# audiomack wrapper around soundcloud song
{
'add_ie': ['Soundcloud'],
- 'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
+ 'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
'info_dict': {
- 'id': '172419696',
+ 'id': '258901379',
'ext': 'mp3',
- 'description': 'md5:1fc3272ed7a635cce5be1568c2822997',
- 'title': 'Young Thug ft Lil Wayne - Take Kare',
- 'uploader': 'Young Thug World',
- 'upload_date': '20141016',
+ 'description': 'mamba day freestyle for the legend Kobe Bryant ',
+ 'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
+ 'uploader': 'ILOVEMAKONNEN',
+ 'upload_date': '20160414',
}
},
]
'info_dict': {
'id': '34475836',
'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
+ 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
},
'playlist_count': 3,
}, {
xpath_text,
xpath_element,
int_or_none,
- ExtractorError,
find_xpath_attr,
)
'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
'only_matching': True,
}]
- TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?manifest=m3u&mbr=true'
+ TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
def _real_extract(self, url):
display_id = self._match_id(url)
pid = xpath_text(item, 'pid')
if not pid:
continue
- try:
- tp_formats, tp_subtitles = self._extract_theplatform_smil(
- self.TP_RELEASE_URL_TEMPLATE % pid, content_id, 'Downloading %s SMIL data' % pid)
- except ExtractorError:
- continue
+ tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid
+ if '.m3u8' in xpath_text(item, 'contentUrl', default=''):
+ tp_release_url += '&manifest=m3u'
+ tp_formats, tp_subtitles = self._extract_theplatform_smil(
+ tp_release_url, content_id, 'Downloading %s SMIL data' % pid)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)
import re
from .common import InfoExtractor
+from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
raise ExtractorError(' '.join(response['errors']), expected=True)
def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
- response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
- self._handle_error(response)
+ try:
+ response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
+ except ExtractorError as ee:
+ if isinstance(ee.cause, compat_HTTPError):
+ response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)
+ self._handle_error(response)
+ raise
return response
def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
from .miomio import MioMioIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mitele import MiTeleIE
-from .mixcloud import MixcloudIE
+from .mixcloud import (
+ MixcloudIE,
+ MixcloudUserIE,
+ MixcloudPlaylistIE,
+ MixcloudStreamIE,
+)
from .mlb import MLBIE
from .mnet import MnetIE
from .mpora import MporaIE
from .mofosex import MofosexIE
from .mojvideo import MojvideoIE
from .moniker import MonikerIE
-from .mooshare import MooshareIE
from .morningstar import MorningstarIE
from .motherless import MotherlessIE
from .motorsport import MotorsportIE
from .ndtv import NDTVIE
from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
-from .nerdist import NerdistIE
from .neteasemusic import (
NetEaseMusicIE,
NetEaseMusicAlbumIE,
from .tagesschau import TagesschauIE
from .tapely import TapelyIE
from .tass import TassIE
+from .tdslifeway import TDSLifewayIE
from .teachertube import (
TeacherTubeIE,
TeacherTubeUserIE,
TwitterIE,
TwitterAmplifyIE,
)
-from .ubu import UbuIE
from .udemy import (
UdemyIE,
UdemyCourseIE
from .walla import WallaIE
from .washingtonpost import WashingtonPostIE
from .wat import WatIE
-from .wayofthemaster import WayOfTheMasterIE
from .wdr import (
WDRIE,
WDRMobileIE,
class GazetaIE(InfoExtractor):
- _VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:(?:main|\d{4}/\d{2}/\d{2})/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
+ _VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:main/)*(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
_TESTS = [{
'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml',
'md5': 'd49c9bdc6e5a7888f27475dc215ee789',
'description': 'md5:38617526050bd17b234728e7f9620a71',
'thumbnail': 're:^https?://.*\.jpg',
},
+ 'skip': 'video not found',
}, {
'url': 'http://www.gazeta.ru/lifestyle/video/2015/03/08/master-klass_krasivoi_byt._delaem_vesennii_makiyazh.shtml',
'only_matching': True,
+ }, {
+ 'url': 'http://www.gazeta.ru/video/main/main/2015/06/22/platit_ili_ne_platit_po_isku_yukosa.shtml',
+ 'info_dict': {
+ 'id': '252048',
+ 'ext': 'mp4',
+ 'title': '"Если по иску ЮКОСа придется платить, это будет большой удар по бюджету"',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ 'add_ie': ['EaglePlatform'],
}]
def _real_extract(self, url):
from .jwplatform import JWPlatformIE
from .digiteka import DigitekaIE
from .instagram import InstagramIE
+from .liveleak import LiveLeakIE
class GenericIE(InfoExtractor):
'skip_download': True, # infinite live stream
},
'expected_warnings': [
- r'501.*Not Implemented'
+ r'501.*Not Implemented',
+ r'400.*Bad Request',
],
},
# Direct link with incorrect MIME type
'upload_date': '20160409',
},
},
+ # LiveLeak embed
+ {
+ 'url': 'http://www.wykop.pl/link/3088787/',
+ 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
+ 'info_dict': {
+ 'id': '874_1459135191',
