from .youtube import YoutubeIE
from ..compat import (
compat_etree_fromstring,
+ compat_str,
compat_urllib_parse_unquote,
compat_urlparse,
compat_xml_parse_error,
HEADRequest,
is_html,
js_to_json,
+ KNOWN_EXTENSIONS,
+ mimetype2ext,
orderedSet,
sanitized_Request,
smuggle_url,
BrightcoveLegacyIE,
BrightcoveNewIE,
)
+from .nexx import (
+ NexxIE,
+ NexxEmbedIE,
+)
from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
DailymotionIE,
DailymotionCloudIE,
)
+from .dailymail import DailyMailIE
from .onionstudios import OnionStudiosIE
from .viewlift import ViewLiftEmbedIE
from .mtv import MTVServicesEmbeddedIE
from .openload import OpenloadIE
from .videopress import VideoPressIE
from .rutube import RutubeIE
+from .limelight import LimelightBaseIE
+from .anvato import AnvatoIE
+from .washingtonpost import WashingtonPostIE
+from .wistia import WistiaIE
+from .mediaset import MediasetIE
+from .joj import JojIE
+from .megaphone import MegaphoneIE
+from .vzaar import VzaarIE
+from .channel9 import Channel9IE
class GenericIE(InfoExtractor):
'skip_download': True, # m3u8 download
},
},
+ {
+ # Brightcove video in <iframe>
+ 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
+ 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
+ 'info_dict': {
+ 'id': '5360463607001',
+ 'ext': 'mp4',
+ 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
+ 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼（Zade Dirani）在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》（HEARTBEAT），为受到六年冲突影响的叙利亚儿童发出强烈呐喊，呼吁世界做出共同努力，使叙利亚儿童重新获得享有正常童年生活的权利。',
+ 'uploader': 'United Nations',
+ 'uploader_id': '1362235914001',
+ 'timestamp': 1489593889,
+ 'upload_date': '20170315',
+ },
+ 'add_ie': ['BrightcoveLegacy'],
+ },
{
# Brightcove with alternative playerID key
'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
},
}],
},
+ {
+ # Brightcove with UUID in videoPlayer
+ 'url': 'http://www8.hp.com/cn/zh/home.html',
+ 'info_dict': {
+ 'id': '5255815316001',
+ 'ext': 'mp4',
+ 'title': 'Sprocket Video - China',
+ 'description': 'Sprocket Video - China',
+ 'uploader': 'HP-Video Gallery',
+ 'timestamp': 1482263210,
+ 'upload_date': '20161220',
+ 'uploader_id': '1107601872001',
+ },
+ 'params': {
+ 'skip_download': True, # m3u8 download
+ },
+ 'skip': 'video rotates...weekly?',
+ },
+ {
+ # Brightcove:new type [2].
+ 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
+ 'md5': '2b35148fcf48da41c9fb4591650784f3',
+ 'info_dict': {
+ 'id': '5348741021001',
+ 'ext': 'mp4',
+ 'upload_date': '20170306',
+ 'uploader_id': '4191638492001',
+ 'timestamp': 1488769918,
+ 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
+
+ },
+ },
+ {
+ # Alternative brightcove <video> attributes
+ 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
+ 'info_dict': {
+ 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
+ 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
+ },
+ 'playlist': [{
+ 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
+ 'info_dict': {
+ 'id': '5311302538001',
+ 'ext': 'mp4',
+ 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
+ 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
+ 'timestamp': 1486321708,
+ 'upload_date': '20170205',
+ 'uploader_id': '800000640001',
+ },
+ 'only_matching': True,
+ }],
+ },
{
# Brightcove with UUID in videoPlayer
'url': 'http://www8.hp.com/cn/zh/home.html',
},
'skip': 'movie expired',
},
+ # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
+ {
+ 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
+ 'info_dict': {
+ 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
+ 'ext': 'mp4',
+ 'title': 'Steampunk Fest Comes to Honesdale',
+ 'duration': 43.276,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ },
# embed.ly video
{
'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
},
'add_ie': ['Dailymotion'],
},
+ # DailyMail embed
+ {
+ 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
+ 'info_dict': {
+ 'id': '1495629',
+ 'ext': 'mp4',
+ 'title': 'Care worker punches elderly dementia patient in head 11 times',
+ 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
+ },
+ 'add_ie': ['DailyMail'],
+ 'params': {
+ 'skip_download': True,
+ },
+ },
# YouTube embed
{
