': 1,
|
|
|
|
|
}))
|
2019-11-26 16:01:34 -05:00
|
|
|
|
|
|
|
|
|
owner = metadata.get('owner') or {}
|
|
|
|
|
stats = media.get('stats') or {}
|
|
|
|
|
get_count = lambda x: int_or_none(try_get(stats, lambda y: y[x + 's']['total']))
|
2013-12-06 07:36:36 -05:00
|
|
|
|
|
2013-10-30 19:20:49 -04:00
|
|
|
|
return {
|
2014-10-05 15:59:53 -04:00
|
|
|
|
'id': video_id,
|
2021-12-15 11:00:46 -05:00
|
|
|
|
'title': title,
|
2019-11-26 16:01:34 -05:00
|
|
|
|
'description': clean_html(media.get('description')),
|
|
|
|
|
'thumbnails': thumbnails,
|
|
|
|
|
'duration': int_or_none(metadata.get('duration')) or None,
|
|
|
|
|
'timestamp': int_or_none(metadata.get('created_time')),
|
|
|
|
|
'uploader': owner.get('screenname'),
|
|
|
|
|
'uploader_id': owner.get('id') or metadata.get('screenname'),
|
|
|
|
|
'age_limit': 18 if metadata.get('explicit') else 0,
|
|
|
|
|
'tags': metadata.get('tags'),
|
|
|
|
|
'view_count': get_count('view') or int_or_none(media.get('audienceCount')),
|
|
|
|
|
'like_count': get_count('like'),
|
2013-10-23 11:33:38 -04:00
|
|
|
|
'formats': formats,
|
2019-11-26 16:01:34 -05:00
|
|
|
|
'subtitles': subtitles,
|
|
|
|
|
'is_live': is_live,
|
2013-10-30 19:20:49 -04:00
|
|
|
|
}
|
2013-07-29 06:07:38 -04:00
|
|
|
|
|
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
class DailymotionPlaylistBaseIE(DailymotionBaseInfoExtractor):
|
2018-07-28 15:29:56 -04:00
|
|
|
|
_PAGE_SIZE = 100
|
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
def _fetch_page(self, playlist_id, page):
|
2018-07-28 15:29:56 -04:00
|
|
|
|
page += 1
|
2019-11-26 16:01:34 -05:00
|
|
|
|
videos = self._call_api(
|
|
|
|
|
self._OBJECT_TYPE, playlist_id,
|
|
|
|
|
'''videos(allowExplicit: %s, first: %d, page: %d) {
|
2018-07-28 15:29:56 -04:00
|
|
|
|
edges {
|
|
|
|
|
node {
|
|
|
|
|
xid
|
|
|
|
|
url
|
|
|
|
|
}
|
|
|
|
|
}
|
2019-11-26 16:01:34 -05:00
|
|
|
|
}''' % ('false' if self._FAMILY_FILTER else 'true', self._PAGE_SIZE, page),
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'Downloading page {page}')['videos']
|
2018-07-28 15:29:56 -04:00
|
|
|
|
for edge in videos['edges']:
|
|
|
|
|
node = edge['node']
|
|
|
|
|
yield self.url_result(
|
|
|
|
|
node['url'], DailymotionIE.ie_key(), node['xid'])
|
2013-09-21 06:45:53 -04:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2018-07-28 15:29:56 -04:00
|
|
|
|
playlist_id = self._match_id(url)
|
|
|
|
|
entries = OnDemandPagedList(functools.partial(
|
2019-11-26 16:01:34 -05:00
|
|
|
|
self._fetch_page, playlist_id), self._PAGE_SIZE)
|
2018-07-28 15:29:56 -04:00
|
|
|
|
return self.playlist_result(
|
2019-11-26 16:01:34 -05:00
|
|
|
|
entries, playlist_id)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class DailymotionPlaylistIE(DailymotionPlaylistBaseIE):
|
|
|
|
|
IE_NAME = 'dailymotion:playlist'
|
|
|
|
|
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>x[0-9a-z]+)'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'xv4bw',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 20,
|
|
|
|
|
}]
|
|
|
|
|
_OBJECT_TYPE = 'collection'
|
2018-07-28 15:29:56 -04:00
|
|
|
|
|
2022-07-31 21:23:25 -04:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_embed_urls(cls, url, webpage):
|
|
|
|
|
# Look for embedded Dailymotion playlist player (#3822)
|
|
|
|
|
for mobj in re.finditer(
|
|
|
|
|
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1',
|
|
|
|
|
webpage):
|
|
|
|
|
for p in re.findall(r'list\[\]=/playlist/([^/]+)/', unescapeHTML(mobj.group('url'))):
|
2024-06-11 19:09:58 -04:00
|
|
|
|
yield f'//dailymotion.com/playlist/{p}'
