mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-05-12 08:09:31 +00:00
Compare commits
15 commits
9a40cd1ef6
...
e9636033e5
Author | SHA1 | Date | |
---|---|---|---|
e9636033e5 | |||
668332b973 | |||
0b2ce3685e | |||
c2766cb80e | |||
eb38665438 | |||
20691a11e6 | |||
585e806d9a | |||
e4c57418df | |||
d7939e2c07 | |||
4a48a17eea | |||
52858d5879 | |||
050b52baf9 | |||
11bd5b9612 | |||
33650c8eb6 | |||
7cc35d1051 |
|
@ -10,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|||
|
||||
from test.helper import (
|
||||
assertGreaterEqual,
|
||||
assertLessEqual,
|
||||
expect_warnings,
|
||||
get_params,
|
||||
gettestcases,
|
||||
|
@ -122,7 +123,10 @@ def generator(test_case, tname):
|
|||
params['outtmpl'] = tname + '_' + params['outtmpl']
|
||||
if is_playlist and 'playlist' not in test_case:
|
||||
params.setdefault('extract_flat', 'in_playlist')
|
||||
params.setdefault('playlistend', test_case.get('playlist_mincount'))
|
||||
params.setdefault('playlistend',
|
||||
test_case['playlist_maxcount'] + 1
|
||||
if test_case.get('playlist_maxcount')
|
||||
else test_case.get('playlist_mincount'))
|
||||
params.setdefault('skip_download', True)
|
||||
|
||||
ydl = YoutubeDL(params, auto_init=False)
|
||||
|
@ -190,6 +194,14 @@ def generator(test_case, tname):
|
|||
'Expected at least %d in playlist %s, but got only %d' % (
|
||||
test_case['playlist_mincount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
if 'playlist_maxcount' in test_case:
|
||||
assertLessEqual(
|
||||
self,
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_maxcount'],
|
||||
'Expected at most %d in playlist %s, but got %d' % (
|
||||
test_case['playlist_maxcount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
if 'playlist_count' in test_case:
|
||||
self.assertEqual(
|
||||
len(res_dict['entries']),
|
||||
|
|
|
@ -1073,7 +1073,7 @@ from .rtl2 import (
|
|||
)
|
||||
from .rtp import RTPIE
|
||||
from .rts import RTSIE
|
||||
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
|
||||
from .rtve import RTVEPlayIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
|
||||
from .rtvnh import RTVNHIE
|
||||
from .rtvs import RTVSIE
|
||||
from .ruhd import RUHDIE
|
||||
|
@ -1653,7 +1653,15 @@ from .younow import (
|
|||
YouNowChannelIE,
|
||||
YouNowMomentIE,
|
||||
)
|
||||
from .youporn import YouPornIE
|
||||
from .youporn import (
|
||||
YouPornIE,
|
||||
YouPornCategoryIE,
|
||||
YouPornChannelIE,
|
||||
YouPornCollectionIE,
|
||||
YouPornStarIE,
|
||||
YouPornTagIE,
|
||||
YouPornVideosIE,
|
||||
)
|
||||
from .yourporn import YourPornIE
|
||||
from .yourupload import YourUploadIE
|
||||
from .youtube import (
|
||||
|
|
|
@ -12,30 +12,30 @@ from ..compat import (
|
|||
compat_struct_unpack,
|
||||
)
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
qualities,
|
||||
remove_end,
|
||||
remove_start,
|
||||
std_headers,
|
||||
)
|
||||
|
||||
_bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
|
||||
|
||||
|
||||
class RTVEALaCartaIE(InfoExtractor):
|
||||
IE_NAME = 'rtve.es:alacarta'
|
||||
IE_DESC = 'RTVE a la carta'
|
||||
_VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
|
||||
class RTVEPlayIE(InfoExtractor):
|
||||
IE_NAME = 'rtve.es:play'
|
||||
IE_DESC = 'RTVE Play'
|
||||
_VALID_URL = r'https?://(?:www\.)?rtve\.es/(?P<kind>(?:playz?|(?:m/)?alacarta)/(?:audios|videos)|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
|
||||
'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
|
||||
'md5': '2c70aacf8a415d1b4e7fcc0525951162',
|
||||
'info_dict': {
|
||||
'id': '2491869',
|
||||
'ext': 'mp4',
|
||||
'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
|
||||
'title': 'Final de la Swiss Cup masculina: España-Suecia',
|
||||
'description': 'Swiss Cup masculina, Final: España-Suecia.',
|
||||
'duration': 5024.566,
|
||||
'series': 'Balonmano',
|
||||
},
|
||||
|
@ -47,6 +47,7 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
'id': '1694255',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'description': '24H LIVE',
|
||||
'is_live': True,
|
||||
},
|
||||
'params': {
|
||||
|
@ -54,11 +55,12 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
},
|
||||
}, {
|
||||
'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
|
||||
'md5': 'd850f3c8731ea53952ebab489cf81cbf',
|
||||
'md5': '30b8827cba25f39d1af5a7c482cc8ac5',
|
||||
'info_dict': {
|
||||
'id': '4236788',
|
||||
'ext': 'mp4',
|
||||
'title': 'Servir y proteger - Capítulo 104',
|
||||
'title': 'Capítulo 104',
|
||||
'description': 'md5:caae29ae04291875e611dd667fe84641',
|
||||
'duration': 3222.0,
|
||||
},
|
||||
'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