+ 'ext': 'mp4',
+ 'title': 'Man shows poor quality of new apartment building',
+ 'description': 'The wall is like a sand pile.',
+ 'uploader': 'Lake8737',
+ }
+ },
]
def report_following_redirect(self, new_url):
# Look for Instagram embeds
instagram_embed_url = InstagramIE._extract_embed_url(webpage)
if instagram_embed_url is not None:
- return self.url_result(instagram_embed_url, InstagramIE.ie_key())
+ return self.url_result(
+ self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
+
+ # Look for LiveLeak embeds
+ liveleak_url = LiveLeakIE._extract_url(webpage)
+ if liveleak_url:
+ return self.url_result(liveleak_url, 'LiveLeak')
def check_video(vurl):
if YoutubeIE.suitable(vurl):
from .common import InfoExtractor
from ..utils import (
+ determine_ext,
parse_duration,
unified_strdate,
)
'description': 'This week on Legalese It, Mike talks to David Bosco about his new book on the ICC, "Rough Justice," he also discusses the Virginia AG\'s historic stance on gay marriage, the execution of Edgar Tamayo, the ICC\'s delay of Kenya\'s President and more. ',
'duration': 1549,
'upload_date': '20140124',
- }
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['HTTP Error 404: Not Found'],
}
def _real_extract(self, url):
description = data.get('description')
thumbnails = []
- for url in data['images'].values():
+ for url in filter(None, data['images'].values()):
m = re.match('.*-([0-9]+x[0-9]+)\.', url)
if not m:
continue
'resolution': m.group(1),
})
- formats = [{
- 'format': key,
- 'format_id': key.replace('/', '.'),
- 'ext': 'mp4',
- 'url': url,
- 'vcodec': 'none' if key.startswith('audio/') else None,
- } for key, url in data.get('sources', {}).get('live', {}).items()]
+ formats = []
+ sources = data.get('sources', {})
+ live_sources = list(sources.get('live', {}).items()) + list(sources.get('live_again', {}).items())
+ for key, url in live_sources:
+ ext = determine_ext(url)
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ url, video_id, ext='mp4', m3u8_id='hls', fatal=False))
+ elif ext == 'f4m':
+ formats.extend(self._extract_f4m_formats(
+ url + '?hdcore=2.9.5', video_id, f4m_id='hds', fatal=False))
+ else:
+ formats.append({
+ 'format': key,
+ 'format_id': key.replace('/', '.'),
+ 'ext': 'mp4',
+ 'url': url,
+ 'vcodec': 'none' if key.startswith('audio/') else None,
+ })
if not formats and data.get('fivemin_id'):
return self.url_result('5min:%s' % data['fivemin_id'])
class InstagramIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+)'
+ _VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
}, {
'url': 'https://instagram.com/p/-Cmh1cukG2/',
'only_matching': True,
+ }, {
+ 'url': 'http://instagram.com/p/9o6LshA7zy/embed/',
+ 'only_matching': True,
}]
@staticmethod
def _extract_embed_url(webpage):
+ mobj = re.search(
+ r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?instagram\.com/p/[^/]+/embed.*?)\1',
+ webpage)
+ if mobj:
+ return mobj.group('url')
+
blockquote_el = get_element_by_attribute(
'class', 'instagram-media', webpage)
if blockquote_el is None:
return mobj.group('link')
def _real_extract(self, url):
- video_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ url = mobj.group('url')
webpage = self._download_webpage(url, video_id)
uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
IE_NAME = 'iqiyi'
IE_DESC = '爱奇艺'
- _VALID_URL = r'https?://(?:[^.]+\.)?iqiyi\.com/.+\.html'
+ _VALID_URL = r'https?://(?:(?:[^.]+\.)?iqiyi\.com|www\.pps\.tv)/.+\.html'
_NETRC_MACHINE = 'iqiyi'
'title': '灌篮高手 国语版',
},
'playlist_count': 101,
+ }, {
+ 'url': 'http://www.pps.tv/w_19rrbav0ph.html',
+ 'only_matching': True,
}]
_FORMATS_MAP = [
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote_plus
-from ..utils import (
- js_to_json,
-)
class KaraoketvIE(InfoExtractor):
- _VALID_URL = r'https?://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
+ _VALID_URL = r'http://www.karaoketv.co.il/[^/]+/(?P<id>\d+)'
_TEST = {
- 'url': 'http://karaoketv.co.il/?container=songs&id=171568',
+ 'url': 'http://www.karaoketv.co.il/%D7%A9%D7%99%D7%A8%D7%99_%D7%A7%D7%A8%D7%99%D7%95%D7%A7%D7%99/58356/%D7%90%D7%99%D7%96%D7%95%D7%9F',
'info_dict': {
- 'id': '171568',
- 'ext': 'mp4',
- 'title': 'אל העולם שלך - רותם כהן - שרים קריוקי',
+ 'id': '58356',
+ 'ext': 'flv',
+ 'title': 'קריוקי של איזון',
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
+
webpage = self._download_webpage(url, video_id)
+ api_page_url = self._search_regex(
+ r'<iframe[^>]+src=(["\'])(?P<url>https?://www\.karaoke\.co\.il/api_play\.php\?.+?)\1',
+ webpage, 'API play URL', group='url')
+
+ api_page = self._download_webpage(api_page_url, video_id)
+ video_cdn_url = self._search_regex(
+ r'<iframe[^>]+src=(["\'])(?P<url>https?://www\.video-cdn\.com/embed/iframe/.+?)\1',
+ api_page, 'video cdn URL', group='url')
+
+ video_cdn = self._download_webpage(video_cdn_url, video_id)
+ play_path = self._parse_json(
+ self._search_regex(
+ r'var\s+options\s*=\s*({.+?});', video_cdn, 'options'),
+ video_id)['clip']['url']
- page_video_url = self._og_search_video_url(webpage, video_id)
- config_json = compat_urllib_parse_unquote_plus(self._search_regex(
- r'config=(.*)', page_video_url, 'configuration'))
