from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
- compat_urllib_parse,
+ compat_urllib_parse_unquote,
+ compat_urllib_request,
compat_urlparse,
compat_xml_parse_error,
)
unsmuggle_url,
UnsupportedError,
url_basename,
+ xpath_text,
)
from .brightcove import BrightcoveIE
+from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
+from .tvc import TVCIE
+from .sportbox import SportBoxEmbedIE
from .smotri import SmotriIE
+from .myvi import MyviIE
from .condenast import CondeNastIE
+from .udn import UDNEmbedIE
+from .senateisvp import SenateISVPIE
+from .bliptv import BlipTVIE
+from .svt import SVTIE
+from .pornhub import PornHubIE
+from .xhamster import XHamsterEmbedIE
+from .vimeo import VimeoIE
+from .dailymotion import DailymotionCloudIE
+from .onionstudios import OnionStudiosIE
+from .snagfilms import SnagFilmsEmbedIE
class GenericIE(InfoExtractor):
_VALID_URL = r'.*'
IE_NAME = 'generic'
_TESTS = [
+ # Direct link to a video
+ {
+ 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
+ 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
+ 'info_dict': {
+ 'id': 'trailer',
+ 'ext': 'mp4',
+ 'title': 'trailer',
+ 'upload_date': '20100513',
+ }
+ },
+ # Direct link to media delivered compressed (until Accept-Encoding is *)
+ {
+ 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
+ 'md5': '128c42e68b13950268b648275386fc74',
+ 'info_dict': {
+ 'id': 'FictionJunction-Parallel_Hearts',
+ 'ext': 'flac',
+ 'title': 'FictionJunction-Parallel_Hearts',
+ 'upload_date': '20140522',
+ },
+ 'expected_warnings': [
+ 'URL could be a direct video link, returning it as such.'
+ ]
+ },
+ # Direct download with broken HEAD
+ {
+ 'url': 'http://ai-radio.org:8000/radio.opus',
+ 'info_dict': {
+ 'id': 'radio',
+ 'ext': 'opus',
+ 'title': 'radio',
+ },
+ 'params': {
+ 'skip_download': True, # infinite live stream
+ },
+ 'expected_warnings': [
+ r'501.*Not Implemented'
+ ],
+ },
+ # Direct link with incorrect MIME type
+ {
+ 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+ 'md5': '4ccbebe5f36706d85221f204d7eb5913',
+ 'info_dict': {
+ 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+ 'id': '5_Lennart_Poettering_-_Systemd',
+ 'ext': 'webm',
+ 'title': '5_Lennart_Poettering_-_Systemd',
+ 'upload_date': '20141120',
+ },
+ 'expected_warnings': [
+ 'URL could be a direct video link, returning it as such.'
+ ]
+ },
+ # RSS feed
+ {
+ 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+ 'info_dict': {
+ 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+ 'title': 'Zero Punctuation',
+ 'description': 're:.*groundbreaking video review series.*'
+ },
+ 'playlist_mincount': 11,
+ },
+ # RSS feed with enclosure
+ {
+ 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
+ 'info_dict': {
+ 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+ 'ext': 'm4v',
+ 'upload_date': '20150228',
+ 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+ }
+ },
+ # google redirect
+ {
+ 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
+ 'info_dict': {
+ 'id': 'cmQHVoWB5FY',
+ 'ext': 'mp4',
+ 'upload_date': '20130224',
+ 'uploader_id': 'TheVerge',
+ 'description': 're:^Chris Ziegler takes a look at the\.*',
+ 'uploader': 'The Verge',
+ 'title': 'First Firefox OS phones side-by-side',
+ },
+ 'params': {
+ 'skip_download': False,
+ }
+ },
{
'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
'skip_download': True, # m3u8 download
},
},
- # Direct link to a video
- {
- 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
- 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
- 'info_dict': {
- 'id': 'trailer',
- 'ext': 'mp4',
- 'title': 'trailer',
- 'upload_date': '20100513',
- }
- },
# ooyala video
{
