from .vimeo import VimeoIE
from .dailymotion import DailymotionCloudIE
from .onionstudios import OnionStudiosIE
-from .snagfilms import SnagFilmsEmbedIE
+from .viewlift import ViewLiftEmbedIE
from .screenwavemedia import ScreenwaveMediaIE
from .mtv import MTVServicesEmbeddedIE
from .pladform import PladformIE
from .googledrive import GoogleDriveIE
from .jwplatform import JWPlatformIE
from .digiteka import DigitekaIE
+from .instagram import InstagramIE
+from .liveleak import LiveLeakIE
+from .threeqsdn import ThreeQSDNIE
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
'ext': 'mp4',
'title': 'car-20120827-manifest',
'formats': 'mincount:9',
+ 'upload_date': '20130904',
},
'params': {
'format': 'bestvideo',
'skip_download': True,
}
},
+ # m3u8 served with Content-Type: text/plain
+ {
+ 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
+ 'info_dict': {
+ 'id': 'index',
+ 'ext': 'mp4',
+ 'title': 'index',
+ 'upload_date': '20140720',
+ 'formats': 'mincount:11',
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
+ },
# 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',
'skip_download': True,
},
},
- # multiple ooyala embeds on SBN network websites
- {
- 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
- 'info_dict': {
- 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
- 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
- },
- 'playlist_mincount': 3,
- 'params': {
- 'skip_download': True,
- },
- 'add_ie': ['Ooyala'],
- },
# embed.ly video
{
'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
'id': 'k2mm4bCdJ6CQ2i7c8o2',
'ext': 'mp4',
'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
+ 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
'uploader': 'Spi0n',
+ 'uploader_id': 'xgditw',
+ 'upload_date': '20140425',
+ 'timestamp': 1398441542,
},
'add_ie': ['Dailymotion'],
},
'id': 'uxjb0lwrcz',
'ext': 'mp4',
'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
+ 'description': 'a Martin Fowler video from ThoughtWorks',
'duration': 1715.0,
'uploader': 'thoughtworks.wistia.com',
+ 'upload_date': '20140603',
+ 'timestamp': 1401832161,
},
},
# Soundcloud embed
# Eagle.Platform 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
'info_dict': {
'id': '227304',
'ext': 'mp4',
# ClipYou (Eagle.Platform) 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
'info_dict': {
'id': '12820',
'ext': 'mp4',
'ext': 'flv',
'title': "PFT Live: New leader in the 'new-look' defense",
'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+ 'uploader': 'NBCU-SPORTS',
+ 'upload_date': '20140107',
+ 'timestamp': 1389118457,
},
},
# UDN embed
'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',
+ 'uploader_id': '1704050871',
+ 'upload_date': '20150525',
+ 'timestamp': 1432570283,
},
},
# Dailymotion Cloud video
# m3u8 downloads
'skip_download': True,
}
- }
+ },
+ # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
+ # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
+ {
+ 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
+ 'info_dict': {
+ 'id': '4785848093001',
+ 'ext': 'mp4',
+ 'title': 'The Cardinal Pell Interview',
+ 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
+ 'uploader': 'GlobeCast Australia - GlobeStream',
+ 'uploader_id': '2733773828001',
+ 'upload_date': '20160304',
+ 'timestamp': 1457083087,
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ },
+ },
+ # Another form of arte.tv embed
+ {
+ 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
+ 'md5': '850bfe45417ddf221288c88a0cffe2e2',
+ 'info_dict': {
+ 'id': '030273-562_PLUS7-F',
+ 'ext': 'mp4',
+ 'title': 'ARTE Reportage - Nulle part, en France',
+ 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
+ '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):
'url': url,
'vcodec': 'none' if m.group('type') == 'audio' else None
}]
- info_dict.update({
- 'direct': True,
- 'formats': formats,
- })
+ info_dict['direct'] = True
+ self._sort_formats(formats)
+ info_dict['formats'] = formats
return info_dict
if not self._downloader.params.get('test', False) and not is_intentional:
request.add_header('Accept-Encoding', '*')
full_response = self._request_webpage(request, video_id)
+ first_bytes = full_response.read(512)
+
+ # Is it an M3U playlist?
+ if first_bytes.startswith(b'#EXTM3U'):
+ info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
+ self._sort_formats(info_dict['formats'])
+ return info_dict
+
# Maybe it's a direct link to a video?
# Be careful not to download the whole thing!
- first_bytes = full_response.read(512)
if not is_html(first_bytes):
self._downloader.report_warning(
'URL could be a direct video link, returning it as such.')
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
- return self._parse_smil(doc, url, video_id)
+ smil = self._parse_smil(doc, url, video_id)
+ self._sort_formats(smil['formats'])
+ return smil
elif doc.tag == '{http://xspf.org/ns/0/}playlist':
return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc, video_id, mpd_base_url=url.rpartition('/')[0])
+ self._sort_formats(info_dict['formats'])
return info_dict
elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
+ self._sort_formats(info_dict['formats'])
return info_dict
except compat_xml_parse_error:
pass
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
- video_title = self._html_search_regex(
+ video_title = self._og_search_title(
+ webpage, default=None) or self._html_search_regex(
r'(?s)<title>(.*?)</title>', webpage, 'video title',
default='video')
video_uploader = self._search_regex(
r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
+ video_description = self._og_search_description(webpage, default=None)
+ video_thumbnail = self._og_search_thumbnail(webpage, default=None)
+
# Helper method
def _playlist_from_matches(matches, getter=None, ie=None):
urlrs = orderedSet(
'id': match.group('id')
}
+ 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:
# Look for embedded arte.tv player
mobj = re.search(
- r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
+ r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'ArteTVEmbed')
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 ViewLift embeds
+ viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
+ if viewlift_url:
+ return self.url_result(viewlift_url)
# Look for JWPlatform embeds
jwplatform_url = JWPlatformIE._extract_url(webpage)
self._proto_relative_url(unescapeHTML(mobj.group(1))),
'AdobeTVVideo')
+ # Look for Vine embeds
+ mobj = re.search(
+ r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
+ webpage)
+ if mobj is not None:
+ return self.url_result(
+ self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
+
+ # Look for Instagram embeds
+ instagram_embed_url = InstagramIE._extract_embed_url(webpage)
+ if instagram_embed_url is not None:
+ 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')
+
+ # Look for 3Q SDN embeds
+ threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
+ if threeqsdn_url:
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': ThreeQSDNIE.ie_key(),
+ 'url': self._proto_relative_url(threeqsdn_url),
+ 'title': video_title,
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'uploader': video_uploader,
+ }
+
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
entries = []
for video_url in found:
+ video_url = unescapeHTML(video_url)
video_url = video_url.replace('\\/', '/')
video_url = compat_urlparse.urljoin(url, video_url)
video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
else:
entry_info_dict['url'] = video_url
+ if entry_info_dict.get('formats'):
+ self._sort_formats(entry_info_dict['formats'])
+
entries.append(entry_info_dict)
if len(entries) == 1:
projects / youtube-dl / blobdiff