|
||||
|
@ -68,6 +70,17 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
}, {
|
||||
'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.rtve.es/alacarta/audios/a-hombros-de-gigantes/palabra-ingeniero-codigos-informaticos-27-04-21/5889192/',
|
||||
'md5': 'ae06d27bff945c4e87a50f89f6ce48ce',
|
||||
'info_dict': {
|
||||
'id': '5889192',
|
||||
'ext': 'mp3',
|
||||
'title': 'Códigos informáticos',
|
||||
'description': 'md5:72b0d7c1ca20fd327bdfff7ac0171afb',
|
||||
'thumbnail': r're:https?://.+/1598856591583.jpg',
|
||||
'duration': 349.440,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
|
@ -86,8 +99,12 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
break
|
||||
data = encrypted_data.read(length)
|
||||
if chunk_type == b'tEXt':
|
||||
alphabet_data, text = data.split(b'\0')
|
||||
quality, url_data = text.split(b'%%')
|
||||
alphabet_data, text = data.replace(b'\0', b'').split(b'#')
|
||||
components = text.split(b'%%')
|
||||
if len(components) < 2:
|
||||
components.insert(0, b'')
|
||||
quality, url_data = components
|
||||
|
||||
alphabet = []
|
||||
e = 0
|
||||
d = 0
|
||||
|
@ -120,7 +137,7 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
|
||||
def _extract_png_formats(self, video_id):
|
||||
png = self._download_webpage(
|
||||
'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
|
||||
'http://ztnr.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
|
||||
video_id, 'Downloading url information', query={'q': 'v2'})
|
||||
q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
|
||||
formats = []
|
||||
|
@ -143,11 +160,16 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
return formats
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
groups = re.match(self._VALID_URL, url).groupdict()
|
||||
is_audio = groups.get('kind') == 'play/audios'
|
||||
return self._real_extract_from_id(groups['id'], is_audio)
|
||||
|
||||
def _real_extract_from_id(self, video_id, is_audio=False):
|
||||
kind = 'audios' if is_audio else 'videos'
|
||||
info = self._download_json(
|
||||
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
|
||||
'http://www.rtve.es/api/%s/%s.json' % (kind, video_id),
|
||||
video_id)['page']['items'][0]
|
||||
if info['state'] == 'DESPU':
|
||||
if (info.get('pubState') or {}).get('code') == 'DESPU':
|
||||
raise ExtractorError('The video is no longer available', expected=True)
|
||||
title = info['title'].strip()
|
||||
formats = self._extract_png_formats(video_id)
|
||||
|
@ -157,17 +179,19 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
if sbt_file:
|
||||
subtitles = self.extract_subtitles(video_id, sbt_file)
|
||||
|
||||
is_live = info.get('live') is True
|
||||
is_live = info.get('consumption') == 'live'
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._live_title(title) if is_live else title,
|
||||
'formats': formats,
|
||||
'thumbnail': info.get('image'),
|
||||
'url': info.get('htmlUrl'),
|
||||
'description': clean_html(info.get('description')),
|
||||
'thumbnail': info.get('thumbnail'),
|
||||
'subtitles': subtitles,
|
||||
'duration': float_or_none(info.get('duration'), 1000),
|
||||
'is_live': is_live,
|
||||
'series': info.get('programTitle'),
|
||||
'series': (info.get('programInfo') or {}).get('title'),
|
||||
}
|
||||
|
||||
def _get_subtitles(self, video_id, sub_file):
|
||||
|
@ -179,36 +203,60 @@ class RTVEALaCartaIE(InfoExtractor):
|
|||
for s in subs)
|
||||
|
||||
|
||||
class RTVEInfantilIE(RTVEALaCartaIE):
|
||||
class RTVEInfantilIE(RTVEPlayIE):
|
||||
IE_NAME = 'rtve.es:infantil'
|
||||
IE_DESC = 'RTVE infantil'
|
||||
_VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
|
||||
'md5': '5747454717aedf9f9fdf212d1bcfc48d',
|
||||
'url': 'https://www.rtve.es/infantil/serie/dino-ranch/video/pequeno-gran-ayudante/6693248/',
|
||||
'md5': '06d3f57eec593ad93fe9dcf079fbd940',
|
||||
'info_dict': {
|
||||
'id': '3040283',
|
||||
'id': '6693248',
|
||||
'ext': 'mp4',
|
||||
'title': 'Maneras de vivir',
|
||||
'thumbnail': r're:https?://.+/1426182947956\.JPG',
|
||||
'duration': 357.958,
|
||||
'title': 'Un pequeño gran ayudante',
|
||||
'description': 'md5:144ca351e31f9ee99a637ab9fc2787d5',
|
||||
'thumbnail': r're:https?://.+/1663318364501\.jpg',
|
||||
'duration': 691.44,
|
||||
},
|
||||
'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
|
||||
}]
|
||||
|
||||
|
||||
class RTVELiveIE(RTVEALaCartaIE):
|
||||
class RTVELiveIE(RTVEPlayIE):
|
||||
IE_NAME = 'rtve.es:live'
|
||||
IE_DESC = 'RTVE.es live streams'
|
||||
_VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?rtve\.es/play/videos/directo/(?P<id>.+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.rtve.es/directo/la-1/',