+ settings = self._parse_json(
+ self._search_regex(
+ r'var\s+settings\s*=\s*({.+?});', video_cdn, 'servers', default='{}'),
+ video_id, fatal=False) or {}
- urls_info_json = self._download_json(
- config_json, video_id, 'Downloading configuration',
- transform_source=js_to_json)
+ servers = settings.get('servers')
+ if not servers or not isinstance(servers, list):
+ servers = ('wowzail.video-cdn.com:80/vodcdn', )
- url = urls_info_json['playlist'][0]['url']
+ formats = [{
+ 'url': 'rtmp://%s' % server if not server.startswith('rtmp') else server,
+ 'play_path': play_path,
+ 'app': 'vodcdn',
+ 'page_url': video_cdn_url,
+ 'player_url': 'http://www.video-cdn.com/assets/flowplayer/flowplayer.commercial-3.2.18.swf',
+ 'rtmp_real_time': True,
+ 'ext': 'flv',
+ } for server in servers]
return {
'id': video_id,
'title': self._og_search_title(webpage),
- 'url': url,
+ 'formats': formats,
}
'title': '八十年代精选',
'description': '这些都是属于八十年代的回忆！',
},
- 'playlist_count': 30,
+ 'playlist_count': 24,
}
def _real_extract(self, url):
}
}]
+ @staticmethod
+ def _extract_url(webpage):
+ mobj = re.search(
+ r'<iframe[^>]+src="https?://(?:\w+\.)?liveleak\.com/ll_embed\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)',
+ webpage)
+ if mobj:
+ return 'http://www.liveleak.com/view?i=%s' % mobj.group('id')
+
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
'ext': 'mp4',
'title': 'Beutolomäus und der geheime Weihnachtswunsch',
'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
- 'timestamp': 1419047100,
- 'upload_date': '20141220',
+ 'timestamp': 1450950000,
+ 'upload_date': '20151224',
'duration': 4628,
'uploader': 'KIKA',
},
webpage = self._download_webpage(url, video_id)
data_url = self._search_regex(
- r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>\\?/.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
- webpage, 'data url', default=None, group='url').replace('\/', '/')
+ r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
+ webpage, 'data url', group='url').replace('\/', '/')
doc = self._download_xml(
compat_urlparse.urljoin(url, data_url), video_id)
from __future__ import unicode_literals
-import json
-import re
-
from .common import InfoExtractor
from ..utils import (
ExtractorError,
'id': '3453494717001',
'ext': 'mp4',
'title': 'The Gospel by Numbers',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'upload_date': '20140410',
'description': 'Coming soon from T4G 2014!',
- 'uploader': 'LifeWay Christian Resources (MG)',
+ 'uploader_id': '2034960640001',
+ 'timestamp': 1397145591,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
},
+ 'add_ie': ['TDSLifeway'],
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- portlets_json = self._search_regex(
- r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list')
- portlets = json.loads(portlets_json)
+ portlets = self._parse_json(self._search_regex(
+ r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list'),
+ video_id)
pl_id = self._search_regex(
- r'<!--\s*p_l_id - ([0-9]+)<br>', webpage, 'p_l_id')
+ r'getPlid:function\(\){return"(\d+)"}', webpage, 'p_l_id')
for i, portlet in enumerate(portlets):
portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet)
r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe',
default=None)
if video_iframe_url:
- surl = smuggle_url(
- video_iframe_url, {'force_videoid': video_id})
- return {
- '_type': 'url',
- 'id': video_id,
- 'url': surl,
- }
+ return self.url_result(
+ smuggle_url(video_iframe_url, {'force_videoid': video_id}),
+ video_id=video_id)
raise ExtractorError('Could not find video iframe in any portlets')
from __future__ import unicode_literals
+import base64
+import functools
+import itertools
import re
from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote
+from ..compat import (
+ compat_chr,
+ compat_ord,
+ compat_urllib_parse_unquote,
+ compat_urlparse,
+)
from ..utils import (
+ clean_html,
ExtractorError,
- HEADRequest,
- NO_DEFAULT,
+ OnDemandPagedList,
parse_count,
str_to_int,
)
class MixcloudIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
IE_NAME = 'mixcloud'
_TESTS = [{
'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
'info_dict': {
'id': 'dholbach-cryptkeeper',
- 'ext': 'mp3',
+ 'ext': 'm4a',
'title': 'Cryptkeeper',
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
'uploader': 'Daniel Holbach',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson',
- 'thumbnail': 're:https?://.*/images/',
+ 'thumbnail': 're:https?://.*',
'view_count': int,
'like_count': int,
},
}]
- def _check_url(self, url, track_id, ext):
- try:
- # We only want to know if the request succeed
- # don't download the whole file
- self._request_webpage(
- HEADRequest(url), track_id,
- 'Trying %s URL' % ext)
- return True
- except ExtractorError:
- return False
+ # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
+ @staticmethod
+ def _decrypt_play_info(play_info):
+ KEY = 'pleasedontdownloadourmusictheartistswontgetpaid'
+
+ play_info = base64.b64decode(play_info.encode('ascii'))
+
+ return ''.join([
+ compat_chr(compat_ord(ch) ^ compat_ord(KEY[idx % len(KEY)]))
+ for idx, ch in enumerate(play_info)])
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
