Compare commits
9 Commits
2abb3e774e
...
b405145a0a
Author | SHA1 | Date |
---|---|---|
dirkf | b405145a0a | |
dirkf | 668332b973 | |
dirkf | 0b2ce3685e | |
dirkf | c2766cb80e | |
dirkf | eb38665438 | |
dirkf | ab5617be9e | |
dirkf | b028b2fa27 | |
dirkf | d1dbd37b09 | |
dirkf | bcb8143f1d |
|
@ -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']),
|
||||
|
|
|
@ -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 (
|
||||
|
|
|
@ -2,32 +2,62 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_kwargs,
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
smuggle_url,
|
||||
ExtractorError,
|
||||
HEADRequest,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
traverse_obj,
|
||||
update_url_query,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class SBSIE(InfoExtractor):
|
||||
IE_DESC = 'sbs.com.au'
|
||||
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=|/watch/)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?sbs\.com\.au/(?:
|
||||
ondemand(?:
|
||||
/video/(?:single/)?|
|
||||
/(?:movie|tv-program)/[^/]+/|
|
||||
/(?:tv|news)-series/(?:[^/]+/){3}|
|
||||
.*?\bplay=|/watch/
|
||||
)|news/(?:embeds/)?video/
|
||||
)(?P<id>[0-9]+)'''
|
||||
_EMBED_REGEX = [r'''(?x)]
|
||||
(?:
|
||||
<meta\s+property="og:video"\s+content=|
|
||||
<iframe[^>]+?src=
|
||||
)
|
||||
(["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''']
|
||||
|
||||
_TESTS = [{
|
||||
# Original URL is handled by the generic IE which finds the iframe:
|
||||
# http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
|
||||
# Exceptional unrestricted show for testing, thanks SBS,
|
||||
# from an iframe of this page, handled by the generic IE, now 404:
|
||||
# http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation, but replaced by
|
||||
# https://www.sbs.com.au/programs/video/320403011771/Dingo-Conservation-The-Feed
|
||||
'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
|
||||
'md5': '3150cf278965eeabb5b4cea1c963fe0a',
|
||||
'md5': 'e49d0290cb4f40d893b8dfe760dce6b0',
|
||||
'info_dict': {
|
||||
'id': '_rFBPRPO4pMR',
|
||||
'id': '320403011771', # formerly '_rFBPRPO4pMR', no longer found
|
||||
'ext': 'mp4',
|
||||
'title': 'Dingo Conservation (The Feed)',
|
||||
'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
|
||||
'thumbnail': r're:http://.*\.jpg',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'duration': 308,
|
||||
'timestamp': 1408613220,
|
||||
'upload_date': '20140821',
|
||||
'uploader': 'SBSC',
|
||||
'tags': None,
|
||||
'categories': None,
|
||||
},
|
||||
'expected_warnings': ['Unable to download JSON metadata'],
|
||||
}, {
|
||||
'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
|
||||
'only_matching': True,
|
||||
|
@ -46,33 +76,160 @@ class SBSIE(InfoExtractor):
|
|||
}, {
|
||||
'url': 'https://www.sbs.com.au/ondemand/watch/1698704451971',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.sbs.com.au/ondemand/movie/coherence/1469404227931',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Live stream',
|
||||
'url': 'https://www.sbs.com.au/ondemand/video/1726824003663/sbs-24x7-live-stream-nsw',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.sbs.com.au/ondemand/news-series/dateline/dateline-2022/dateline-s2022-ep26/2072245827515',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.sbs.com.au/ondemand/tv-series/the-handmaids-tale/season-5/the-handmaids-tale-s5-ep1/2065631811776',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.sbs.com.au/ondemand/tv-program/autun-romes-forgotten-sister/2116212803602',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_m3u8_formats(self, m3u8_url, video_id, *args, **kwargs):