|
||||
'url': 'https://www.rtve.es/play/videos/directo/la-1/',
|
||||
'info_dict': {
|
||||
'id': 'la-1',
|
||||
'id': '1688877',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'description': 'La 1',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'live stream',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.rtve.es/play/videos/directo/canales-lineales/la-1/',
|
||||
'info_dict': {
|
||||
'id': '1688877',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'description': 'La 1',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'live stream',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.rtve.es/play/videos/directo/canales-lineales/capilla-ardiente-isabel-westminster/10886/',
|
||||
'info_dict': {
|
||||
'id': '1938028',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^Mas24 - 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'description': 'Mas24 - 1',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'live stream',
|
||||
|
@ -216,53 +264,77 @@ class RTVELiveIE(RTVEALaCartaIE):
|
|||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
|
||||
title = remove_start(title, 'Estoy viendo ')
|
||||
|
||||
vidplayer_id = self._search_regex(
|
||||
(r'playerId=player([0-9]+)',
|
||||
r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
|
||||
r'data-id=["\'](\d+)'),
|
||||
webpage = self._download_webpage(url, self._match_id(url))
|
||||
asset_id = self._search_regex(
|
||||
r'class=["\'].*?\bvideoPlayer\b.*?["\'][^>]+data-setup=[^>]+?(?:"|")idAsset(?:"|")\s*:\s*(?:"|")(\d+)(?:"|")',
|
||||
webpage, 'internal video ID')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._live_title(title),
|
||||
'formats': self._extract_png_formats(vidplayer_id),
|
||||
'is_live': True,
|
||||
}
|
||||
return self._real_extract_from_id(asset_id)
|
||||
|
||||
|
||||
class RTVETelevisionIE(InfoExtractor):
|
||||
IE_NAME = 'rtve.es:television'
|
||||
_VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
|
||||
# https://www.rtve.es/SECTION/YYYYMMDD/CONTENT_SLUG/CONTENT_ID.shtml
|
||||
_VALID_URL = r'https?://(?:www\.)?rtve\.es/[^/]+/\d{8}/[^/]+/(?P<id>\d+)\.shtml'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
|
||||
_TESTS = [{
|
||||
'url': 'https://www.rtve.es/television/20220916/destacados-festival-san-sebastian-rtve-play/2395620.shtml',
|
||||
'info_dict': {
|
||||
'id': '3069778',
|
||||
'id': '6668919',
|
||||
'ext': 'mp4',
|
||||
'title': 'Documentos TV - La revolución del móvil',
|
||||
'duration': 3496.948,
|
||||
'title': 'Las películas del Festival de San Sebastián en RTVE Play',
|
||||
'description': 'El\xa0Festival de San Sebastián vuelve a llenarse de artistas. Y en su honor,\xa0RTVE Play\xa0destacará cada viernes una\xa0película galardonada\xa0con la\xa0Concha de Oro\xa0en su catálogo.',
|
||||
'duration': 20.048,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.rtve.es/noticias/20220917/penelope-cruz-san-sebastian-premio-nacional/2402565.shtml',
|
||||
'info_dict': {
|
||||
'id': '6694087',
|
||||
'ext': 'mp4',
|
||||
'title': 'Penélope Cruz recoge el Premio Nacional de Cinematografía: "No dejen nunca de proteger nuestro cine"',
|
||||
'description': 'md5:eda9e6baa78dbbbcc7708c0cc8150a91',
|
||||
'duration': 388.2,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.rtve.es/deportes/20220917/motogp-bagnaia-pole-marquez-decimotercero-motorland-aragon/2402566.shtml',
|
||||
'info_dict': {
|
||||
'id': '6694142',
|
||||
'ext': 'mp4',
|
||||
'title': "Bagnaia logra su quinta 'pole' del año y Márquez partirá decimotercero",
|
||||
'description': 'md5:07e2ccb983a046cb42f896cce225f0a7',
|
||||
'duration': 153.44,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.rtve.es/playz/20220807/covaleda-fest-final/2394809.shtml',
|
||||
'info_dict': {
|
||||
'id': '6665408',
|
||||
'ext': 'mp4',
|
||||
'title': 'Covaleda Fest (Soria) - Día 3 con Marc Seguí y Paranoid 1966',
|
||||
'description': 'Festivales Playz viaja a Covaleda, Soria, para contarte todo lo que sucede en el Covaleda Fest. Entrevistas, challenges a los artistas, juegos... Khan, Adriana Jiménez y María García no dejarán pasar ni una. ¡No te lo pierdas!',
|
||||
'duration': 12009.92,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
page_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, page_id)
|
||||
|
||||
alacarta_url = self._search_regex(
|
||||
r'data-location="alacarta_videos"[^<]+url":"(http://www\.rtve\.es/alacarta.+?)&',
|
||||
r'data-location="alacarta_videos"[^<]+url":"(https?://www\.rtve\.es/play.+?)&',
|
||||
webpage, 'alacarta url', default=None)
|
||||