'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
'skip_download': True,
}
},
+ # YouTube <object> embed
+ {
+ 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
+ 'md5': '516718101ec834f74318df76259fb3cc',
+ 'info_dict': {
+ 'id': 'msN87y-iEx0',
+ 'ext': 'webm',
+ 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
+ 'upload_date': '20080526',
+ 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
+ 'uploader': 'Christopher Sykes',
+ 'uploader_id': 'ChristopherJSykes',
+ },
+ 'add_ie': ['Youtube'],
+ },
# Camtasia studio
{
'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
'ext': 'mp4',
'upload_date': '20150212',
'uploader': 'The National Archives UK',
- 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
+ 'description': 'md5:8078af856dca76edc42910b61273dbbf',
'uploader_id': 'NationalArchives08',
'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
},
},
'params': {
'skip_download': True,
- }
+ },
+ 'skip': 'does not contain a video anymore',
},
# Complex jwplayer
{
'id': 'videos',
'ext': 'mp4',
'title': 'king machine trailer 1',
+ 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
'thumbnail': r're:^https?://.*\.jpg$',
},
},
'skip_download': True,
}
},
+ {
+ # Video.js embed, multiple formats
+ 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
+ 'info_dict': {
+ 'id': 'yygqldloqIk',
+ 'ext': 'mp4',
+ 'title': 'SolidWorks. Урок 6 Настройка чертежа',
+ 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
+ 'upload_date': '20130314',
+ 'uploader': 'PROстое3D',
+ 'uploader_id': 'PROstoe3D',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ # Video.js embed, single format
+ 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
+ 'info_dict': {
+ 'id': 'watch',
+ 'ext': 'mp4',
+ 'title': 'Step 1 - Good Foundation',
+ 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
# rtl.nl embed
{
'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
'playlist_mincount': 5,
'info_dict': {
'id': 'aanslagen-kopenhagen',
- 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
+ 'title': 'Aanslagen Kopenhagen',
}
},
# Zapiks embed
},
'add_ie': ['Kaltura'],
},
- # Eagle.Platform embed (generic URL)
+ {
+ # Kaltura iframe embed
+ 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
+ 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
+ 'info_dict': {
+ 'id': '0_f2cfbpwy',
+ 'ext': 'mp4',
+ 'title': 'I. M. Pei: A Centennial Celebration',
+ 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
+ 'upload_date': '20170403',
+ 'uploader_id': 'batchUser',
+ 'timestamp': 1491232186,
+ },
+ 'add_ie': ['Kaltura'],
+ },
+ # EaglePlatform embed (generic URL)
{
'url': 'http://lenta.ru/news/2015/03/06/navalny/',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
'view_count': int,
'age_limit': 0,
},
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ # referrer protected EaglePlatform embed
+ {
+ 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
+ 'info_dict': {
+ 'id': '582306',
+ 'ext': 'mp4',
+ 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'duration': 3382,
+ 'view_count': int,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
},
- # ClipYou (Eagle.Platform) embed (custom URL)
+ # ClipYou (EaglePlatform) embed (custom URL)
{
'url': 'http://muz-tv.ru/play/7129/',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
'duration': 216,
'view_count': int,
},
+ 'params': {
+ 'skip_download': True,
+ },
+ 'skip': 'This video is unavailable.',
},
# Pladform embed
{
'duration': 694,
'age_limit': 0,
},
+ 'skip': 'HTTP Error 404: Not Found',
},
# Playwire embed
{
'id': '518726732',
'ext': 'mp4',
'title': 'Facebook Creates "On This Day" | Crunch Report',
+ 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
+ 'timestamp': 1427237531,
+ 'uploader': 'Crunch Report',
+ 'upload_date': '20150324',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
},
},
# SVT embed
'upload_date': '20140107',
'timestamp': 1389118457,
},
+ 'skip': 'Invalid Page URL',
},
# NBC News embed
{
'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
'md5': '1aa589c675898ae6d37a17913cf68d66',
'info_dict': {
- 'id': '701714499682',
+ 'id': 'x_dtl_oa_LettermanliftPR_160608',
'ext': 'mp4',
