mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-25 11:41:52 +00:00
Remove extractors for dead pages
They all redirect to youporn.com.
This commit is contained in:
marieell
parent
3472227074
commit
7561727db6
6 changed files with 58 additions and 276 deletions
|
|
@ -356,7 +356,6 @@ from .esri import EsriVideoIE
|
|||
from .europa import EuropaIE
|
||||
from .expotv import ExpoTVIE
|
||||
from .expressen import ExpressenIE
|
||||
from .extremetube import ExtremeTubeIE
|
||||
from .eyedotv import EyedoTVIE
|
||||
from .facebook import (
|
||||
FacebookIE,
|
||||
|
|
@ -537,7 +536,6 @@ from .kaltura import KalturaIE
|
|||
from .kankan import KankanIE
|
||||
from .karaoketv import KaraoketvIE
|
||||
from .karrierevideos import KarriereVideosIE
|
||||
from .keezmovies import KeezMoviesIE
|
||||
from .ketnet import KetnetIE
|
||||
from .khanacademy import (
|
||||
KhanAcademyIE,
|
||||
|
|
@ -686,10 +684,6 @@ from .mlb import (
|
|||
)
|
||||
from .mnet import MnetIE
|
||||
from .moevideo import MoeVideoIE
|
||||
from .mofosex import (
|
||||
MofosexIE,
|
||||
MofosexEmbedIE,
|
||||
)
|
||||
from .mojvideo import MojvideoIE
|
||||
from .morningstar import MorningstarIE
|
||||
from .motherless import (
|
||||
|
|
|
|||
|
|
@ -1,50 +0,0 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
from ..utils import str_to_int
|
||||
from .keezmovies import KeezMoviesIE
|
||||
|
||||
|
||||
class ExtremeTubeIE(KeezMoviesIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
|
||||
'md5': '92feaafa4b58e82f261e5419f39c60cb',
|
||||
'info_dict': {
|
||||
'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
|
||||
'ext': 'mp4',
|
||||
'title': 'Music Video 14 british euro brit european cumshots swallow',
|
||||
'uploader': 'anonim',
|
||||
'view_count': int,
|
||||
'age_limit': 18,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.extremetube.com/gay/video/abcde-1234',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.extremetube.com/video/652431',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
webpage, info = self._extract_info(url)
|
||||
|
||||
if not info['title']:
|
||||
info['title'] = self._search_regex(
|
||||
r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'Uploaded by:\s*</[^>]+>\s*<a[^>]+>(.+?)</a>',
|
||||
webpage, 'uploader', fatal=False)
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'Views:\s*</[^>]+>\s*<[^>]+>([\d,\.]+)</',
|
||||
webpage, 'view count', fatal=False))
|
||||
|
||||
info.update({
|
||||
'uploader': uploader,
|
||||
'view_count': view_count,
|
||||
})
|
||||
|
||||
return info
|
||||
|
|
@ -64,7 +64,6 @@ from .tnaflix import TNAFlixNetworkEmbedIE
|
|||
from .drtuber import DrTuberIE
|
||||
from .redtube import RedTubeIE
|
||||
from .tube8 import Tube8IE
|
||||
from .mofosex import MofosexEmbedIE
|
||||
from .spankwire import SpankwireIE
|
||||
from .youporn import YouPornIE
|
||||
from .vimeo import (
|
||||
|
|
@ -2843,11 +2842,6 @@ class GenericIE(InfoExtractor):
|
|||
if tube8_urls:
|
||||
return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
|
||||
|
||||
# Look for embedded Mofosex player
|
||||
mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
|
||||
if mofosex_urls:
|
||||
return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
|
||||
|
||||
# Look for embedded Spankwire player
|
||||
spankwire_urls = SpankwireIE._extract_urls(webpage)
|
||||
if spankwire_urls:
|
||||
|
|
|
|||
|
|
@ -1,133 +0,0 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..aes import aes_decrypt_text
|
||||
from ..compat import compat_urllib_parse_unquote
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
str_to_int,
|
||||
strip_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class KeezMoviesIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.keezmovies.com/video/arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money-18070681',
|
||||
'md5': '2ac69cdb882055f71d82db4311732a1a',
|
||||
'info_dict': {
|
||||
'id': '18070681',
|
||||
'display_id': 'arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money',
|
||||
'ext': 'mp4',
|
||||
'title': 'Arab wife want it so bad I see she thirsty and has tiny money.',
|
||||
'thumbnail': None,
|
||||
'view_count': int,
|
||||
'age_limit': 18,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.keezmovies.com/video/18070681',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_info(self, url, fatal=True):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = (mobj.group('display_id')
|
||||
if 'display_id' in mobj.groupdict()
|
||||
else None) or mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(
|
||||
url, display_id, headers={'Cookie': 'age_verified=1'})
|
||||
|
||||
formats = []
|
||||
format_urls = set()
|
||||
|
||||
title = None
|
||||
thumbnail = None
|
||||
duration = None
|
||||
encrypted = False
|
||||
|
||||
def extract_format(format_url, height=None):
|
||||
format_url = url_or_none(format_url)
|
||||
if not format_url or not format_url.startswith(('http', '//')):
|
||||
return
|
||||
if format_url in format_urls:
|
||||
return
|
||||
format_urls.add(format_url)
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
|
||||
if not height:
|
||||
height = int_or_none(self._search_regex(
|
||||
r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
|
||||
if encrypted:
|
||||
format_url = aes_decrypt_text(
|
||||
video_url, title, 32).decode('utf-8')
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': '%dp' % height if height else None,
|
||||
'height': height,
|
||||
'tbr': tbr,
|
||||
})
|
||||
|
||||
flashvars = self._parse_json(
|
||||
self._search_regex(
|
||||
r'flashvars\s*=\s*({.+?});', webpage,
|
||||
'flashvars', default='{}'),
|
||||
display_id, fatal=False)
|
||||
|
||||
if flashvars:
|
||||
title = flashvars.get('video_title')