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
},
'add_ie': ['Ooyala'],
},
- # google redirect
- {
- 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
- 'info_dict': {
- 'id': 'cmQHVoWB5FY',
- 'ext': 'mp4',
- 'upload_date': '20130224',
- 'uploader_id': 'TheVerge',
- 'description': 're:^Chris Ziegler takes a look at the\.*',
- 'uploader': 'The Verge',
- 'title': 'First Firefox OS phones side-by-side',
- },
- 'params': {
- 'skip_download': False,
- }
- },
# embed.ly video
{
'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
'skip_download': True,
},
},
+ # TVC embed
+ {
+ 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
+ 'info_dict': {
+ 'id': '55304',
+ 'ext': 'mp4',
+ 'title': 'Дошкольное воспитание',
+ },
+ },
+ # SportBox embed
+ {
+ 'url': 'http://www.vestifinance.ru/articles/25753',
+ 'info_dict': {
+ 'id': '25753',
+ 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
+ },
+ 'playlist': [{
+ 'info_dict': {
+ 'id': '370908',
+ 'title': 'Госзаказ. День 3',
+ 'ext': 'mp4',
+ }
+ }, {
+ 'info_dict': {
+ 'id': '370905',
+ 'title': 'Госзаказ. День 2',
+ 'ext': 'mp4',
+ }
+ }, {
+ 'info_dict': {
+ 'id': '370902',
+ 'title': 'Госзаказ. День 1',
+ 'ext': 'mp4',
+ }
+ }],
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ },
+ # Myvi.ru embed
+ {
+ 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
+ 'info_dict': {
+ 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
+ 'ext': 'mp4',
+ 'title': 'Ужастики, русский трейлер (2015)',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 153,
+ }
+ },
+ # XHamster embed
+ {
+ 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
+ 'info_dict': {
+ 'id': 'showthread',
+ 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
+ },
+ 'playlist_mincount': 7,
+ },
# Embedded TED video
{
'url': 'http://en.support.wordpress.com/videos/ted-talks/',
'skip_download': 'Requires rtmpdump'
}
},
+ # francetv embed
+ {
+ 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
+ 'info_dict': {
+ 'id': 'EV_30231',
+ 'ext': 'mp4',
+ 'title': 'Alcaline, le concert avec Calogero',
+ 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
+ 'upload_date': '20150226',
+ 'timestamp': 1424989860,
+ 'duration': 5400,
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ },
+ 'expected_warnings': [
+ 'Forbidden'
+ ]
+ },
# Condé Nast embed
{
'url': 'http://www.wired.com/2014/04/honda-asimo/',
'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
}
},
- # RSS feed
- {
- 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
- 'info_dict': {
- 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
- 'title': 'Zero Punctuation',
- 'description': 're:.*groundbreaking video review series.*'
- },
- 'playlist_mincount': 11,
- },
# Multiple brightcove videos
# https://github.com/rg3/youtube-dl/issues/2283
{
'uploader': 'thoughtworks.wistia.com',
},
},
- # Direct download with broken HEAD
- {
- 'url': 'http://ai-radio.org:8000/radio.opus',
- 'info_dict': {
- 'id': 'radio',
- 'ext': 'opus',
- 'title': 'radio',
- },
- 'params': {
- 'skip_download': True, # infinite live stream
- },
- 'expected_warnings': [
- r'501.*Not Implemented'
- ],
- },
# Soundcloud embed
{
'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
},
'playlist_mincount': 2,
},
- # Direct link with incorrect MIME type
- {
- 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
- 'md5': '4ccbebe5f36706d85221f204d7eb5913',
- 'info_dict': {
- 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
- 'id': '5_Lennart_Poettering_-_Systemd',
- 'ext': 'webm',
- 'title': '5_Lennart_Poettering_-_Systemd',
- 'upload_date': '20141120',
- },
- 'expected_warnings': [
- 'URL could be a direct video link, returning it as such.'