- 'title': 'PREVIEW: On Assignment: David Letterman',
+ 'title': 'David Letterman: A Preview',
'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
+ 'upload_date': '20160609',
+ 'timestamp': 1465431544,
+ 'uploader': 'NBCU-NEWS',
},
},
# UDN embed
# m3u8 download
'skip_download': True,
},
+ 'expected_warnings': ['Failed to parse JSON Expecting value'],
},
# Ooyala embed
{
'info_dict': {
'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
'ext': 'mp4',
- 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
+ 'description': 'Index/Match versus VLOOKUP.',
'title': 'This is what separates the Excel masters from the wannabes',
'duration': 191.933,
},
'upload_date': '20150622',
'uploader': 'Public Sénat',
'uploader_id': 'xa9gza',
- }
+ },
+ 'skip': 'File not found.',
},
# OnionStudios embed
{
'skip_download': True,
},
},
+ {
+ # Brightcove embed with whitespace around attribute names
+ 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
+ 'info_dict': {
+ 'id': '3167554373001',
+ 'ext': 'mp4',
+ 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
+ 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
+ 'uploader_id': '1079349493',
+ 'upload_date': '20140207',
+ 'timestamp': 1391810548,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
# Another form of arte.tv embed
{
'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
# LiveLeak embed
{
'url': 'http://www.wykop.pl/link/3088787/',
- 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
+ 'md5': '7619da8c820e835bef21a1efa2a0fc71',
'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',
- }
+ },
+ 'add_ie': [LiveLeakIE.ie_key()],
+ },
+ # Another LiveLeak embed pattern (#13336)
+ {
+ 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
+ 'info_dict': {
+ 'id': '2eb_1496309988',
+ 'ext': 'mp4',
+ 'title': 'Thief robs place where everyone was armed',
+ 'description': 'md5:694d73ee79e535953cf2488562288eee',
+ 'uploader': 'brazilwtf',
+ },
+ 'add_ie': [LiveLeakIE.ie_key()],
},
# Duplicated embedded video URLs
{
'title': 'Facebook video #599637780109885',
},
},
+ # Facebook <iframe> embed, plugin video
+ {
+ 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
+ 'info_dict': {
+ 'id': '1754168231264132',
+ 'ext': 'mp4',
+ 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
+ 'uploader': 'Tariq Ramadan (official)',
+ 'timestamp': 1496758379,
+ 'upload_date': '20170606',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
# Facebook API embed
{
'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
},
'add_ie': [SenateISVPIE.ie_key()],
},
+ {
+ # Limelight embeds (1 channel embed + 4 media embeds)
+ 'url': 'http://www.sedona.com/FacilitatorTraining2017',
+ 'info_dict': {
+ 'id': 'FacilitatorTraining2017',
+ 'title': 'Facilitator Training 2017',
+ },
+ 'playlist_mincount': 5,
+ },
+ {
+ # Limelight embed (LimelightPlayerUtil.embed)
+ 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
+ 'info_dict': {
+ 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
+ 'ext': 'mp4',
+ 'title': '07448641',
+ 'timestamp': 1499890639,
+ 'upload_date': '20170712',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': ['LimelightMedia'],
+ },
+ {
+ 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
+ 'info_dict': {
+ 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
+ 'title': 'Standoff with Walnut Creek murder suspect ends',
+ 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
+ },
+ 'playlist_mincount': 4,
+ },
+ {
+ # WashingtonPost embed
+ 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
+ 'info_dict': {
+ 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
+ 'ext': 'mp4',
+ 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
+ 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
+ 'timestamp': 1455216756,
+ 'uploader': 'The Washington Post',
+ 'upload_date': '20160211',
+ },
+ 'add_ie': [WashingtonPostIE.ie_key()],
+ },
+ {
+ # Mediaset embed
+ 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
+ 'info_dict': {
+ 'id': '720642',
+ 'ext': 'mp4',
+ 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': [MediasetIE.ie_key()],
+ },
+ {
+ # JOJ.sk embeds
+ 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