|
||||
thumbnail = flashvars.get('image_url')
|
||||
duration = int_or_none(flashvars.get('video_duration'))
|
||||
encrypted = flashvars.get('encrypted') is True
|
||||
for key, value in flashvars.items():
|
||||
mobj = re.search(r'quality_(\d+)[pP]', key)
|
||||
if mobj:
|
||||
extract_format(value, int(mobj.group(1)))
|
||||
video_url = flashvars.get('video_url')
|
||||
if video_url and determine_ext(video_url, None):
|
||||
extract_format(video_url)
|
||||
|
||||
video_url = self._html_search_regex(
|
||||
r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
|
||||
webpage, 'video url', default=None, group='url')
|
||||
if video_url:
|
||||
extract_format(compat_urllib_parse_unquote(video_url))
|
||||
|
||||
if not formats:
|
||||
if 'title="This video is no longer available"' in webpage:
|
||||
raise ExtractorError(
|
||||
'Video %s is no longer available' % video_id, expected=True)
|
||||
|
||||
try:
|
||||
self._sort_formats(formats)
|
||||
except ExtractorError:
|
||||
if fatal:
|
||||
raise
|
||||
|
||||
if not title:
|
||||
title = self._html_search_regex(
|
||||
r'<h1[^>]*>([^<]+)', webpage, 'title')
|
||||
|
||||
return webpage, {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': strip_or_none(title),
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'age_limit': 18,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
webpage, info = self._extract_info(url, fatal=False)
|
||||
if not info['formats']:
|
||||
return self.url_result(url, 'Generic')
|
||||
info['view_count'] = str_to_int(self._search_regex(
|
||||
r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
|
||||
return info
|
||||
|
|
@ -1,79 +0,0 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
str_to_int,
|
||||
unified_strdate,
|
||||
)
|
||||
from .keezmovies import KeezMoviesIE
|
||||
|
||||
|
||||
class MofosexIE(KeezMoviesIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
|
||||
'md5': '558fcdafbb63a87c019218d6e49daf8a',
|
||||
'info_dict': {
|
||||
'id': '318131',
|
||||
'display_id': 'amateur-teen-playing-and-masturbating-318131',
|
||||
'ext': 'mp4',
|
||||
'title': 'amateur teen playing and masturbating',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'upload_date': '20121114',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'dislike_count': int,
|
||||
'age_limit': 18,
|
||||
}
|
||||
}, {
|
||||
# This video is no longer available
|
||||
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
webpage, info = self._extract_info(url)
|
||||
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
|
||||
like_count = int_or_none(self._search_regex(
|
||||
r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
|
||||
'like count', fatal=False))
|
||||
dislike_count = int_or_none(self._search_regex(
|
||||
r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
|
||||
'like count', fatal=False))
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
|
||||
|
||||
info.update({
|
||||
'view_count': view_count,
|
||||
'like_count': like_count,
|
||||
'dislike_count': dislike_count,
|
||||
'upload_date': upload_date,
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
})
|
||||
|
||||
return info
|
||||
|
||||
|
||||
class MofosexEmbedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)',
|
||||
webpage)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
return self.url_result(
|
||||
'http://www.mofosex.com/videos/{0}/{0}.html'.format(video_id),
|
||||
ie=MofosexIE.ie_key(), video_id=video_id)
|
||||
|
|
@ -3,13 +3,19 @@ from __future__ import unicode_literals
|
|||
import re
|
||||
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
str_to_int,
|
||||
strip_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
from .keezmovies import KeezMoviesIE
|
||||
from .common import InfoExtractor
|
||||
from ..aes import aes_decrypt_text
|
||||
from ..compat import compat_urllib_parse_unquote
|
||||
|
||||
|
||||
class Tube8IE(KeezMoviesIE):
|
||||
class Tube8IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
|
||||
|
|
@ -37,6 +43,56 @@ class Tube8IE(KeezMoviesIE):
|
|||
r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)',
|
||||
webpage)
|
||||
|
||||
def _extract_info(self, url, fatal=True):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = (mobj.group('display_id')
|
||||
if 'display_id' in mobj.groupdict()
|
||||
else None) or mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(
|
||||
url, display_id, headers={'Cookie': 'age_verified=1'})
|
||||
|
||||
formats = []
|
||||
format_urls = set()
|
||||
|
||||
title = None
|
||||
thumbnail = None
|
||||
duration = None
|
||||
encrypted = False
|
||||
|
||||
def extract_format(format_url, height=None):
|
||||
format_url = url_or_none(format_url)
|
||||
if not format_url or not format_url.startswith(('http', '//')):
|
||||
return
|
||||
if format_url in format_urls:
|
||||
return
|
||||
format_urls.add(format_url)
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
|
||||
if not height:
|
||||
height = int_or_none(self._search_regex(
|
||||
r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
|
||||
if encrypted:
|
||||
format_url = aes_decrypt_text(
|
||||
video_url, title, 32).decode('utf-8')
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': '%dp' % height if height else None,
|
||||
'height': height,
|
||||
'tbr': tbr,
|
||||
})
|
||||
|
||||
flashvars = self._parse_json(
|
||||
self._search_regex(
|
||||
r'flashvars\s*=\s*({.+?});', webpage,
|
||||
'flashvars', default='{}'),
|
||||
display_id, fatal=False)
|
||||
|
||||
if flashvars:
|
||||
title = flashvars.get('video_title')
|
||||
thumbnail = flashvars.get('image_url')
|
||||
|
||||
def _real_extract(self, url):
|
||||
webpage, info = self._extract_info(url)
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue