R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into paj/sbs-news-without-id

Browse Source
This commit is contained in:
Pete Johns 2019-05-27 11:15:06 +10:00
commit e355d11e13
No known key found for this signature in database
GPG Key ID: 06099EDB683EDD63
17 changed files with 99 additions and 397 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.travis.yml
View File

@ -9,6 +9,7 @@ python:
- "3.6"
- "pypy"
- "pypy3"
dist: trusty
env:
- YTDL_TEST_SET=core
- YTDL_TEST_SET=download

13
test/test_utils.py
View File

@ -73,6 +73,7 @@ from youtube_dl.utils import (
smuggle_url,
str_to_int,
strip_jsonp,
strip_or_none,
timeconvert,
unescapeHTML,
unified_strdate,
@ -752,6 +753,18 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_strip_or_none(self):
self.assertEqual(strip_or_none(' abc'), 'abc')
self.assertEqual(strip_or_none('abc '), 'abc')
self.assertEqual(strip_or_none(' abc '), 'abc')
self.assertEqual(strip_or_none('\tabc\t'), 'abc')
self.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc')
self.assertEqual(strip_or_none('abc'), 'abc')
self.assertEqual(strip_or_none(''), '')
self.assertEqual(strip_or_none(None), None)
self.assertEqual(strip_or_none(42), None)
self.assertEqual(strip_or_none([]), None)
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')

5
youtube_dl/extractor/bitchute.py
View File

@ -65,8 +65,9 @@ class BitChuteIE(InfoExtractor):
webpage, default=None) or self._html_search_meta(
'twitter:image:src', webpage, 'thumbnail')
uploader = self._html_search_regex(
r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage,
'uploader', fatal=False)
(r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
webpage, 'uploader', fatal=False)
return {
'id': video_id,

7
youtube_dl/extractor/common.py
View File

@ -67,6 +67,7 @@ from ..utils import (
sanitized_Request,
sanitize_filename,
str_or_none,
strip_or_none,
unescapeHTML,
unified_strdate,
unified_timestamp,
@ -2480,7 +2481,7 @@ class InfoExtractor(object):
'subtitles': {},
}
media_attributes = extract_attributes(media_tag)
src = media_attributes.get('src')
src = strip_or_none(media_attributes.get('src'))
if src:
_, formats = _media_formats(src, media_type)
media_info['formats'].extend(formats)
@ -2490,7 +2491,7 @@ class InfoExtractor(object):
s_attr = extract_attributes(source_tag)
# data-video-src and data-src are non standard but seen
# several times in the wild
src = dict_get(s_attr, ('src', 'data-video-src', 'data-src'))
src = strip_or_none(dict_get(s_attr, ('src', 'data-video-src', 'data-src')))
if not src:
continue
f = parse_content_type(s_attr.get('type'))
@ -2533,7 +2534,7 @@ class InfoExtractor(object):
track_attributes = extract_attributes(track_tag)
kind = track_attributes.get('kind')
if not kind or kind in ('subtitles', 'captions'):
src = track_attributes.get('src')
src = strip_or_none(track_attributes.get('src'))
if not src:
continue
lang = track_attributes.get('srclang') or track_attributes.get('lang') or track_attributes.get('label')

39
youtube_dl/extractor/criterion.py
View File

@ -1,39 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class CriterionIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P<id>[0-9]+)-.+'
_TEST = {
'url': 'http://www.criterion.com/films/184-le-samourai',
'md5': 'bc51beba55685509883a9a7830919ec3',
'info_dict': {
'id': '184',
'ext': 'mp4',
'title': 'Le Samouraï',
'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
'thumbnail': r're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
final_url = self._search_regex(
r'so\.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
title = self._og_search_title(webpage)
description = self._html_search_meta('description', webpage)
thumbnail = self._search_regex(
r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url')
return {
'id': video_id,
'url': final_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}

9
youtube_dl/extractor/extractors.py
View File

@ -240,7 +240,6 @@ from .condenast import CondeNastIE
from .corus import CorusIE
from .cracked import CrackedIE
from .crackle import CrackleIE
from .criterion import CriterionIE
from .crooksandliars import CrooksAndLiarsIE
from .crunchyroll import (
CrunchyrollIE,
@ -772,13 +771,6 @@ from .nova import (
NovaEmbedIE,
NovaIE,
)
from .novamov import (
AuroraVidIE,
CloudTimeIE,
NowVideoIE,
VideoWeedIE,
WholeCloudIE,
)
from .nowness import (
NownessIE,
NownessPlaylistIE,
@ -896,7 +888,6 @@ from .polskieradio import (
from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE
from .porncom import PornComIE
from .pornflip import PornFlipIE
from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,

13
youtube_dl/extractor/generic.py
View File

@ -2583,19 +2583,6 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group(1), 'Mpora')
# Look for embedded NovaMov-based player
mobj = re.search(
r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
(?P<url>http://(?:(?:embed|www)\.)?
(?:novamov\.com|
nowvideo\.(?:ch|sx|eu|at|ag|co)|
videoweed\.(?:es|com)|
movshare\.(?:net|sx|ag)|
divxstage\.(?:eu|net|ch|co|at|ag))
/embed\.php.+?)\1''', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for embedded Facebook player
facebook_urls = FacebookIE._extract_urls(webpage)
if facebook_urls:

212
youtube_dl/extractor/novamov.py
View File

@ -1,212 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
NO_DEFAULT,
sanitized_Request,
urlencode_postdata,
)
class NovaMovIE(InfoExtractor):
IE_NAME = 'novamov'
IE_DESC = 'NovaMov'
_VALID_URL_TEMPLATE = r'''(?x)
http://
(?:
(?:www\.)?%(host)s/(?:file|video|mobile/\#/videos)/|
(?:(?:embed|www)\.)%(host)s/embed(?:\.php|/)?\?(?:.*?&)?\bv=
)
(?P<id>[a-z\d]{13})
'''
_VALID_URL = _VALID_URL_TEMPLATE % {'host': r'novamov\.com'}
_HOST = 'www.novamov.com'
_FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
_FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);'
_TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
_DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
_URL_TEMPLATE = 'http://%s/video/%s'
_TEST = None
def _check_existence(self, webpage, video_id):
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
url = self._URL_TEMPLATE % (self._HOST, video_id)
webpage = self._download_webpage(
url, video_id, 'Downloading video page')
self._check_existence(webpage, video_id)
def extract_filekey(default=NO_DEFAULT):
filekey = self._search_regex(
self._FILEKEY_REGEX, webpage, 'filekey', default=default)
if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
return self._search_regex(
r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default)
else:
return filekey
filekey = extract_filekey(default=None)
if not filekey:
fields = self._hidden_inputs(webpage)
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
'post url', default=url, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(url, post_url)
request = sanitized_Request(
post_url, urlencode_postdata(fields))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
request.add_header('Referer', post_url)
webpage = self._download_webpage(
request, video_id, 'Downloading continue to the video page')
self._check_existence(webpage, video_id)
filekey = extract_filekey()
title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title')
description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
api_response = self._download_webpage(
'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
'Downloading video api response')
response = compat_urlparse.parse_qs(api_response)
if 'error_msg' in response:
raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
video_url = response['url'][0]
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description
}
class WholeCloudIE(NovaMovIE):
IE_NAME = 'wholecloud'
IE_DESC = 'WholeCloud'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
_HOST = 'www.wholecloud.net'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
_DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
_TEST = {
'url': 'http://www.wholecloud.net/video/559e28be54d96',
'md5': 'abd31a2132947262c50429e1d16c1bfd',
'info_dict': {
'id': '559e28be54d96',
'ext': 'flv',
'title': 'dissapeared image',
'description': 'optical illusion dissapeared image magic illusion',
}
}
class NowVideoIE(NovaMovIE):
IE_NAME = 'nowvideo'
IE_DESC = 'NowVideo'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
_HOST = 'www.nowvideo.to'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<h4>([^<]+)</h4>'
_DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
_TEST = {
'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b',
'md5': '12c82cad4f2084881d8bc60ee29df092',
'info_dict': {
'id': 'f1d6fce9a968b',
'ext': 'flv',
'title': 'youtubedl test video BaWjenozKc',
'description': 'Description',
},
}
class VideoWeedIE(NovaMovIE):
IE_NAME = 'videoweed'
IE_DESC = 'VideoWeed'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'videoweed\.(?:es|com)'}
_HOST = 'www.videoweed.es'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
_URL_TEMPLATE = 'http://%s/file/%s'
_TEST = {
'url': 'http://www.videoweed.es/file/b42178afbea14',
'md5': 'abd31a2132947262c50429e1d16c1bfd',
'info_dict': {
'id': 'b42178afbea14',
'ext': 'flv',
'title': 'optical illusion dissapeared image magic illusion',
'description': ''
},
}
class CloudTimeIE(NovaMovIE):
IE_NAME = 'cloudtime'
IE_DESC = 'CloudTime'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'cloudtime\.to'}
_HOST = 'www.cloudtime.to'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
_TEST = None
class AuroraVidIE(NovaMovIE):
IE_NAME = 'auroravid'
IE_DESC = 'AuroraVid'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'auroravid\.to'}
_HOST = 'www.auroravid.to'
_FILE_DELETED_REGEX = r'This file no longer exists on our servers!<'
_TESTS = [{
'url': 'http://www.auroravid.to/video/4rurhn9x446jj',
'md5': '7205f346a52bbeba427603ba10d4b935',
'info_dict': {
'id': '4rurhn9x446jj',
'ext': 'flv',
'title': 'search engine optimization',
'description': 'search engine optimization is used to rank the web page in the google search engine'
},
'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
}, {
'url': 'http://www.auroravid.to/embed/?v=4rurhn9x446jj',
'only_matching': True,
}]