webpage, 'error message', default=None)
- preview_url = self._search_regex(
- r'\s(?:data-preview-url|m-preview)="([^"]+)"',
- webpage, 'preview url', default=None if message else NO_DEFAULT)
+ encrypted_play_info = self._search_regex(
+ r'm-play-info="([^"]+)"', webpage, 'play info')
+ play_info = self._parse_json(
+ self._decrypt_play_info(encrypted_play_info), track_id)
- if message:
+ if message and 'stream_url' not in play_info:
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
- song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
- song_url = song_url.replace('/previews/', '/c/originals/')
- if not self._check_url(song_url, track_id, 'mp3'):
- song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
- if not self._check_url(song_url, track_id, 'm4a'):
- raise ExtractorError('Unable to extract track url')
+ song_url = play_info['stream_url']
PREFIX = (
r'm-play-on-spacebar[^>]+'
'view_count': view_count,
'like_count': like_count,
}
+
+
+class MixcloudPlaylistBaseIE(InfoExtractor):
+ _PAGE_SIZE = 24
+
+ def _find_urls_in_page(self, page):
+ for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', page):
+ yield self.url_result(
+ compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
+ MixcloudIE.ie_key())
+
+ def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None):
+ real_page_number = real_page_number or current_page + 1
+ return self._download_webpage(
+ 'https://www.mixcloud.com/%s/' % path, video_id,
+ note='Download %s (page %d)' % (page_name, current_page + 1),
+ errnote='Unable to download %s' % page_name,
+ query={'page': real_page_number, 'list': 'main', '_ajax': '1'},
+ headers={'X-Requested-With': 'XMLHttpRequest'})
+
+ def _tracks_page_func(self, page, video_id, page_name, current_page):
+ resp = self._fetch_tracks_page(page, video_id, page_name, current_page)
+
+ for item in self._find_urls_in_page(resp):
+ yield item
+
+ def _get_user_description(self, page_content):
+ return self._html_search_regex(
+ r'<div[^>]+class="description-text"[^>]*>(.+?)</div>',
+ page_content, 'user description', fatal=False)
+
+
+class MixcloudUserIE(MixcloudPlaylistBaseIE):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
+ IE_NAME = 'mixcloud:user'
+
+ _TESTS = [{
+ 'url': 'http://www.mixcloud.com/dholbach/',
+ 'info_dict': {
+ 'id': 'dholbach_uploads',
+ 'title': 'Daniel Holbach (uploads)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'playlist_mincount': 11,
+ }, {
+ 'url': 'http://www.mixcloud.com/dholbach/uploads/',
+ 'info_dict': {
+ 'id': 'dholbach_uploads',
+ 'title': 'Daniel Holbach (uploads)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'playlist_mincount': 11,
+ }, {
+ 'url': 'http://www.mixcloud.com/dholbach/favorites/',
+ 'info_dict': {
+ 'id': 'dholbach_favorites',
+ 'title': 'Daniel Holbach (favorites)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'params': {
+ 'playlist_items': '1-100',
+ },
+ 'playlist_mincount': 100,
+ }, {
+ 'url': 'http://www.mixcloud.com/dholbach/listens/',
+ 'info_dict': {
+ 'id': 'dholbach_listens',
+ 'title': 'Daniel Holbach (listens)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'params': {
+ 'playlist_items': '1-100',
+ },
+ 'playlist_mincount': 100,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user_id = mobj.group('user')
+ list_type = mobj.group('type')
+
+ # if only a profile URL was supplied, default to download all uploads
+ if list_type is None:
+ list_type = 'uploads'
+
+ video_id = '%s_%s' % (user_id, list_type)
+
+ profile = self._download_webpage(
+ 'https://www.mixcloud.com/%s/' % user_id, video_id,
+ note='Downloading user profile',
+ errnote='Unable to download user profile')
+
+ username = self._og_search_title(profile)
+ description = self._get_user_description(profile)
+
+ entries = OnDemandPagedList(
+ functools.partial(
+ self._tracks_page_func,
+ '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
+ self._PAGE_SIZE, use_cache=True)
+
+ return self.playlist_result(
+ entries, video_id, '%s (%s)' % (username, list_type), description)
+
+
+class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
+ IE_NAME = 'mixcloud:playlist'
+
+ _TESTS = [{
+ 'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
+ 'info_dict': {
+ 'id': 'RedBullThre3style_tokyo-finalists-2015',
+ 'title': 'National Champions 2015',
+ 'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
+ },
+ 'playlist_mincount': 16,
+ }, {
+ 'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
+ 'info_dict': {
+ 'id': 'maxvibes_jazzcat-on-ness-radio',
+ 'title': 'Jazzcat on Ness Radio',
+ 'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
+ },
+ 'playlist_mincount': 23
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user_id = mobj.group('user')
+ playlist_id = mobj.group('playlist')
+ video_id = '%s_%s' % (user_id, playlist_id)
+
+ profile = self._download_webpage(
+ url, user_id,
+ note='Downloading playlist page',
+ errnote='Unable to download playlist page')
+
+ description = self._get_user_description(profile)
+ playlist_title = self._html_search_regex(
+ r'<span[^>]+class="[^"]*list-playlist-title[^"]*"[^>]*>(.*?)</span>',
+ profile, 'playlist title')
+
+ entries = OnDemandPagedList(
+ functools.partial(
+ self._tracks_page_func,
+ '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
+ self._PAGE_SIZE)
+
+ return self.playlist_result(entries, video_id, playlist_title, description)
+
+
+class MixcloudStreamIE(MixcloudPlaylistBaseIE):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
+ IE_NAME = 'mixcloud:stream'
+
+ _TEST = {
+ 'url': 'https://www.mixcloud.com/FirstEar/stream/',
+ 'info_dict': {
+ 'id': 'FirstEar',
+ 'title': 'First Ear',
+ 'description': 'Curators of good music\nfirstearmusic.com',
+ },
+ 'playlist_mincount': 192,
+ }
+
+ def _real_extract(self, url):
+ user_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, user_id)
+
+ entries = []
+ prev_page_url = None
+
+ def _handle_page(page):
+ entries.extend(self._find_urls_in_page(page))
+ return self._search_regex(
+ r'm-next-page-url="([^"]+)"', page,
+ 'next page URL', default=None)
+
+ next_page_url = _handle_page(webpage)
+
+ for idx in itertools.count(0):
+ if not next_page_url or prev_page_url == next_page_url:
+ break
+
+ prev_page_url = next_page_url
+ current_page = int(self._search_regex(
+ r'\?page=(\d+)', next_page_url, 'next page number'))
+
+ next_page_url = _handle_page(self._fetch_tracks_page(
+ '%s/stream' % user_id, user_id, 'stream', idx,
+ real_page_number=current_page))
+
+ username = self._og_search_title(webpage)
+ description = self._get_user_description(webpage)
+
+ return self.playlist_result(entries, user_id, username, description)
+++ /dev/null
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
- sanitized_Request,
- urlencode_postdata,
-)
-
-
-class MooshareIE(InfoExtractor):
- IE_NAME = 'mooshare'
- IE_DESC = 'Mooshare.biz'
- _VALID_URL = r'https?://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
-
- _TESTS = [
- {
- 'url': 'http://mooshare.biz/8dqtk4bjbp8g',
- 'md5': '4e14f9562928aecd2e42c6f341c8feba',
- 'info_dict': {
- 'id': '8dqtk4bjbp8g',
- 'ext': 'mp4',
- 'title': 'Comedy Football 2011 - (part 1-2)',
- 'duration': 893,
- },
- },
- {
- 'url': 'http://mooshare.biz/aipjtoc4g95j',
- 'info_dict': {
- 'id': 'aipjtoc4g95j',
- 'ext': 'mp4',
- 'title': 'Orange Caramel Dashing Through the Snow',
- 'duration': 212,
- },
- 'params': {
- # rtmp download
- 'skip_download': True,
- }
- }
- ]
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- page = self._download_webpage(url, video_id, 'Downloading page')
-
- if re.search(r'>Video Not Found or Deleted<', page) is not None:
- raise ExtractorError('Video %s does not exist' % video_id, expected=True)
-
- hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash')
- title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title')
-
- download_form = {
- 'op': 'download1',
- 'id': video_id,
- 'hash': hash_key,
- }
-
- request = sanitized_Request(
- 'http://mooshare.biz/%s' % video_id, urlencode_postdata(download_form))
- request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-
- self._sleep(5, video_id)
-
- video_page = self._download_webpage(request, video_id, 'Downloading video page')
-
- thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False)
- duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False)
- duration = int(duration_str) if duration_str is not None else None
-
- formats = []
-
- # SD video
- mobj = re.search(r'(?m)file:\s*"(?P<url>[^"]+)",\s*provider:', video_page)
- if mobj is not None:
- formats.append({
- 'url': mobj.group('url'),
- 'format_id': 'sd',
- 'format': 'SD',
- })
-
- # HD video
- mobj = re.search(r'\'hd-2\': { file: \'(?P<url>[^\']+)\' },', video_page)
- if mobj is not None:
- formats.append({
- 'url': mobj.group('url'),
- 'format_id': 'hd',
- 'format': 'HD',
- })
-
- # rtmp video
- mobj = re.search(r'(?m)file: "(?P<playpath>[^"]+)",\s*streamer: "(?P<rtmpurl>rtmp://[^"]+)",', video_page)
- if mobj is not None:
- formats.append({
- 'url': mobj.group('rtmpurl'),
- 'play_path': mobj.group('playpath'),
- 'rtmp_live': False,
- 'ext': 'mp4',
- 'format_id': 'rtmp',
- 'format': 'HD',
- })
-
- return {
- 'id': video_id,
- 'title': title,
- 'thumbnail': thumbnail,
- 'duration': duration,
- 'formats': formats,
- }
+++ /dev/null
-# encoding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-from ..utils import (
- determine_ext,
- parse_iso8601,
- xpath_text,
-)
-
-
-class NerdistIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?nerdist\.com/vepisode/(?P<id>[^/?#]+)'
- _TEST = {
- 'url': 'http://www.nerdist.com/vepisode/exclusive-which-dc-characters-w',
- 'md5': '3698ed582931b90d9e81e02e26e89f23',
- 'info_dict': {
- 'display_id': 'exclusive-which-dc-characters-w',
- 'id': 'RPHpvJyr',
- 'ext': 'mp4',
- 'title': 'Your TEEN TITANS Revealed! Who\'s on the show?',
- 'thumbnail': 're:^https?://.*/thumbs/.*\.jpg$',
- 'description': 'Exclusive: Find out which DC Comics superheroes will star in TEEN TITANS Live-Action TV Show on Nerdist News with Jessica Chobot!',
- 'uploader': 'Eric Diaz',
- 'upload_date': '20150202',
- 'timestamp': 1422892808,
- }
- }
-
- def _real_extract(self, url):
- display_id = self._match_id(url)
- webpage = self._download_webpage(url, display_id)
-
- video_id = self._search_regex(
- r'''(?x)<script\s+(?:type="text/javascript"\s+)?