|
||||
# ext, entry_protocol, preference, m3u8_id, note, errnote, fatal,
|
||||
# live, data, headers, query
|
||||
entry_protocol = args[1] if len(args) > 1 else kwargs.get('entry_protocol')
|
||||
if not entry_protocol:
|
||||
entry_protocol = 'm3u8_native'
|
||||
if len(args) > 1:
|
||||
args = list(args)
|
||||
args[1] = entry_protocol
|
||||
else:
|
||||
kwargs['entry_protocol'] = entry_protocol
|
||||
kwargs = compat_kwargs(kwargs)
|
||||
|
||||
return super(SBSIE, self)._extract_m3u8_formats(m3u8_url, video_id, *args, **kwargs)
|
||||
|
||||
_GEO_COUNTRIES = ['AU']
|
||||
# naming for exportability
|
||||
AUS_TV_PARENTAL_GUIDELINES = {
|
||||
'P': 0,
|
||||
'C': 7,
|
||||
'G': 0,
|
||||
'PG': 0,
|
||||
'M': 14,
|
||||
'MA15+': 15,
|
||||
'AV15+': 15,
|
||||
'MAV15+': 15,
|
||||
'R18+': 18,
|
||||
'NC': 0, # not classified (unofficial, used by SBS)
|
||||
}
|
||||
_PLAYER_API = 'https://www.sbs.com.au/api/v3'
|
||||
_CATALOGUE_API = 'https://catalogue.pr.sbsod.com/'
|
||||
_VOD_BASE_URL = 'https://sbs-vod-prod-01.akamaized.net/'
|
||||
|
||||
def _call_api(self, video_id, path, query=None, data=None, headers=None, fatal=True):
|
||||
return self._download_json(update_url_query(
|
||||
self._CATALOGUE_API + path, query),
|
||||
video_id, headers=headers or {}, fatal=fatal) or {}
|
||||
|
||||
def _get_smil_url(self, video_id):
|
||||
return update_url_query(
|
||||
self._PLAYER_API + 'video_smil', {'id': video_id})
|
||||
|
||||
def _get_player_data(self, video_id, headers=None, fatal=False):
|
||||
return self._download_json(update_url_query(
|
||||
self._PLAYER_API + 'video_stream', {'id': video_id, 'context': 'tv'}),
|
||||
video_id, headers=headers or {}, fatal=fatal) or {}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
player_params = self._download_json(
|
||||
'http://www.sbs.com.au/api/video_pdkvars/id/%s?form=json' % video_id, video_id)
|
||||
# get media links directly though later metadata may contain contentUrl
|
||||
smil_url = self._get_smil_url(video_id)
|
||||
formats = self._extract_smil_formats(smil_url, video_id, fatal=False) or []
|
||||
|
||||
error = player_params.get('error')
|
||||
if error:
|
||||
error_message = 'Sorry, The video you are looking for does not exist.'
|
||||
video_data = error.get('results') or {}
|
||||
error_code = error.get('errorCode')
|
||||
if error_code == 'ComingSoon':
|
||||
error_message = '%s is not yet available.' % video_data.get('title', '')
|
||||
elif error_code in ('Forbidden', 'intranetAccessOnly'):
|
||||
error_message = 'Sorry, This video cannot be accessed via this website'
|
||||
elif error_code == 'Expired':
|
||||
error_message = 'Sorry, %s is no longer available.' % video_data.get('title', '')
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
if not formats:
|
||||
urlh = self._request_webpage(
|
||||
HEADRequest(self._VOD_BASE_URL), video_id,
|
||||
note='Checking geo-restriction', fatal=False, expected_status=403)
|
||||
if urlh:
|
||||
error_reasons = urlh.headers.get_all('x-error-reason') or []
|
||||
if 'geo-blocked' in error_reasons:
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
|
||||
urls = player_params['releaseUrls']
|
||||
theplatform_url = (urls.get('progressive') or urls.get('html')
|
||||
or urls.get('standard') or player_params['relatedItemsURL'])
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'ThePlatform',
|
||||
# try for metadata from the same source
|
||||
player_data = self._get_player_data(video_id, fatal=False)
|
||||
media = traverse_obj(player_data, 'video_object', expected_type=dict) or {}
|
||||
# get, or add, metadata from catalogue
|
||||
media.update(self._call_api(video_id, 'mpx-media/' + video_id, fatal=not media))
|
||||
|
||||
# utils candidate for use with traverse_obj()
|
||||
def txt_or_none(s):
|
||||
return (s.strip() or None) if isinstance(s, compat_str) else None
|
||||
|
||||
# expected_type fn for thumbs
|
||||
def xlate_thumb(t):
|
||||
u = url_or_none(t.get('contentUrl'))
|
||||
return u and {
|
||||
'id': t.get('name'),
|
||||
'url': u,
|
||||
'width': int_or_none(t.get('width')),
|
||||
'height': int_or_none(t.get('height')),
|
||||
}
|
||||
|
||||
# may be numeric or timecoded
|
||||
def really_parse_duration(d):
|
||||
result = float_or_none(d)
|
||||
if result is None:
|
||||
result = parse_duration(d)
|
||||
return result
|
||||
|
||||
def traverse_media(*args, **kwargs):
|
||||
nkwargs = None
|
||||
if 'expected_type' not in kwargs:
|
||||
kwargs['expected_type'] = txt_or_none
|
||||
nkwargs = kwargs
|
||||
if 'get_all' not in kwargs:
|
||||
kwargs['get_all'] = False
|
||||
nkwargs = kwargs
|
||||
if nkwargs:
|
||||
kwargs = compat_kwargs(nkwargs)
|
||||
return traverse_obj(media, *args, **kwargs)
|
||||
|
||||
# For named episodes, use the catalogue's title to set episode, rather than generic 'Episode N'.
|
||||
if traverse_media('partOfSeries', expected_type=dict):
|
||||
media['epName'] = traverse_media('title')
|
||||
|
||||
return merge_dicts(*reversed(({
|
||||
'id': video_id,
|
||||
'url': smuggle_url(self._proto_relative_url(theplatform_url), {'force_smil_url': True}),
|
||||
}
|
||||
}, dict((k, traverse_media(v)) for k, v in {
|
||||
'title': 'name',
|
||||
'description': 'description',
|
||||
'channel': ('taxonomy', 'channel', 'name'),
|
||||
'series': ((('partOfSeries', 'name'), 'seriesTitle')),
|
||||
'series_id': ((('partOfSeries', 'uuid'), 'seriesID')),
|
||||
'episode': 'epName',
|
||||
}.items()), {
|
||||
'season_number': traverse_media((('partOfSeries', None), 'seasonNumber'), expected_type=int_or_none),
|
||||
'episode_number': traverse_media('episodeNumber', expected_type=int_or_none),
|
||||
'timestamp': traverse_media('datePublished', ('publication', 'startDate'),
|
||||
expected_type=parse_iso8601),
|
||||
'release_year': traverse_media('releaseYear', expected_type=int_or_none),
|
||||
'duration': traverse_media('duration', expected_type=really_parse_duration),
|
||||
'is_live': traverse_media('liveStream', expected_type=bool),
|
||||
'age_limit': self.AUS_TV_PARENTAL_GUIDELINES.get(traverse_media(
|
||||
'classificationID', 'contentRating', default='').upper()),
|
||||
'categories': traverse_media(
|
||||
('genres', Ellipsis), ('taxonomy', ('genre', 'subgenre'), 'name'),
|
||||
get_all=True) or None,
|
||||
'tags': traverse_media(
|
||||
(('consumerAdviceTexts', ('sbsSubCertification', 'consumerAdvice')), Ellipsis),
|
||||
get_all=True) or None,
|
||||
'thumbnails': traverse_media(('thumbnails', Ellipsis),
|
||||
expected_type=xlate_thumb, get_all=True),
|
||||
'formats': formats,
|
||||
# TODO: _extract_smil_formats_and_subtitles()
|
||||
# 'subtitles': subtitles,
|
||||
'uploader': 'SBSC',
|
||||
})))
|
||||
|
|
|
@ -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 New Issue