+ 'info_dict': {
+ 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
+ 'title': 'Slovenskom sa prehnala vlna silných búrok',
+ },
+ 'playlist_mincount': 5,
+ 'add_ie': [JojIE.ie_key()],
+ },
+ {
+ # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
+ 'url': 'https://tvrain.ru/amp/418921/',
+ 'md5': 'cc00413936695987e8de148b67d14f1d',
+ 'info_dict': {
+ 'id': '418921',
+ 'ext': 'mp4',
+ 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
+ },
+ },
+ {
+ # vzaar embed
+ 'url': 'http://help.vzaar.com/article/165-embedding-video',
+ 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
+ 'info_dict': {
+ 'id': '8707641',
+ 'ext': 'mp4',
+ 'title': 'Building A Business Online: Principal Chairs Q & A',
+ },
+ },
+ {
+ # multiple HTML5 videos on one page
+ 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
+ 'info_dict': {
+ 'id': 'keyscenarios',
+ 'title': 'Rescue Kit 14 Free Edition - Getting started',
+ },
+ 'playlist_count': 4,
+ }
# {
# # TODO: find another test
# # http://schema.org/VideoObject
continue
entries.append({
- '_type': 'url',
+ '_type': 'url_transparent',
'url': next_url,
'title': it.find('title').text,
})
if head_response is not False:
# Check for redirect
- new_url = head_response.geturl()
+ new_url = compat_str(head_response.geturl())
if url != new_url:
self.report_following_redirect(new_url)
if force_videoid:
content_type = head_response.headers.get('Content-Type', '').lower()
m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
if m:
- format_id = m.group('format_id')
+ format_id = compat_str(m.group('format_id'))
if format_id.endswith('mpegurl'):
formats = self._extract_m3u8_formats(url, video_id, 'mp4')
elif format_id == 'f4m':
formats = self._extract_f4m_formats(url, video_id)
else:
formats = [{
- 'format_id': m.group('format_id'),
+ 'format_id': format_id,
'url': url,
'vcodec': 'none' if m.group('type') == 'audio' else None
}]
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc, video_id,
- mpd_base_url=full_response.geturl().rpartition('/')[0],
+ mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
mpd_url=url)
self._sort_formats(info_dict['formats'])
return info_dict
# And then there are the jokers who advertise that they use RTA,
# but actually don't.
AGE_LIMIT_MARKERS = [
- r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
+ r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
]
if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
age_limit = 18
video_description = self._og_search_description(webpage, default=None)
video_thumbnail = self._og_search_thumbnail(webpage, default=None)
+ info_dict.update({
+ 'title': video_title,
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'age_limit': age_limit,
+ })
+
# Look for Brightcove Legacy Studio embeds
bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
- self.to_screen('Brightcove video detected.')
entries = [{
'_type': 'url',
'url': smuggle_url(bc_url, {'Referer': url}),
}
# Look for Brightcove New Studio embeds
- bc_urls = BrightcoveNewIE._extract_urls(webpage)
+ bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
if bc_urls:
return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
+ # Look for Nexx embeds
+ nexx_urls = NexxIE._extract_urls(webpage)
+ if nexx_urls:
+ return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
+
+ # Look for Nexx iFrame embeds
+ nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
+ if nexx_embed_urls:
+ return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
+
# Look for ThePlatform embeds
tp_urls = ThePlatformIE._extract_urls(webpage)
if tp_urls:
# Look for embedded rtl.nl player
matches = re.findall(
- r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
+ r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
webpage)
if matches:
return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
if vid_me_embed_url is not None:
return self.url_result(vid_me_embed_url, 'Vidme')
- # Look for embedded YouTube player
- matches = re.findall(r'''(?x)
- (?:
- <iframe[^>]+?src=|
- data-video-url=|
- <embed[^>]+?src=|
- embedSWF\(?:\s*|
- new\s+SWFObject\(
- )
- (["\'])
- (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
- (?:embed|v|p)/.+?)