- src="https?://content\.nerdist\.com/players/([a-zA-Z0-9_]+)-''',
- webpage, 'video ID')
- timestamp = parse_iso8601(self._html_search_meta(
- 'shareaholic:article_published_time', webpage, 'upload date'))
- uploader = self._html_search_meta(
- 'shareaholic:article_author_name', webpage, 'article author')
-
- doc = self._download_xml(
- 'http://content.nerdist.com/jw6/%s.xml' % video_id, video_id)
- video_info = doc.find('.//item')
- title = xpath_text(video_info, './title', fatal=True)
- description = xpath_text(video_info, './description')
- thumbnail = xpath_text(
- video_info, './{http://rss.jwpcdn.com/}image', 'thumbnail')
-
- formats = []
- for source in video_info.findall('./{http://rss.jwpcdn.com/}source'):
- vurl = source.attrib['file']
- ext = determine_ext(vurl)
- if ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- vurl, video_id, entry_protocol='m3u8_native', ext='mp4',
- preference=0))
- elif ext == 'smil':
- formats.extend(self._extract_smil_formats(
- vurl, video_id, fatal=False
- ))
- else:
- formats.append({
- 'format_id': ext,
- 'url': vurl,
- })
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'display_id': display_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'timestamp': timestamp,
- 'formats': formats,
- 'uploader': uploader,
- }
class NewgroundsIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/audio/listen/(?P<id>[0-9]+)'
- _TEST = {
+ _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
+ _TESTS = [{
'url': 'http://www.newgrounds.com/audio/listen/549479',
'md5': 'fe6033d297591288fa1c1f780386f07a',
'info_dict': {
'title': 'B7 - BusMode',
'uploader': 'Burn7',
}
- }
+ }, {
+ 'url': 'http://www.newgrounds.com/portal/view/673111',
+ 'md5': '3394735822aab2478c31b1004fe5e5bc',
+ 'info_dict': {
+ 'id': '673111',
+ 'ext': 'mp4',
+ 'title': 'Dancin',
+ 'uploader': 'Squirrelman82',
+ },
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, music_id)
title = self._html_search_regex(
- r',"name":"([^"]+)",', webpage, 'music title')
+ r'<title>([^>]+)</title>', webpage, 'title')
+
uploader = self._html_search_regex(
- r',"artist":"([^"]+)",', webpage, 'music uploader')
+ [r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
+ webpage, 'uploader')
music_url_json_string = self._html_search_regex(
r'({"url":"[^"]+"),', webpage, 'music url') + '}'
import re
from .common import InfoExtractor
-from ..utils import determine_ext
+from ..utils import (
+ determine_ext,
+ int_or_none,
+)
class OnionStudiosIE(InfoExtractor):
'id': '2937',
'ext': 'mp4',
'title': 'Hannibal charges forward, stops for a cocktail',
- 'description': 'md5:545299bda6abf87e5ec666548c6a9448',
+ 'description': 'md5:e786add7f280b7f0fe237b64cc73df76',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'The A.V. Club',
'uploader_id': 'TheAVClub',
formats = []
for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
- if determine_ext(src) != 'm3u8': # m3u8 always results in 403
+ ext = determine_ext(src)
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+ else:
+ height = int_or_none(self._search_regex(
+ r'/(\d+)\.%s' % ext, src, 'height', default=None))
formats.append({
+ 'format_id': ext + ('-%sp' % height if height else ''),
'url': src,
+ 'height': height,
+ 'ext': ext,
+ 'preference': 1,
})
self._sort_formats(formats)
webpage = self._download_webpage(url, video_id)
error_message = self._html_search_regex(
- r'<div class="message-error">(.+?)</div>',
+ r'<div[^>]+class="message-error"[^>]*>(.+?)</div>',
webpage, 'error message', default=None)
if error_message:
raise ExtractorError(
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
+ js_to_json,
unified_strdate,
)
webpage = self._download_webpage(url, video_id)
- hls = self._search_regex(
- r"sportboxPlayer\.jwplayer_common_params\.file\s*=\s*['\"]([^'\"]+)['\"]",
- webpage, 'hls file')
+ formats = []
- formats = self._extract_m3u8_formats(hls, video_id, 'mp4')
- self._sort_formats(formats)
+ def cleanup_js(code):
+ # desktop_advert_config contains complex Javascripts and we don't need it
+ return js_to_json(re.sub(r'desktop_advert_config.*', '', code))
+
+ jwplayer_data = self._parse_json(self._search_regex(
+ r'(?s)player\.setup\(({.+?})\);', webpage, 'jwplayer settings'), video_id,
+ transform_source=cleanup_js)
+
+ hls_url = jwplayer_data.get('hls_url')
+ if hls_url:
+ formats.extend(self._extract_m3u8_formats(
+ hls_url, video_id, ext='mp4', m3u8_id='hls'))
- title = self._search_regex(
- r'sportboxPlayer\.node_title\s*=\s*"([^"]+)"', webpage, 'title')
+ rtsp_url = jwplayer_data.get('rtsp_url')
+ if rtsp_url:
+ formats.append({
+ 'url': rtsp_url,
+ 'format_id': 'rtsp',
+ })
+
+ self._sort_formats(formats)
- thumbnail = self._search_regex(
- r'sportboxPlayer\.jwplayer_common_params\.image\s*=\s*"([^"]+)"',
- webpage, 'thumbnail', default=None)
+ title = jwplayer_data['node_title']
+ thumbnail = jwplayer_data.get('image_url')
return {
'id': video_id,
--- /dev/null
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class TDSLifewayIE(InfoExtractor):
+ _VALID_URL = r'https?://tds\.lifeway\.com/v1/trainingdeliverysystem/courses/(?P<id>\d+)/index\.html'
+
+ _TEST = {
+ # From http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers
+ 'url': 'http://tds.lifeway.com/v1/trainingdeliverysystem/courses/3453494717001/index.html?externalRegistration=AssetId%7C34F466F1-78F3-4619-B2AB-A8EFFA55E9E9%21InstanceId%7C0%21UserId%7Caaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa&grouping=http%3A%2F%2Flifeway.com%2Fvideo%2F3453494717001&activity_id=http%3A%2F%2Flifeway.com%2Fvideo%2F3453494717001&content_endpoint=http%3A%2F%2Ftds.lifeway.com%2Fv1%2Ftrainingdeliverysystem%2FScormEngineInterface%2FTCAPI%2Fcontent%2F&actor=%7B%22name%22%3A%5B%22Guest%20Guest%22%5D%2C%22account%22%3A%5B%7B%22accountServiceHomePage%22%3A%22http%3A%2F%2Fscorm.lifeway.com%2F%22%2C%22accountName%22%3A%22aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa%22%7D%5D%2C%22objectType%22%3A%22Agent%22%7D&content_token=462a50b2-b6f9-4970-99b1-930882c499fb®istration=93d6ec8e-7f7b-4ed3-bbc8-a857913c0b2a&externalConfiguration=access%7CFREE%21adLength%7C-1%21assignOrgId%7C4AE36F78-299A-425D-91EF-E14A899B725F%21assignOrgParentId%7C%21courseId%7C%21isAnonymous%7Cfalse%21previewAsset%7Cfalse%21previewLength%7C-1%21previewMode%7Cfalse%21royalty%7CFREE%21sessionId%7C671422F9-8E79-48D4-9C2C-4EE6111EA1CD%21trackId%7C&auth=Basic%20OjhmZjk5MDBmLTBlYTMtNDJhYS04YjFlLWE4MWQ3NGNkOGRjYw%3D%3D&endpoint=http%3A%2F%2Ftds.lifeway.com%2Fv1%2Ftrainingdeliverysystem%2FScormEngineInterface%2FTCAPI%2F',
+ 'info_dict': {
+ 'id': '3453494717001',
+ 'ext': 'mp4',
+ 'title': 'The Gospel by Numbers',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'upload_date': '20140410',
+ 'description': 'Coming soon from T4G 2014!',
+ 'uploader_id': '2034960640001',
+ 'timestamp': 1397145591,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ 'add_ie': ['BrightcoveNew'],
+ }
+
+ BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/2034960640001/default_default/index.html?videoId=%s'
+
+ def _real_extract(self, url):
+ brightcove_id = self._match_id(url)
+ return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
else:
formats.append(_format)
- self._sort_formats(formats)
-
subtitles = self._parse_smil_subtitles(meta, default_ns)
return formats, subtitles
smil_url = self._sign_url(smil_url, sig['key'], sig['secret'])
formats, subtitles = self._extract_theplatform_smil(smil_url, video_id)
+ self._sort_formats(formats)
ret = self.get_metadata(path, video_id)
combined_subtitles = self._merge_subtitles(ret.get('subtitles', {}), subtitles)
if quality:
info_url += '&hd' + quality
xml_data = self._download_xml(info_url, video_id, 'Opening the info XML page')
+ error = xml_data.attrib.get('error')
+ if error is not None:
+ raise ExtractorError('Tudou said: %s' % error, expected=True)
final_url = xml_data.text
return final_url
'upload_date': '20140615',
},
'add_ie': ['Vine'],
+ }, {
+ 'url': 'https://twitter.com/captainamerica/status/719944021058060289',
+ # md5 constantly changes
+ 'info_dict': {
+ 'id': '719944021058060289',
+ 'ext': 'mp4',
+ 'title': 'Captain America - @King0fNerd Are you sure you made the right choice? Find out in theaters.',
+ 'description': 'Captain America on Twitter: "@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI"',
+ 'uploader_id': 'captainamerica',
+ 'uploader': 'Captain America',
+ },
}]
def _real_extract(self, url):
'title': username + ' - ' + title,
}
- card_id = self._search_regex(
- r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None)
- if card_id:
- card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
- info.update({
- '_type': 'url_transparent',
- 'ie_key': 'TwitterCard',
- 'url': card_url,
- })
- return info
-
mobj = re.search(r'''(?x)
<video[^>]+class="animated-gif"(?P<more_info>[^>]+)>\s*
<source[^>]+video-src="(?P<url>[^"]+)"
+++ /dev/null
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
- int_or_none,
- qualities,
-)
-
-
-class UbuIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
- _TEST = {
- 'url': 'http://ubu.com/film/her_noise.html',
- 'md5': '138d5652618bf0f03878978db9bef1ee',
- 'info_dict': {
- 'id': 'her_noise',
- 'ext': 'm4v',
- 'title': 'Her Noise - The Making Of (2007)',
- 'duration': 3600,
- },
- }
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- title = self._html_search_regex(
- r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title')
-
- duration = int_or_none(self._html_search_regex(
- r'Duration: (\d+) minutes', webpage, 'duration', fatal=False),
- invscale=60)
-
- formats = []
- FORMAT_REGEXES = [
- ('sq', r"'flashvars'\s*,\s*'file=([^']+)'"),
- ('hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'),
- ]
- preference = qualities([fid for fid, _ in FORMAT_REGEXES])
- for format_id, format_regex in FORMAT_REGEXES:
- m = re.search(format_regex, webpage)
- if m:
- formats.append({
- 'url': m.group(1),
- 'format_id': format_id,
- 'preference': preference(format_id),
- })
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': title,
- 'duration': duration,
- 'formats': formats,
- }
'uploader': 'sportscanadatv',
},
'skip': 'This Pro Broadcaster has chosen to remove this video from the ustream.tv site.',
+ }, {
+ 'url': 'http://www.ustream.tv/embed/10299409',
+ 'info_dict': {
+ 'id': '10299409',
+ },
+ 'playlist_count': 3,
}]
def _real_extract(self, url):
if m.group('type') == 'embed':
video_id = m.group('id')
webpage = self._download_webpage(url, video_id)
- desktop_video_id = self._html_search_regex(
- r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id')
- desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id
- return self.url_result(desktop_url, 'Ustream')
+ content_video_ids = self._parse_json(self._search_regex(
+ r'ustream\.vars\.offAirContentVideoIds=([^;]+);', webpage,
+ 'content video IDs'), video_id)
+ return self.playlist_result(
+ map(lambda u: self.url_result('http://www.ustream.tv/recorded/' + u, 'Ustream'), content_video_ids),
+ video_id)
params = self._download_json(
'https://api.ustream.tv/videos/%s.json' % video_id, video_id)
from __future__ import unicode_literals
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_parse_urlparse,
+ compat_parse_qs,
+)
+from ..utils import (
+ clean_html,
+ remove_start,
+)
class Varzesh3IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?video\.varzesh3\.com/(?:[^/]+/)+(?P<id>[^/]+)/?'