if alacarta_url is None:
|
||||
raise ExtractorError(
|
||||
'The webpage doesn\'t contain any video', expected=True)
|
||||
|
||||
return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())
|
||||
return self.url_result(alacarta_url, ie=RTVEPlayIE.ie_key())
|
||||
|
|
|
@ -1,20 +1,38 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
import re
|
||||
from time import sleep
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
get_element_by_class,
|
||||
get_element_by_id,
|
||||
int_or_none,
|
||||
str_to_int,
|
||||
merge_dicts,
|
||||
parse_count,
|
||||
parse_qs,
|
||||
T,
|
||||
traverse_obj,
|
||||
unified_strdate,
|
||||
url_or_none,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class YouPornIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
|
||||
_VALID_URL = (
|
||||
r'youporn:(?P<id>\d+)',
|
||||
r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)
|
||||
(?:/(?:(?P<display_id>[^/?#&]+)/?)?)?(?:[#?]|$)
|
||||
'''
|
||||
)
|
||||
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)']
|
||||
_TESTS = [{
|
||||
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
|
||||
'md5': '3744d24c50438cf5b6f6d59feb5055c2',
|
||||
|
@ -34,7 +52,7 @@ class YouPornIE(InfoExtractor):
|
|||
'tags': list,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'skip': 'This video has been disabled',
|
||||
'skip': 'This video has been deactivated',
|
||||
}, {
|
||||
# Unknown uploader
|
||||
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
|
||||
|
@ -66,57 +84,104 @@ class YouPornIE(InfoExtractor):
|
|||
}, {
|
||||
'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.youporn.com/watch/16290308/tinderspecial-trailer1/',
|
||||
'info_dict': {
|
||||
'id': '16290308',
|
||||
'age_limit': 18,
|
||||
'categories': [],
|
||||
'description': None, # SEO spam using title removed
|
||||
'display_id': 'tinderspecial-trailer1',
|
||||
'duration': 298.0,
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20201123',
|
||||
'uploader': 'Ersties',
|
||||
'tags': [],
|
||||
'thumbnail': 'https://fi1.ypncdn.com/m=eaSaaTbWx/202011/23/16290308/original/3.jpg',
|
||||
'timestamp': 1606147564,
|
||||
'title': 'Tinder In Real Life',
|
||||
'view_count': int,
|
||||
}
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
|
||||
webpage)
|
||||
@classmethod
|
||||
def _extract_urls(cls, webpage):
|
||||
def yield_urls():
|
||||
for p in cls._EMBED_REGEX:
|
||||
for m in re.finditer(p, webpage):
|
||||
yield m.group('url')
|
||||
|
||||
return list(yield_urls())
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
# A different video ID (data-video-id) is hidden in the page but
|
||||
# never seems to be used
|
||||
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
|
||||
url = 'http://www.youporn.com/watch/%s' % (video_id,)
|
||||
webpage = self._download_webpage(
|
||||
url, video_id, headers={'Cookie': 'age_verified=1'})
|
||||
|
||||
definitions = self._download_json(
|
||||
'https://www.youporn.com/api/video/media_definitions/%s/' % video_id,
|
||||
display_id)
|
||||
watchable = self._search_regex(
|
||||
r'''(<div\s[^>]*\bid\s*=\s*('|")?watch-container(?(2)\2|(?!-)\b)[^>]*>)''',
|
||||
webpage, 'watchability', default=None)
|
||||
if not watchable:
|
||||
msg = re.split(r'\s{4}', clean_html(get_element_by_id(
|
||||
'mainContent', webpage)) or '')[0]
|
||||
raise ExtractorError(
|
||||
('%s says: %s' % (self.IE_NAME, msg))
|
||||
if msg else 'Video unavailable: no reason found',
|
||||
expected=True)
|
||||
# internal ID ?
|
||||
# video_id = extract_attributes(watchable).get('data-video-id')
|
||||
|
||||
playervars = self._search_json(
|
||||
r'\bplayervars\s*:', webpage, 'playervars', video_id)
|
||||
|
||||
def get_fmt(x):
|
||||
v_url = url_or_none(x.get('videoUrl'))
|
||||
if v_url:
|
||||
x['videoUrl'] = v_url
|
||||
return (x['format'], x)
|
||||
|
||||
defs_by_format = dict(traverse_obj(playervars, (
|
||||
'mediaDefinitions', lambda _, v: v.get('format'), T(get_fmt))))
|
||||
|
||||
def get_format_data(f):
|
||||
if f not in defs_by_format:
|
||||
return []
|
||||
return self._download_json(
|
||||
defs_by_format[f]['videoUrl'], video_id, '{0}-formats'.format(f))
|
||||
|
||||
formats = []
|
||||
for definition in definitions:
|
||||
if not isinstance(definition, dict):
|
||||
continue
|
||||
video_url = url_or_none(definition.get('videoUrl'))
|
||||
if not video_url:
|
||||
continue
|
||||
f = {
|
||||
'url': video_url,
|
||||
'filesize': int_or_none(definition.get('videoSize')),
|
||||
}
|
||||
height = int_or_none(definition.get('quality'))
|
||||
# Try to extract only the actual master m3u8 first, avoiding the duplicate single resolution "master" m3u8s
|