|
2022-07-31 21:23:25 -04:00
|
|
|
|
|
2018-07-28 15:29:56 -04:00
|
|
|
|
|
2024-03-04 11:42:46 -05:00
|
|
|
|
class DailymotionSearchIE(DailymotionPlaylistBaseIE):
|
|
|
|
|
IE_NAME = 'dailymotion:search'
|
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/search/(?P<id>[^/?#]+)/videos'
|
|
|
|
|
_PAGE_SIZE = 20
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'http://www.dailymotion.com/search/king of turtles/videos',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'king of turtles',
|
|
|
|
|
'title': 'king of turtles',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 90,
|
|
|
|
|
}]
|
|
|
|
|
_SEARCH_QUERY = 'query SEARCH_QUERY( $query: String! $page: Int $limit: Int ) { search { videos( query: $query first: $limit page: $page ) { edges { node { xid } } } } } '
|
|
|
|
|
|
|
|
|
|
def _call_search_api(self, term, page, note):
|
|
|
|
|
if not self._HEADERS.get('Authorization'):
|
|
|
|
|
self._HEADERS['Authorization'] = f'Bearer {self._get_token(term)}'
|
|
|
|
|
resp = self._download_json(
|
|
|
|
|
'https://graphql.api.dailymotion.com/', None, note, data=json.dumps({
|
|
|
|
|
'operationName': 'SEARCH_QUERY',
|
|
|
|
|
'query': self._SEARCH_QUERY,
|
|
|
|
|
'variables': {
|
|
|
|
|
'limit': 20,
|
|
|
|
|
'page': page,
|
|
|
|
|
'query': term,
|
2024-06-11 19:09:58 -04:00
|
|
|
|
},
|
2024-03-04 11:42:46 -05:00
|
|
|
|
}).encode(), headers=self._HEADERS)
|
|
|
|
|
obj = traverse_obj(resp, ('data', 'search', {dict}))
|
|
|
|
|
if not obj:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
traverse_obj(resp, ('errors', 0, 'message', {str})) or 'Could not fetch search data')
|
|
|
|
|
|
|
|
|
|
return obj
|
|
|
|
|
|
|
|
|
|
def _fetch_page(self, term, page):
|
|
|
|
|
page += 1
|
|
|
|
|
response = self._call_search_api(term, page, f'Searching "{term}" page {page}')
|
|
|
|
|
for xid in traverse_obj(response, ('videos', 'edges', ..., 'node', 'xid')):
|
|
|
|
|
yield self.url_result(f'https://www.dailymotion.com/video/{xid}', DailymotionIE, xid)
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
term = urllib.parse.unquote_plus(self._match_id(url))
|
|
|
|
|
return self.playlist_result(
|
|
|
|
|
OnDemandPagedList(functools.partial(self._fetch_page, term), self._PAGE_SIZE), term, term)
|
|
|
|
|
|
|
|
|
|
|
2019-11-26 16:01:34 -05:00
|
|
|
|
class DailymotionUserIE(DailymotionPlaylistBaseIE):
|
2014-08-27 18:58:24 -04:00
|
|
|
|
IE_NAME = 'dailymotion:user'
|
2024-11-03 18:02:48 -05:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist|search|crawler)/)(?:(?:old/)?user/)?(?P<id>[^/?#]+)'
|
2014-08-27 18:58:24 -04:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'https://www.dailymotion.com/user/nqtv',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'nqtv',
|
|
|
|
|
},
|
2019-11-26 16:01:34 -05:00
|
|
|
|
'playlist_mincount': 152,
|
2015-07-24 09:29:44 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.dailymotion.com/user/UnderProject',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UnderProject',
|
|
|
|
|
},
|
2019-11-26 16:01:34 -05:00
|
|
|
|
'playlist_mincount': 1000,
|
2015-07-24 09:29:44 -04:00
|
|
|
|
'skip': 'Takes too long time',
|
2019-11-26 16:01:34 -05:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.dailymotion.com/user/nqtv',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'nqtv',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 148,
|
|
|
|
|
'params': {
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
},
|
2014-08-27 18:58:24 -04:00
|
|
|
|
}]
|
2019-11-26 16:01:34 -05:00
|
|
|
|
_OBJECT_TYPE = 'channel'
|