- _TEST = {
+ _TESTS = [{
'url': 'http://video.varzesh3.com/germany/bundesliga/5-%D9%88%D8%A7%DA%A9%D9%86%D8%B4-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AF%D8%B1%D9%88%D8%A7%D8%B2%D9%87%E2%80%8C%D8%A8%D8%A7%D9%86%D8%A7%D9%86%D8%9B%D9%87%D9%81%D8%AA%D9%87-26-%D8%A8%D9%88%D9%86%D8%AF%D8%B3/',
'md5': '2a933874cb7dce4366075281eb49e855',
'info_dict': {
'title': '۵ واکنش برتر دروازهبانان؛هفته ۲۶ بوندسلیگا',
'description': 'فصل ۲۰۱۵-۲۰۱۴',
'thumbnail': 're:^https?://.*\.jpg$',
- }
- }
+ },
+ 'skip': 'HTTP 404 Error',
+ }, {
+ 'url': 'http://video.varzesh3.com/video/112785/%D8%AF%D9%84%D9%87-%D8%B9%D9%84%DB%8C%D8%9B-%D8%B3%D8%AA%D8%A7%D8%B1%D9%87-%D9%86%D9%88%D8%B8%D9%87%D9%88%D8%B1-%D9%84%DB%8C%DA%AF-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AC%D8%B2%DB%8C%D8%B1%D9%87',
+ 'md5': '841b7cd3afbc76e61708d94e53a4a4e7',
+ 'info_dict': {
+ 'id': '112785',
+ 'ext': 'mp4',
+ 'title': 'دله علی؛ ستاره نوظهور لیگ برتر جزیره',
+ 'description': 'فوتبال 120',
+ },
+ 'expected_warnings': ['description'],
+ }]
def _real_extract(self, url):
display_id = self._match_id(url)
video_url = self._search_regex(
r'<source[^>]+src="([^"]+)"', webpage, 'video url')
- title = self._og_search_title(webpage)
+ title = remove_start(self._html_search_regex(
+ r'<title>([^<]+)</title>', webpage, 'title'), 'ویدیو ورزش 3 | ')
+
description = self._html_search_regex(
r'(?s)<div class="matn">(.+?)</div>',
- webpage, 'description', fatal=False)
- thumbnail = self._og_search_thumbnail(webpage)
+ webpage, 'description', default=None)
+ if description is None:
+ description = clean_html(self._html_search_meta('description', webpage))
+
+ thumbnail = self._og_search_thumbnail(webpage, default=None)
+ if thumbnail is None:
+ fb_sharer_url = self._search_regex(
+ r'<a[^>]+href="(https?://www\.facebook\.com/sharer/sharer\.php?[^"]+)"',
+ webpage, 'facebook sharer URL', fatal=False)
+ sharer_params = compat_parse_qs(compat_urllib_parse_urlparse(fb_sharer_url).query)
+ thumbnail = sharer_params.get('p[images][0]', [None])[0]
video_id = self._search_regex(
r"<link[^>]+rel='(?:canonical|shortlink)'[^>]+href='/\?p=([^']+)'",
- webpage, display_id, default=display_id)
+ webpage, display_id, default=None)
+ if video_id is None:
+ video_id = self._search_regex(
+ 'var\s+VideoId\s*=\s*(\d+);', webpage, 'video id',
+ default=display_id)
return {
'url': video_url,
'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
'info_dict': {
'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
- 'ext': 'mp4',
+ 'ext': 'flv',
'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
'duration': 725.983,
},
- 'params': {
- # Requires ffmpeg (m3u8 manifest)
- 'skip_download': True,
+ }, {
+ 'url': 'http://www.vice.com/video/how-to-hack-a-car',
+ 'md5': '6fb2989a3fed069fb8eab3401fc2d3c9',
+ 'info_dict': {
+ 'id': '3jstaBeXgAs',
+ 'ext': 'mp4',
+ 'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
+ 'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
+ 'uploader_id': 'MotherboardTV',
+ 'uploader': 'Motherboard',
+ 'upload_date': '20140529',
},
}, {
'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
try:
embed_code = self._search_regex(
r'embedCode=([^&\'"]+)', webpage,
- 'ooyala embed code')
- ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
+ 'ooyala embed code', default=None)
+ if embed_code:
+ ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
+ return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
+ youtube_id = self._search_regex(
+ r'data-youtube-id="([^"]+)"', webpage, 'youtube id')
+ return self.url_result(youtube_id, 'Youtube')
except ExtractorError:
raise ExtractorError('The page doesn\'t contain a video', expected=True)
- return self.url_result(ooyala_url, ie='Ooyala')
class ViceShowIE(InfoExtractor):
+++ /dev/null
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-
-class WayOfTheMasterIE(InfoExtractor):
- _VALID_URL = r'https?://www\.wayofthemaster\.com/([^/?#]*/)*(?P<id>[^/?#]+)\.s?html(?:$|[?#])'
-
- _TEST = {
- 'url': 'http://www.wayofthemaster.com/hbks.shtml',
- 'md5': '5316b57487ada8480606a93cb3d18d24',
- 'info_dict': {
- 'id': 'hbks',
- 'ext': 'mp4',
- 'title': 'Intelligent Design vs. Evolution',
- },
- }
-
- 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 = self._search_regex(
- r'<img src="images/title_[^"]+".*?alt="([^"]+)"',
- webpage, 'title', default=None)
- if title is None:
- title = self._html_search_regex(
- r'<title>(.*?)</title>', webpage, 'page title')
-
- url_base = self._search_regex(
- r'<param\s+name="?movie"?\s+value=".*?/wotm_videoplayer_highlow[0-9]*\.swf\?vid=([^"]+)"',
- webpage, 'URL base')
- formats = [{
- 'format_id': 'low',
- 'quality': 1,
- 'url': url_base + '_low.mp4',
- }, {
- 'format_id': 'high',
- 'quality': 2,
- 'url': url_base + '_high.mp4',
- }]
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': title,
- 'formats': formats,
- }
class XboxClipsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?xboxclips\.com/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\w-]{36})'
_TEST = {
- 'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
+ 'url': 'http://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
'info_dict': {
'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
def suitable(cls, url):
# Don't return True if the url can be extracted with other youtube
# extractor, the regex would is too permissive and it would match.
- other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls)
- if any(ie.suitable(url) for ie in other_ies):
+ other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
+ if any(ie.suitable(url) for ie in other_yt_ies):
return False
else:
return super(YoutubeUserIE, cls).suitable(url)
projects / youtube-dl / commitdiff