||||
for hls_url in traverse_obj(
|
||||
get_format_data('hls'),
|
||||
(lambda _, v: not isinstance(v['defaultQuality'], bool), 'videoUrl'),
|
||||
(Ellipsis, 'videoUrl')):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls',
|
||||
entry_protocol='m3u8_native'))
|
||||
|
||||
for f in traverse_obj(get_format_data('mp4'), (
|
||||
lambda _, v: v.get('videoUrl'), {
|
||||
'url': ('videoUrl', T(url_or_none)),
|
||||
'filesize': ('videoSize', T(int_or_none)),
|
||||
'height': ('quality', T(int_or_none)),
|
||||
}, T(lambda x: x.get('videoUrl') and x))):
|
||||
# Video URL's path looks like this:
|
||||
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /videos/201703/11/109285532/1080P_4000K_109285532.mp4
|
||||
# We will benefit from it by extracting some metadata
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', f['videoUrl'])
|
||||
if mobj:
|
||||
if not height:
|
||||
height = int(mobj.group('height'))
|
||||
bitrate = int(mobj.group('bitrate'))
|
||||
f.update({
|
||||
'format_id': '%dp-%dk' % (height, bitrate),
|
||||
'tbr': bitrate,
|
||||
})
|
||||
f['height'] = height
|
||||
if not f.get('height'):
|
||||
f['height'] = int(mobj.group('height'))
|
||||
f['tbr'] = int(mobj.group('bitrate'))
|
||||
f['format_id'] = '%dp-%dk' % (f['height'], f['tbr'])
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'http://www.youporn.com/watch/%s' % video_id, display_id,
|
||||
headers={'Cookie': 'age_verified=1'})
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
|
||||
webpage, 'title', default=None) or self._og_search_title(
|
||||
|
@ -131,8 +196,10 @@ class YouPornIE(InfoExtractor):
|
|||
thumbnail = self._search_regex(
|
||||
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
|
||||
webpage, 'thumbnail', fatal=False, group='thumbnail')
|
||||
duration = int_or_none(self._html_search_meta(
|
||||
'video:duration', webpage, 'duration', fatal=False))
|
||||
duration = traverse_obj(playervars, ('duration', T(int_or_none)))
|
||||
if duration is None:
|
||||
duration = int_or_none(self._html_search_meta(
|
||||
'video:duration', webpage, 'duration', fatal=False))
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
|
||||
|
@ -148,11 +215,11 @@ class YouPornIE(InfoExtractor):
|
|||
|
||||
view_count = None
|
||||
views = self._search_regex(
|
||||
r'(<div[^>]+\bclass=["\']js_videoInfoViews["\']>)', webpage,
|
||||
'views', default=None)
|
||||
r'(<div\s[^>]*\bdata-value\s*=[^>]+>)\s*<label>Views:</label>',
|
||||
webpage, 'views', default=None)
|
||||
if views:
|
||||
view_count = str_to_int(extract_attributes(views).get('data-value'))
|
||||
comment_count = str_to_int(self._search_regex(
|
||||
view_count = parse_count(extract_attributes(views).get('data-value'))
|
||||
comment_count = parse_count(self._search_regex(
|
||||
r'>All [Cc]omments? \(([\d,.]+)\)',
|
||||
webpage, 'comment count', default=None))
|
||||
|
||||
|
@ -168,7 +235,10 @@ class YouPornIE(InfoExtractor):
|
|||
r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
|
||||
'tags')
|
||||
|
||||
return {
|
||||
data = self._search_json_ld(webpage, video_id, expected_type='VideoObject', fatal=False) or {}
|
||||
data.pop('url', None)
|
||||
|
||||
result = merge_dicts(data, {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
|
@ -183,4 +253,442 @@ class YouPornIE(InfoExtractor):
|
|||
'tags': tags,
|
||||
'age_limit': age_limit,
|
||||
'formats': formats,
|
||||
}
|
||||
})
|
||||
# Remove promotional non-description
|
||||
if result.get('description', '').startswith(
|
||||
'Watch %s online' % (result['title'],)):
|
||||
del result['description']
|
||||
return result
|
||||
|
||||
|
||||
class YouPornListBase(InfoExtractor):
|
||||
# pattern in '.title-text' element of page section containing videos
|
||||
_PLAYLIST_TITLEBAR_RE = r'\s+[Vv]ideos\s*$'
|
||||
_PAGE_RETRY_COUNT = 0 # ie, no retry
|
||||
_PAGE_RETRY_DELAY = 2 # seconds
|
||||
|
||||
def _get_next_url(self, url, pl_id, html):
|
||||
return urljoin(url, self._search_regex(
|
||||
r'''<a\s[^>]*?\bhref\s*=\s*("|')(?P<url>(?:(?!\1)[^>])+)\1''',
|
||||
get_element_by_id('next', html) or '', 'next page',
|
||||
group='url', default=None))
|
||||
|
||||
@classmethod
|
||||
def _get_title_from_slug(cls, title_slug):
|
||||
return re.sub(r'[_-]', ' ', title_slug)
|
||||
|
||||
def _entries(self, url, pl_id, html=None, page_num=None):
|
||||
|
||||
# separates page sections
|
||||
PLAYLIST_SECTION_RE = (
|
||||
r'''<div\s[^>]*\bclass\s*=\s*('|")(?:[\w$-]+\s+|\s)*?title-bar(?:\s+[\w$-]+|\s)*\1[^>]*>'''
|
||||
)
|
||||
# contains video link
|
||||
VIDEO_URL_RE = r'''(?x)
|
||||
<div\s[^>]*\bdata-video-id\s*=\s*('|")\d+\1[^>]*>\s*
|
||||
(?:<div\b[\s\S]+?</div>\s*)*
|
||||
<a\s[^>]*\bhref\s*=\s*('|")(?P<url>(?:(?!\2)[^>])+)\2
|
||||
'''
|
||||
|
||||
def yield_pages(url, html=html, page_num=page_num):
|
||||
fatal = not html
|
||||
for pnum in itertools.count(start=page_num or 1):
|
||||
if not html:
|
||||
html = self._download_webpage(
|
||||
url, pl_id, note='Downloading page %d' % pnum,
|
||||
fatal=fatal)
|
||||
if not html:
|
||||
break
|
||||
fatal = False
|
||||
yield (url, html, pnum)
|
||||
# explicit page: extract just that page
|
||||
if page_num is not None:
|
||||
break
|
||||
next_url = self._get_next_url(url, pl_id, html)
|
||||
if not next_url or next_url == url:
|
||||
break
|
||||
url, html = next_url, None
|
||||
|
||||
def retry_page(msg, tries_left, page_data):
|
||||
if tries_left <= 0:
|
||||
return
|
||||
self.report_warning(msg, pl_id)
|
||||
sleep(self._PAGE_RETRY_DELAY)
|
||||
return next(
|
||||
yield_pages(page_data[0], page_num=page_data[2]), None)
|
||||
|
||||
def yield_entries(html):
|
||||
for frag in re.split(PLAYLIST_SECTION_RE, html):
|
||||
if not frag:
|
||||
continue
|
||||
t_text = get_element_by_class('title-text', frag or '')
|
||||
if not (t_text and re.search(self._PLAYLIST_TITLEBAR_RE, t_text)):
|
||||
continue
|
||||
for m in re.finditer(VIDEO_URL_RE, frag):
|
||||
video_url = urljoin(url, m.group('url'))
|
||||
if video_url:
|
||||
yield self.url_result(video_url)
|
||||
|
||||
last_first_url = None
|
||||
for page_data in yield_pages(url, html=html, page_num=page_num):
|
||||
# page_data: url, html, page_num
|
||||
first_url = None
|
||||
tries_left = self._PAGE_RETRY_COUNT + 1
|
||||
while tries_left > 0:
|
||||
tries_left -= 1
|
||||
for from_ in yield_entries(page_data[1]):
|
||||
# may get the same page twice instead of empty page
|
||||
# or (site bug) intead of actual next page
|
||||
if not first_url:
|
||||
first_url = from_['url']
|
||||
if first_url == last_first_url:
|
||||
# sometimes (/porntags/) the site serves the previous page
|
||||
# instead but may provide the correct page after a delay
|
||||
page_data = retry_page(
|
||||
'Retrying duplicate page...', tries_left, page_data)
|
||||
if page_data:
|
||||
first_url = None
|
||||
break
|
||||
continue
|
||||
yield from_
|
||||
else:
|
||||
if not first_url and 'no-result-paragarph1' in page_data[1]:
|
||||
page_data = retry_page(
|
||||
'Retrying empty page...', tries_left, page_data)
|
||||
if page_data:
|
||||
continue
|
||||
else:
|
||||
# success/failure
|
||||
break
|
||||
# may get an infinite (?) sequence of empty pages
|
||||
if not first_url:
|
||||
break
|
||||
last_first_url = first_url
|
||||
|
||||
def _real_extract(self, url, html=None):
|
||||
# exceptionally, id may be None
|
||||
m_dict = self._match_valid_url(url).groupdict()
|
||||
pl_id, page_type, sort = (m_dict.get(k) for k in ('id', 'type', 'sort'))
|
||||
|
||||
qs = parse_qs(url)
|
||||
for q, v in qs.items():
|
||||
if v:
|
||||
qs[q] = v[-1]
|
||||
else:
|
||||
del qs[q]
|
||||
|
||||
base_id = pl_id or 'YouPorn'
|
||||
title = self._get_title_from_slug(base_id)
|
||||
if page_type:
|
||||
title = '%s %s' % (page_type.capitalize(), title)
|
||||
base_id = [base_id.lower()]
|
||||
if sort is None:
|
||||
title += ' videos'
|
||||
else:
|
||||
title = '%s videos by %s' % (title, re.sub(r'[_-]', ' ', sort))
|
||||
base_id.append(sort)
|
||||
if qs:
|
||||
ps = ['%s=%s' % item for item in sorted(qs.items())]
|
||||
title += ' (%s)' % ','.join(ps)
|
||||
base_id.extend(ps)
|
||||
pl_id = '/'.join(base_id)
|
||||
|
||||
return self.playlist_result(
|
||||
self._entries(url, pl_id, html=html,
|
||||
page_num=int_or_none(qs.get('page'))),
|
||||
playlist_id=pl_id, playlist_title=title)
|
||||
|
||||
|
||||
class YouPornCategoryIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn category, with sorting, filtering and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>category)/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>popular|views|rating|time|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/category/lingerie/popular/',
|
||||
'info_dict': {
|
||||
'id': 'lingerie/popular',
|
||||
'title': 'Category lingerie videos by popular',
|
||||
},
|
||||
'playlist_mincount': 39,
|
||||
}, {
|
||||
'note': 'Filtered paginated list with single page result',
|
||||
'url': 'https://www.youporn.com/category/lingerie/duration/?min_minutes=10',
|
||||
'info_dict': {
|
||||
'id': 'lingerie/duration/min_minutes=10',
|
||||
'title': 'Category lingerie videos by duration (min_minutes=10)',
|
||||
},
|
||||
'playlist_maxcount': 30,
|
||||
}, {
|
||||
'note': 'Single page of full list',
|
||||
'url': 'https://www.youporn.com/category/lingerie/popular?page=1',
|
||||
'info_dict': {
|
||||
'id': 'lingerie/popular/page=1',
|
||||
'title': 'Category lingerie videos by popular (page=1)',
|
||||
},
|
||||
'playlist_count': 30,
|
||||
}]
|
||||
|
||||
|
||||
class YouPornChannelIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn channel, with sorting and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>channel)/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>rating|views|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/channel/x-feeds/',
|
||||
'info_dict': {
|
||||
'id': 'x-feeds',
|
||||
'title': 'Channel X-Feeds videos',
|
||||
},
|
||||
'playlist_mincount': 37,
|
||||
}, {
|
||||
'note': 'Single page of full list (no filters here)',
|
||||
'url': 'https://www.youporn.com/channel/x-feeds/duration?page=1',
|
||||
'info_dict': {
|
||||
'id': 'x-feeds/duration/page=1',
|
||||
'title': 'Channel X-Feeds videos by duration (page=1)',
|
||||
},
|
||||
'playlist_count': 24,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _get_title_from_slug(title_slug):
|
||||
return re.sub(r'_', ' ', title_slug).title()
|
||||
|
||||
|
||||
class YouPornCollectionIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn collection (user playlist), with sorting and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>collection)s/videos/(?P<id>\d+)
|
||||
(?:/(?P<sort>rating|views|time|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+in\s'
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/collections/videos/33044251/',
|
||||
'info_dict': {
|
||||
'id': '33044251',
|
||||
'title': 'Collection Sexy Lips videos',
|
||||
'uploader': 'ph-littlewillyb',
|
||||
},
|
||||
'playlist_mincount': 50,
|
||||
}, {
|
||||
'note': 'Single page of full list (no filters here)',
|
||||
'url': 'https://www.youporn.com/collections/videos/33044251/time?page=1',
|
||||
'info_dict': {
|
||||
'id': '33044251/time/page=1',
|
||||
'title': 'Collection Sexy Lips videos by time (page=1)',
|
||||
'uploader': 'ph-littlewillyb',
|
||||
},
|
||||
'playlist_count': 20,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
pl_id = self._match_id(url)
|
||||
html = self._download_webpage(url, pl_id)
|
||||
playlist = super(YouPornCollectionIE, self)._real_extract(url, html=html)
|
||||
infos = re.sub(r'\s+', ' ', clean_html(get_element_by_class(
|
||||
'collection-infos', html)) or '')
|
||||
title, uploader = self._search_regex(
|
||||
r'^\s*Collection: (?P<title>.+?) \d+ VIDEOS \d+ VIEWS \d+ days LAST UPDATED From: (?P<uploader>[\w_-]+)',
|
||||
infos, 'title/uploader', group=('title', 'uploader'), default=(None, None))
|
||||
|
||||
return merge_dicts({
|
||||
'title': playlist['title'].replace(playlist['id'].split('/')[0], title),
|
||||
'uploader': uploader,
|
||||
}, playlist) if title else playlist
|
||||
|
||||
|
||||
class YouPornTagIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn tag (porntags), with sorting, filtering and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
porn(?P<type>tag)s/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>views|rating|time|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+tagged\s'
|
||||
_PAGE_RETRY_COUNT = 1
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/porntags/austrian',
|
||||
'info_dict': {
|
||||
'id': 'austrian',
|
||||
'title': 'Tag austrian videos',
|
||||
},
|
||||
'playlist_mincount': 35,
|
||||
'expected_warnings': ['Retrying duplicate page'],
|
||||
}, {
|
||||
'note': 'Filtered paginated list with single page result',
|
||||
'url': 'https://www.youporn.com/porntags/austrian/duration/?min_minutes=10',
|
||||
'info_dict': {
|
||||
'id': 'austrian/duration/min_minutes=10',
|
||||
'title': 'Tag austrian videos by duration (min_minutes=10)',
|
||||
},
|
||||
# number of videos per page is (row x col) 2x3 + 6x4 + 2, or + 3,
|
||||
# or more, varying with number of ads; let's set max as 9x4
|
||||
# NB col 1 may not be shown in non-JS page with site CSS and zoom 100%
|
||||
'playlist_maxcount': 32,
|
||||
'expected_warnings': ['Retrying duplicate page', 'Retrying empty page'],
|
||||
}, {
|
||||
'note': 'Single page of full list',
|
||||
'url': 'https://www.youporn.com/porntags/austrian/?page=1',
|
||||
'info_dict': {
|
||||
'id': 'austrian/page=1',
|
||||
'title': 'Tag austrian videos (page=1)',
|
||||
},
|
||||
'playlist_mincount': 32,
|
||||
'playlist_maxcount': 34,
|
||||
'expected_warnings': ['Retrying duplicate page', 'Retrying empty page'],
|
||||
}]
|
||||
|
||||
# YP tag navigation is broken, loses sort
|
||||
def _get_next_url(self, url, pl_id, html):
|
||||
next_url = super(YouPornTagIE, self)._get_next_url(url, pl_id, html)
|
||||
if next_url:
|
||||
n = self._match_valid_url(next_url)
|
||||
if n:
|
||||
s = n.groupdict().get('sort')
|
||||
if s:
|
||||
u = self._match_valid_url(url)
|
||||
if u:
|
||||
u = u.groupdict().get('sort')
|
||||
if s and not u:
|
||||
n = n.end('sort')
|
||||
next_url = next_url[:n] + '/' + u + next_url[n:]
|
||||
return next_url
|
||||
|
||||
|
||||
class YouPornStarIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn Pornstar, with description, sorting and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>pornstar)/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>rating|views|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+[fF]eaturing\s'
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/pornstar/daynia/',
|
||||
'info_dict': {
|
||||
'id': 'daynia',
|
||||
'title': 'Pornstar Daynia videos',
|
||||
'description': r're:Daynia Rank \d+ Videos \d+ Views [\d,.]+ .+ Subscribers \d+',
|
||||
},
|
||||
'playlist_mincount': 45,
|
||||
}, {
|
||||
'note': 'Single page of full list (no filters here)',
|
||||
'url': 'https://www.youporn.com/pornstar/daynia/?page=1',
|
||||
'info_dict': {
|
||||
'id': 'daynia/page=1',
|
||||
'title': 'Pornstar Daynia videos (page=1)',
|
||||
'description': 're:.{180,}',
|
||||
},
|
||||
'playlist_count': 26,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _get_title_from_slug(title_slug):
|
||||
return re.sub(r'_', ' ', title_slug).title()
|
||||
|
||||
def _real_extract(self, url):
|
||||
pl_id = self._match_id(url)
|
||||
html = self._download_webpage(url, pl_id)
|
||||
playlist = super(YouPornStarIE, self)._real_extract(url, html=html)
|
||||
INFO_ELEMENT_RE = r'''(?x)
|
||||
<div\s[^>]*\bclass\s*=\s*('|")(?:[\w$-]+\s+|\s)*?pornstar-info-wrapper(?:\s+[\w$-]+|\s)*\1[^>]*>
|
||||
(?P<info>[\s\S]+?)(?:</div>\s*){6,}
|
||||
'''
|
||||
|
||||
infos = self._search_regex(INFO_ELEMENT_RE, html, 'infos', group='info', default='')
|
||||
if infos:
|
||||
infos = re.sub(
|
||||
r'(?:\s*nl=nl)+\s*', ' ',
|
||||
re.sub(r'(?u)\s+', ' ', clean_html(
|
||||
re.sub('\n', 'nl=nl', infos)))).replace('ribe Subsc', '')
|
||||
|
||||
return merge_dicts({
|
||||
'description': infos.strip() or None,
|
||||
}, playlist)
|
||||
|
||||
|
||||
class YouPornVideosIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn video (browse) playlists, with sorting, filtering and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?:(?P<id>browse)/)?
|
||||
(?P<sort>(?(id)
|
||||
(?:duration|rating|time|views)|
|
||||
(?:most_(?:favou?rit|view)ed|recommended|top_rated)?))
|
||||
(?:[/#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'\s+(?:[Vv]ideos|VIDEOS)\s*$'
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/',
|
||||
'info_dict': {
|
||||
'id': 'youporn',
|
||||
'title': 'YouPorn videos',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/recommended',
|
||||
'info_dict': {
|
||||
'id': 'youporn/recommended',
|
||||
'title': 'YouPorn videos by recommended',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/top_rated',
|
||||
'info_dict': {
|
||||
'id': 'youporn/top_rated',
|
||||
'title': 'YouPorn videos by top rated',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/browse/time',
|
||||
'info_dict': {
|
||||
'id': 'browse/time',
|
||||
'title': 'YouPorn videos by time',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Filtered paginated list with single page result',
|
||||
'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=2',
|
||||
'info_dict': {
|
||||
'id': 'youporn/most_favorited/max_minutes=2/res=VR',
|
||||
'title': 'YouPorn videos by most favorited (max_minutes=2,res=VR)',
|
||||
},
|
||||
'playlist_mincount': 10,
|
||||
'playlist_maxcount': 28,
|
||||
}, {
|
||||
'note': 'Filtered paginated list with several pages',
|
||||
'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=5',
|
||||
'info_dict': {
|
||||
'id': 'youporn/most_favorited/max_minutes=5/res=VR',
|
||||
'title': 'YouPorn videos by most favorited (max_minutes=5,res=VR)',
|
||||
},
|
||||
'playlist_mincount': 45,
|
||||
}, {
|
||||
'note': 'Single page of full list',
|
||||
'url': 'https://www.youporn.com/browse/time?page=1',
|
||||
'info_dict': {
|
||||
'id': 'browse/time/page=1',
|
||||
'title': 'YouPorn videos by time (page=1)',
|
||||
},
|
||||
'playlist_count': 36,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _get_title_from_slug(title_slug):
|
||||
return 'YouPorn' if title_slug == 'browse' else title_slug
|
||||
|
|
Loading…
Reference in a new issue