- ]
- },
# Cinchcast embed
{
'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
},
'add_ie': ['Viddler'],
},
+ # Libsyn embed
+ {
+ 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+ 'info_dict': {
+ 'id': '3377616',
+ 'ext': 'mp3',
+ 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+ 'description': 'md5:601cb790edd05908957dae8aaa866465',
+ 'upload_date': '20150220',
+ },
+ },
# jwplayer YouTube
{
'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
'title': 'John Carlson Postgame 2/25/15',
},
},
+ # Kaltura embed (different embed code)
+ {
+ 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
+ 'info_dict': {
+ 'id': '1_a52wc67y',
+ 'ext': 'flv',
+ 'upload_date': '20150127',
+ 'uploader_id': 'PremierMedia',
+ 'timestamp': int,
+ 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
+ },
+ },
+ # Eagle.Platform embed (generic URL)
+ {
+ 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
+ 'info_dict': {
+ 'id': '227304',
+ 'ext': 'mp4',
+ 'title': 'Навальный вышел на свободу',
+ 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 87,
+ 'view_count': int,
+ 'age_limit': 0,
+ },
+ },
+ # ClipYou (Eagle.Platform) embed (custom URL)
+ {
+ 'url': 'http://muz-tv.ru/play/7129/',
+ 'info_dict': {
+ 'id': '12820',
+ 'ext': 'mp4',
+ 'title': "'O Sole Mio",
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 216,
+ 'view_count': int,
+ },
+ },
+ # Pladform embed
+ {
+ 'url': 'http://muz-tv.ru/kinozal/view/7400/',
+ 'info_dict': {
+ 'id': '100183293',
+ 'ext': 'mp4',
+ 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
+ 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 694,
+ 'age_limit': 0,
+ },
+ },
+ # Playwire embed
+ {
+ 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
+ 'info_dict': {
+ 'id': '3519514',
+ 'ext': 'mp4',
+ 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
+ 'thumbnail': 're:^https?://.*\.png$',
+ 'duration': 45.115,
+ },
+ },
+ # 5min embed
+ {
+ 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
+ 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
+ 'info_dict': {
+ 'id': '518726732',
+ 'ext': 'mp4',
+ 'title': 'Facebook Creates "On This Day" | Crunch Report',
+ },
+ },
+ # SVT embed
+ {
+ 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
+ 'info_dict': {
+ 'id': '2900353',
+ 'ext': 'flv',
+ 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
+ 'duration': 27,
+ 'age_limit': 0,
+ },
+ },
+ # Crooks and Liars embed
+ {
+ 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
+ 'info_dict': {
+ 'id': '8RUoRhRi',
+ 'ext': 'mp4',
+ 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
+ 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
+ 'timestamp': 1428207000,
+ 'upload_date': '20150405',
+ 'uploader': 'Heather',
+ },
+ },
+ # Crooks and Liars external embed
+ {
+ 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
+ 'info_dict': {
+ 'id': 'MTE3MjUtMzQ2MzA',
+ 'ext': 'mp4',
+ 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
+ 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
+ 'timestamp': 1265032391,
+ 'upload_date': '20100201',
+ 'uploader': 'Heather',
+ },
+ },
+ # NBC Sports vplayer embed
+ {
+ 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
+ 'info_dict': {
+ 'id': 'ln7x1qSThw4k',
+ 'ext': 'flv',
+ 'title': "PFT Live: New leader in the 'new-look' defense",
+ 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+ },
+ },
+ # UDN embed
+ {
+ 'url': 'http://www.udn.com/news/story/7314/822787',
+ 'md5': 'fd2060e988c326991037b9aff9df21a6',
+ 'info_dict': {
+ 'id': '300346',
+ 'ext': 'mp4',
+ 'title': '中一中男師變性 全校師生力挺',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ }
+ },
+ # Ooyala embed
+ {
+ 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
+ 'info_dict': {
+ 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
+ 'ext': 'mp4',
+ 'description': 'VIDEO: Index/Match versus VLOOKUP.',
+ 'title': 'This is what separates the Excel masters from the wannabes',
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
+ },
+ # Contains a SMIL manifest
+ {
+ 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
+ 'info_dict': {
+ 'id': 'file',
+ 'ext': 'flv',
+ 'title': '+ Football: Lottery Champions League Europe',
+ 'uploader': 'www.telewebion.com',
+ },
+ 'params': {
+ # rtmpe downloads
+ 'skip_download': True,
+ }
+ },
+ # Brightcove URL in single quotes
+ {
+ 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
+ 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
+ 'info_dict': {
+ 'id': '4255764656001',
+ 'ext': 'mp4',
+ 'title': 'SN Presents: Russell Martin, World Citizen',
+ 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
+ 'uploader': 'Rogers Sportsnet',
+ },
+ },
+ # Dailymotion Cloud video
+ {
+ 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
+ 'md5': '49444254273501a64675a7e68c502681',
+ 'info_dict': {
+ 'id': '5585de919473990de4bee11b',
+ 'ext': 'mp4',
+ 'title': 'Le débat',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ }
+ },
+ # OnionStudios embed
+ {
+ 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
+ 'info_dict': {
+ 'id': '2855',
+ 'ext': 'mp4',
+ 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ 'uploader': 'ClickHole',
+ 'uploader_id': 'clickhole',
+ }
+ },
+ # SnagFilms embed
+ {
+ 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
+ 'info_dict': {
+ 'id': '74849a00-85a9-11e1-9660-123139220831',
+ 'ext': 'mp4',
+ 'title': '#whilewewatch',
+ }
+ },
+ # AdobeTVVideo embed
+ {
+ 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
+ 'md5': '43662b577c018ad707a63766462b1e87',
+ 'info_dict': {
+ 'id': '2456',
+ 'ext': 'mp4',
+ 'title': 'New experience with Acrobat DC',