- \1''', webpage)
- if matches:
+ # Look for YouTube embeds
+ youtube_urls = YoutubeIE._extract_urls(webpage)
+ if youtube_urls:
return self.playlist_from_matches(
- matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
-
- # Look for lazyYT YouTube embed
- matches = re.findall(
- r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
- if matches:
- return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
-
- # Look for Wordpress "YouTube Video Importer" plugin
- matches = re.findall(r'''(?x)<div[^>]+
- class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
- data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
- if matches:
- return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
+ youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
matches = DailymotionIE._extract_urls(webpage)
if matches:
return self.playlist_from_matches(
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
- # Look for embedded Wistia player
- match = re.search(
- r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
- if match:
- embed_url = self._proto_relative_url(
- unescapeHTML(match.group('url')))
- return {
- '_type': 'url_transparent',
- 'url': embed_url,
- 'ie_key': 'Wistia',
- 'uploader': video_uploader,
- }
+ # Look for DailyMail embeds
+ dailymail_urls = DailyMailIE._extract_urls(webpage)
+ if dailymail_urls:
+ return self.playlist_from_matches(
+ dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
- match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
- if match:
+ # Look for embedded Wistia player
+ wistia_url = WistiaIE._extract_url(webpage)
+ if wistia_url:
return {
'_type': 'url_transparent',
- 'url': 'wistia:%s' % match.group('id'),
- 'ie_key': 'Wistia',
+ 'url': self._proto_relative_url(wistia_url),
+ 'ie_key': WistiaIE.ie_key(),
'uploader': video_uploader,
}
- match = re.search(
- r'''(?sx)
- <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
- <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
- ''', webpage)
- if match:
- return self.url_result(self._proto_relative_url(
- 'wistia:%s' % match.group('id')), 'Wistia')
-
# Look for SVT player
svt_url = SVTIE._extract_url(webpage)
if svt_url:
return self.url_result(svt_url, 'SVT')
- # Look for embedded condenast player
- matches = re.findall(
- r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
- webpage)
- if matches:
- return {
- '_type': 'playlist',
- 'entries': [{
- '_type': 'url',
- 'ie_key': 'CondeNast',
- 'url': ma,
- } for ma in matches],
- 'title': video_title,
- 'id': video_id,
- }
-
# Look for Bandcamp pages with custom domain
mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
if mobj is not None:
# Look for Ooyala videos
mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
+ re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for embedded Facebook player
- facebook_url = FacebookIE._extract_url(webpage)
- if facebook_url is not None:
- return self.url_result(facebook_url, 'Facebook')
+ facebook_urls = FacebookIE._extract_urls(webpage)
+ if facebook_urls:
+ return self.playlist_from_matches(facebook_urls, video_id, video_title)
# Look for embedded VK player
mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
if kaltura_url:
return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
- # Look for Eagle.Platform embeds
+ # Look for EaglePlatform embeds
eagleplatform_url = EaglePlatformIE._extract_url(webpage)
if eagleplatform_url:
- return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
+ return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
- # Look for ClipYou (uses Eagle.Platform) embeds
+ # Look for ClipYou (uses EaglePlatform) embeds
mobj = re.search(
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
if mobj is not None:
# Look for UDN embeds
mobj = re.search(
- r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
+ r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
if mobj is not None:
return self.url_result(
compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
return self.url_result(piksel_url, PikselIE.ie_key())
# Look for Limelight embeds
- mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
- if mobj:
- lm = {
- 'Media': 'media',
- 'Channel': 'channel',
- 'ChannelList': 'channel_list',
- }
- return self.url_result(smuggle_url('limelight:%s:%s' % (
- lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
- 'Limelight%s' % mobj.group(1), mobj.group(2))
+ limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
+ if limelight_urls:
+ return self.playlist_result(
+ limelight_urls, video_id, video_title, video_description)
- mobj = re.search(
- r'''(?sx)
- <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
- <param[^>]+
- name=(["\'])flashVars\2[^>]+
- value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
- ''', webpage)
- if mobj:
- return self.url_result(smuggle_url(
- 'limelight:media:%s' % mobj.group('id'),
- {'source_url': url}), 'LimelightMedia', mobj.group('id'))
+ # Look for Anvato embeds
+ anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
+ if anvato_urls:
+ return self.playlist_result(
+ anvato_urls, video_id, video_title, video_description)
# Look for AdobeTVVideo embeds
mobj = re.search(
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')
+ liveleak_urls = LiveLeakIE._extract_urls(webpage)
+ if liveleak_urls:
+ return self.playlist_from_matches(liveleak_urls, video_id, video_title)
# Look for 3Q SDN embeds
threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
rutube_urls = RutubeIE._extract_urls(webpage)
if rutube_urls:
return self.playlist_from_matches(
- rutube_urls, ie=RutubeIE.ie_key())
+ rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
- # Looking for http://schema.org/VideoObject
- json_ld = self._search_json_ld(
- webpage, video_id, default={}, expected_type='VideoObject')
- if json_ld.get('url'):
- info_dict.update({
- 'title': video_title or info_dict['title'],
- 'description': video_description,
- 'thumbnail': video_thumbnail,
- 'age_limit': age_limit
- })
- info_dict.update(json_ld)
- return info_dict
+ # Look for WashingtonPost embeds
+ wapo_urls = WashingtonPostIE._extract_urls(webpage)
+ if wapo_urls:
+ return self.playlist_from_matches(
+ wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
+
+ # Look for Mediaset embeds
+ mediaset_urls = MediasetIE._extract_urls(webpage)
+ if mediaset_urls:
+ return self.playlist_from_matches(
+ mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
+
+ # Look for JOJ.sk embeds
+ joj_urls = JojIE._extract_urls(webpage)
+ if joj_urls:
+ return self.playlist_from_matches(
+ joj_urls, video_id, video_title, ie=JojIE.ie_key())
+
+ # Look for megaphone.fm embeds
+ mpfn_urls = MegaphoneIE._extract_urls(webpage)
+ if mpfn_urls:
+ return self.playlist_from_matches(
+ mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
+
+ # Look for vzaar embeds
+ vzaar_urls = VzaarIE._extract_urls(webpage)
+ if vzaar_urls:
+ return self.playlist_from_matches(
+ vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
+
+ channel9_urls = Channel9IE._extract_urls(webpage)
+ if channel9_urls:
+ return self.playlist_from_matches(
+ channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
+
+ def merge_dicts(dict1, dict2):
+ merged = {}
+ for k, v in dict1.items():
+ if v is not None:
+ merged[k] = v
+ for k, v in dict2.items():
+ if v is None:
+ continue
+ if (k not in merged or
+ (isinstance(v, compat_str) and v and
+ isinstance(merged[k], compat_str) and
+ not merged[k])):
+ merged[k] = v
+ return merged
# Look for HTML5 media
entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
if entries:
- for entry in entries:
- entry.update({
+ if len(entries) == 1:
+ entries[0].update({
'id': video_id,
'title': video_title,
})
+ else:
+ for num, entry in enumerate(entries, start=1):
+ entry.update({
+ 'id': '%s-%s' % (video_id, num),
+ 'title': '%s (%d)' % (video_title, num),
+ })
+ for entry in entries:
self._sort_formats(entry['formats'])
- return self.playlist_result(entries)
+ return self.playlist_result(entries, video_id, video_title)
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
if jwplayer_data:
info = self._parse_jwplayer_data(
- jwplayer_data, video_id, require_title=False)
- if not info.get('title'):
- info['title'] = video_title
- return info
+ jwplayer_data, video_id, require_title=False, base_url=url)
+ return merge_dicts(info, info_dict)
+
+ # Video.js embed
+ mobj = re.search(
+ r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
+ webpage)
+ if mobj is not None:
+ sources = self._parse_json(
+ mobj.group(1), video_id, transform_source=js_to_json,
+ fatal=False) or []
+ if not isinstance(sources, list):
+ sources = [sources]
+ formats = []
+ for source in sources:
+ src = source.get('src')
+ if not src or not isinstance(src, compat_str):
+ continue
+ src = compat_urlparse.urljoin(url, src)
+ src_type = source.get('type')
+ if isinstance(src_type, compat_str):
+ src_type = src_type.lower()
+ ext = determine_ext(src).lower()
+ if src_type == 'video/youtube':
+ return self.url_result(src, YoutubeIE.ie_key())
+ if src_type == 'application/dash+xml' or ext == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ src, video_id, mpd_id='dash', fatal=False))
+ elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ src, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ else:
+ formats.append({
+ 'url': src,
+ 'ext': (mimetype2ext(src_type) or
+ ext if ext in KNOWN_EXTENSIONS else 'mp4'),
+ })
+ if formats:
+ self._sort_formats(formats)
+ info_dict['formats'] = formats
+ return info_dict
+
+ # Looking for http://schema.org/VideoObject
+ json_ld = self._search_json_ld(
+ webpage, video_id, default={}, expected_type='VideoObject')
+ if json_ld.get('url'):
+ return merge_dicts(json_ld, info_dict)
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
vpath = compat_urlparse.urlparse(vurl).path
vext = determine_ext(vpath)
- return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
+ return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
def filter_video(urls):
return list(filter(check_video, urls))
# be supported by youtube-dl thus this is checked the very last (see
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
embed_url = self._html_search_meta('twitter:player', webpage, default=None)
- if embed_url:
+ if embed_url and embed_url != url:
return self.url_result(embed_url)
if not found:
Rapsys Git / youtubedl / blobdiff