5
youtube_dl/extractor/openload.py
View File

@ -244,7 +244,7 @@ class PhantomJSwrapper(object):
class OpenloadIE(InfoExtractor):
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space|services)|oladblock\.(?:services|xyz|me)|openloed\.co)'
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|live|space|services)|oladblock\.(?:services|xyz|me)|openloed\.co)'
_VALID_URL = r'''(?x)
https?://
(?P<host>
@ -357,6 +357,9 @@ class OpenloadIE(InfoExtractor):
}, {
'url': 'https://oload.services/embed/bs1NWj1dCag/',
'only_matching': True,
}, {
'url': 'https://oload.press/embed/drTBl1aOTvk/',
'only_matching': True,
}, {
'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
'only_matching': True,

101
youtube_dl/extractor/pornflip.py
View File

@ -1,101 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
)
from ..utils import (
int_or_none,
try_get,
unified_timestamp,
)
class PornFlipIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
'md5': '98c46639849145ae1fd77af532a9278c',
'info_dict': {
'id': 'wz7DfNhMmep',
'ext': 'mp4',
'title': '2 Amateurs swallow make his dream cumshots true',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 112,
'timestamp': 1481655502,
'upload_date': '20161213',
'uploader_id': '106786',
'uploader': 'figifoto',
'view_count': int,
'age_limit': 18,
}
}, {
'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
'only_matching': True,
}, {
'url': 'https://www.pornflip.com/v/EkRD6-vS2-s',
'only_matching': True,
}, {
'url': 'https://www.pornflip.com/embed/EkRD6-vS2-s',
'only_matching': True,
}, {
'url': 'https://www.pornflip.com/v/NG9q6Pb_iK8',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://www.pornflip.com/v/%s' % video_id, video_id)
flashvars = compat_parse_qs(self._search_regex(
r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
webpage, 'flashvars', group='flashvars'))
title = flashvars['video_vars[title]'][0]
def flashvar(kind):
return try_get(
flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
formats = []
for key, value in flashvars.items():
if not (value and isinstance(value, list)):
continue
format_url = value[0]
if key == 'video_vars[hds_manifest]':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False))
continue
height = self._search_regex(
r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
if not height:
continue
formats.append({
'url': format_url,
'format_id': 'http-%s' % height,
'height': int_or_none(height),
})
self._sort_formats(formats)
uploader = self._html_search_regex(
(r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
webpage, 'uploader', fatal=False, group='uploader')
return {
'id': video_id,
'formats': formats,
'title': title,
'thumbnail': flashvar('big_thumb'),
'duration': int_or_none(flashvar('duration')),
'timestamp': unified_timestamp(self._html_search_meta(
'uploadDate', webpage, 'timestamp')),
'uploader_id': flashvar('author_id'),
'uploader': uploader,
'view_count': int_or_none(flashvar('views')),
'age_limit': 18,
}

2
youtube_dl/extractor/pornhub.py
View File

@ -170,7 +170,7 @@ class PornHubIE(PornHubBaseIE):
def dl_webpage(platform):
self._set_cookie(host, 'platform', platform)
return self._download_webpage(
'http://www.%s/view_video.php?viewkey=%s' % (host, video_id),
'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
video_id, 'Downloading %s webpage' % platform)
webpage = dl_webpage('pc')

37
youtube_dl/extractor/shared.py
View File

@ -3,8 +3,11 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
KNOWN_EXTENSIONS,
parse_filesize,
url_or_none,
urlencode_postdata,
)
@ -22,10 +25,8 @@ class SharedBaseIE(InfoExtractor):
video_url = self._extract_video_url(webpage, video_id, url)
title = compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
title = self._extract_title(webpage)
filesize = int_or_none(self._extract_filesize(webpage))
return {
'id': video_id,
@ -35,6 +36,14 @@ class SharedBaseIE(InfoExtractor):
'title': title,
}
def _extract_title(self, webpage):
return compat_b64decode(self._html_search_meta(
'full:title', webpage, 'title')).decode('utf-8')
def _extract_filesize(self, webpage):
return self._html_search_meta(
'full:size', webpage, 'file size', fatal=False)
class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx'
@ -82,11 +91,27 @@ class VivoIE(SharedBaseIE):
'id': 'd7ddda0e78',
'ext': 'mp4',
'title': 'Chicken',
'filesize': 528031,
'filesize': 515659,
},
}
def _extract_video_url(self, webpage, video_id, *args):
def _extract_title(self, webpage):
title = self._html_search_regex(
r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
'title', default=None, group='title')
if title:
ext = determine_ext(title)
if ext.lower() in KNOWN_EXTENSIONS:
title = title.rpartition('.' + ext)[0]
return title
return self._og_search_title(webpage)
def _extract_filesize(self, webpage):
return parse_filesize(self._search_regex(
r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)',
webpage, 'filesize', fatal=False))
def _extract_video_url(self, webpage, video_id, url):
def decode_url(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8')

19
youtube_dl/extractor/srgssr.py
View File

@ -106,7 +106,16 @@ class SRGSSRIE(InfoExtractor):
class SRGSSRPlayIE(InfoExtractor):
IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites'
_VALID_URL = r'https?://(?:(?:www|play)\.)?(?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/[^/]+/(?P<type>video|audio)/[^?]+\?id=(?P<id>[0-9a-f\-]{36}|\d+)'
_VALID_URL = r'''(?x)
https?://
(?:(?:www|play)\.)?
(?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/
(?:
[^/]+/(?P<type>video|audio)/[^?]+|
popup(?P<type_2>video|audio)player
)
\?id=(?P<id>[0-9a-f\-]{36}|\d+)
'''
_TESTS = [{
'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
@ -163,9 +172,15 @@ class SRGSSRPlayIE(InfoExtractor):
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
'only_matching': True,
}]
def _real_extract(self, url):
bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
mobj = re.match(self._VALID_URL, url)
bu = mobj.group('bu')
media_type = mobj.group('type') or mobj.group('type_2')
media_id = mobj.group('id')
# other info can be extracted from url + '&layout=json'
return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')

2
youtube_dl/extractor/streamcloud.py
View File

@ -45,7 +45,7 @@ class StreamcloudIE(InfoExtractor):
value="([^"]*)"
''', orig_webpage)
self._sleep(12, video_id)
self._sleep(6, video_id)
webpage = self._download_webpage(
url, video_id, data=urlencode_postdata(fields), headers={

19
youtube_dl/extractor/twentyfourvideo.py
View File

@ -14,7 +14,18 @@ from ..utils import (
class TwentyFourVideoIE(InfoExtractor):
IE_NAME = '24video'
_VALID_URL = r'https?://(?P<host>(?:www\.)?24video\.(?:net|me|xxx|sexy?|tube|adult))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
_VALID_URL = r'''(?x)
https?://
(?P<host>
(?:(?:www|porno)\.)?24video\.
(?:net|me|xxx|sexy?|tube|adult|site)
)/
(?:
video/(?:(?:view|xml)/)?|
player/new24_play\.swf\?id=
)
(?P<id>\d+)
'''
_TESTS = [{
'url': 'http://www.24video.net/video/view/1044982',
@ -42,6 +53,12 @@ class TwentyFourVideoIE(InfoExtractor):
}, {
'url': 'http://www.24video.tube/video/view/2363750',
'only_matching': True,
}, {
'url': 'https://www.24video.site/video/view/2640421',
'only_matching': True,
}, {
'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle',
'only_matching': True,
}]
def _real_extract(self, url):

8
youtube_dl/extractor/youtube.py
View File

@ -1789,9 +1789,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
raise ExtractorError(
'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
if video_info.get('license_info'):
raise ExtractorError('This video is DRM protected.', expected=True)
video_details = try_get(
player_response, lambda x: x['videoDetails'], dict) or {}
@ -1927,7 +1924,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
formats = []
for url_data_str in encoded_url_map.split(','):
url_data = compat_parse_qs(url_data_str)
if 'itag' not in url_data or 'url' not in url_data:
if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'):
continue
stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
# Unsupported FORMAT_STREAM_TYPE_OTF
@ -2323,6 +2320,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'"token" parameter not in video info for unknown reason',
video_id=video_id)
if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
raise ExtractorError('This video is DRM protected.', expected=True)
self._sort_formats(formats)
self.mark_watched(video_id, video_info, player_response)

4
youtube_dl/utils.py
View File

@ -1951,8 +1951,8 @@ def bool_or_none(v, default=None):
return v if isinstance(v, bool) else default
def strip_or_none(v):
return None if v is None else v.strip()
def strip_or_none(v, default=None):
return v.strip() if isinstance(v, compat_str) else default
def url_or_none(url):