+ 'description': 'New experience with Acrobat DC',
+ 'duration': 248.667,
+ },
+ }
]
def report_following_redirect(self, new_url):
playlist_desc_el = doc.find('./channel/description')
playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
- entries = [{
- '_type': 'url',
- 'url': e.find('link').text,
- 'title': e.find('title').text,
- } for e in doc.findall('./channel/item')]
+ entries = []
+ for it in doc.findall('./channel/item'):
+ next_url = xpath_text(it, 'link', fatal=False)
+ if not next_url:
+ enclosure_nodes = it.findall('./enclosure')
+ for e in enclosure_nodes:
+ next_url = e.attrib.get('url')
+ if next_url:
+ break
+
+ if not next_url:
+ continue
+
+ entries.append({
+ '_type': 'url',
+ 'url': next_url,
+ 'title': it.find('title').text,
+ })
return {
'_type': 'playlist',
force_videoid = smuggled_data['force_videoid']
video_id = force_videoid
else:
- video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
+ video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
self.to_screen('%s: Requesting header' % video_id)
full_response = None
if head_response is False:
- full_response = self._request_webpage(url, video_id)
+ request = compat_urllib_request.Request(url)
+ request.add_header('Accept-Encoding', '*')
+ full_response = self._request_webpage(request, video_id)
head_response = full_response
# Check for direct link to a video
head_response.headers.get('Last-Modified'))
return {
'id': video_id,
- 'title': os.path.splitext(url_basename(url))[0],
+ 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
'direct': True,
'formats': [{
'format_id': m.group('format_id'),
}
if not self._downloader.params.get('test', False) and not is_intentional:
- self._downloader.report_warning('Falling back on generic information extractor.')
+ force = self._downloader.params.get('force_generic_extractor', False)
+ self._downloader.report_warning(
+ '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
if not full_response:
- full_response = self._request_webpage(url, video_id)
+ request = compat_urllib_request.Request(url)
+ # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
+ # making it impossible to download only chunk of the file (yet we need only 512kB to
+ # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
+ # that will always result in downloading the whole file that is not desirable.
+ # Therefore for extraction pass we have to override Accept-Encoding to any in order
+ # to accept raw bytes and being able to download only a chunk.
+ # It may probably better to solve this by checking Content-Type for application/octet-stream
+ # after HEAD request finishes, but not sure if we can rely on this.
+ request.add_header('Accept-Encoding', '*')
+ full_response = self._request_webpage(request, video_id)
# Maybe it's a direct link to a video?
# Be careful not to download the whole thing!
head_response.headers.get('Last-Modified'))
return {
'id': video_id,
- 'title': os.path.splitext(url_basename(url))[0],
+ 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
'direct': True,
'url': url,
'upload_date': upload_date,
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/rg3/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way
- webpage = compat_urllib_parse.unquote(webpage)
+ webpage = compat_urllib_parse_unquote(webpage)
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Look for embedded rtl.nl player
matches = re.findall(
- r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
+ r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
webpage)
if matches:
return _playlist_from_matches(matches, ie='RtlNl')
- # Look for embedded (iframe) Vimeo player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
- if mobj:
- player_url = unescapeHTML(mobj.group('url'))
- surl = smuggle_url(player_url, {'Referer': url})
- return self.url_result(surl)
- # Look for embedded (swf embed) Vimeo player
- mobj = re.search(
- r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
- if mobj:
- return self.url_result(mobj.group(1))
+ vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+ if vimeo_url is not None:
+ return self.url_result(vimeo_url)
+
+ vid_me_embed_url = self._search_regex(
+ r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
+ webpage, 'vid.me embed', default=None)
+ 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)
}
# Look for embedded blip.tv player
- mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
- if mobj:
- return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
- mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
- if mobj:
- return self.url_result(mobj.group(1), 'BlipTV')
+ bliptv_url = BlipTVIE._extract_url(webpage)
+ if bliptv_url:
+ return self.url_result(bliptv_url, 'BlipTV')
+
+ # 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(
if mobj is not None:
return self.url_result(mobj.group('url'))
+ # Look for NYTimes player
+ mobj = re.search(
+ r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for Libsyn player
+ mobj = re.search(
+ r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
# 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'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
+ 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 OoyalaIE._build_url_result(mobj.group('ec'))
return self.url_result(mobj.group('url'))
mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
if mobj is not None:
- return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
+ return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
# Look for funnyordie embed
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
if rutv_url:
return self.url_result(rutv_url, 'RUTV')
+ # Look for embedded TVC player
+ tvc_url = TVCIE._extract_url(webpage)
+ if tvc_url:
+ return self.url_result(tvc_url, 'TVC')
+
+ # Look for embedded SportBox player
+ sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
+ if sportbox_urls:
+ return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
+
+ # Look for embedded PornHub player
+ pornhub_url = PornHubIE._extract_url(webpage)
+ if pornhub_url:
+ return self.url_result(pornhub_url, 'PornHub')
+
+ # Look for embedded XHamster player
+ xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
+ if xhamster_urls:
+ return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
+
+ # Look for embedded Tvigle player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Tvigle')
+
# Look for embedded TED player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'ArteTVEmbed')
+ # Look for embedded francetv player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
# Look for embedded smotri.com player
smotri_url = SmotriIE._extract_url(webpage)
if smotri_url:
return self.url_result(smotri_url, 'Smotri')
+ # Look for embedded Myvi.ru player
+ myvi_url = MyviIE._extract_url(webpage)
+ if myvi_url:
+ return self.url_result(myvi_url)
+
# Look for embeded soundcloud player
mobj = re.search(
r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
webpage)
+ if not mobj:
+ mobj = re.search(
+ r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+ webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'MLB')
return self.url_result(mobj.group('url'), 'Zapiks')
# Look for Kaltura embeds
- mobj = re.search(
- r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
+ mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
+ re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
if mobj is not None:
return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
+ # Look for Eagle.Platform embeds
+ mobj = re.search(
+ r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'EaglePlatform')
+
+ # Look for ClipYou (uses Eagle.Platform) 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:
+ return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
+
+ # Look for Pladform embeds
+ mobj = re.search(
+ r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Pladform')
+
+ # Look for Playwire embeds
+ mobj = re.search(
+ r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for 5min embeds
+ mobj = re.search(
+ r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
+ if mobj is not None:
+ return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
+
+ # Look for Crooks and Liars embeds
+ mobj = re.search(
+ r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for NBC Sports VPlayer embeds
+ nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
+ if nbc_sports_url:
+ return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
+
+ # Look for UDN embeds
+ mobj = re.search(
+ r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
+ if mobj is not None:
+ return self.url_result(
+ compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
+
+ # Look for Senate ISVP iframe
+ senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+ if senate_isvp_url:
+ return self.url_result(senate_isvp_url, 'SenateISVP')
+
+ # Look for Dailymotion Cloud videos
+ dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+ if dmcloud_url:
+ return self.url_result(dmcloud_url, 'DailymotionCloud')
+
+ # Look for OnionStudios embeds
+ onionstudios_url = OnionStudiosIE._extract_url(webpage)
+ if onionstudios_url:
+ return self.url_result(onionstudios_url)
+
+ # Look for SnagFilms embeds
+ snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
+ if snagfilms_url:
+ return self.url_result(snagfilms_url)
+
+ # Look for AdobeTVVideo embeds
+ mobj = re.search(
+ r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
+ webpage)
+ if mobj is not None:
+ return self.url_result(
+ self._proto_relative_url(unescapeHTML(mobj.group(1))),
+ 'AdobeTVVideo')
+
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
# HTML5 video
found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
if not found:
+ REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
found = re.search(
r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
- r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+ r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
webpage)
+ if not found:
+ # Look also in Refresh HTTP header
+ refresh_header = head_response.headers.get('Refresh')
+ if refresh_header:
+ found = re.search(REDIRECT_REGEX, refresh_header)
if found:
- new_url = found.group(1)
+ new_url = compat_urlparse.urljoin(url, found.group(1))
self.report_following_redirect(new_url)
return {
'_type': 'url',
entries = []
for video_url in found:
video_url = compat_urlparse.urljoin(url, video_url)
- video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
+ video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
# Sometimes, jwplayer extraction will result in a YouTube URL
if YoutubeIE.suitable(video_url):
# here's a fun little line of code for you:
video_id = os.path.splitext(video_id)[0]
- entries.append({
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'title': video_title,
- 'age_limit': age_limit,
- })
+ if determine_ext(video_url) == 'smil':
+ entries.append({
+ 'id': video_id,
+ 'formats': self._extract_smil_formats(video_url, video_id),
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'age_limit': age_limit,
+ })
+ else:
+ entries.append({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'age_limit': age_limit,
+ })
if len(entries) == 1:
return entries[0]
Rapsys Git / youtubedl / blobdiff