X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=9883cde6193063d76f65cc2af316bb947481e413;hb=7ded6545edb18bb008e8277b42a21d60fb6cd653;hp=518b4f9de1c49cd7884f8c590422e8249e476d20;hpb=ef0e4e7bc03669fbef0cb7923a21637a71993dad;p=youtube-dl
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 518b4f9de..9883cde61 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -51,7 +51,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE
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
@@ -61,6 +61,7 @@ from .jwplatform import JWPlatformIE
from .digiteka import DigitekaIE
from .instagram import InstagramIE
from .liveleak import LiveLeakIE
+from .threeqsdn import ThreeQSDNIE
class GenericIE(InfoExtractor):
@@ -237,6 +238,7 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'car-20120827-manifest',
'formats': 'mincount:9',
+ 'upload_date': '20130904',
},
'params': {
'format': 'bestvideo',
@@ -596,7 +598,11 @@ class GenericIE(InfoExtractor):
'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'],
},
@@ -729,9 +735,28 @@ class GenericIE(InfoExtractor):
'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,
+ },
+ },
+ # Wistia standard embed (async)
+ {
+ 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
+ 'info_dict': {
+ 'id': '807fafadvk',
+ 'ext': 'mp4',
+ 'title': 'Drip Brennan Dunn Workshop',
+ 'description': 'a JV Webinars video from getdrip-1',
+ 'duration': 4986.95,
+ 'upload_date': '20160518',
+ 'timestamp': 1463607249,
},
+ 'params': {
+ 'skip_download': True,
+ }
},
# Soundcloud embed
{
@@ -879,6 +904,7 @@ class GenericIE(InfoExtractor):
# 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',
@@ -893,6 +919,7 @@ class GenericIE(InfoExtractor):
# 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',
@@ -981,6 +1008,9 @@ class GenericIE(InfoExtractor):
'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
@@ -1033,6 +1063,9 @@ class GenericIE(InfoExtractor):
'title': 'SN Presents: Russell Martin, World Citizen',
'description': 'To understand why he was the Toronto Blue Jaysâ 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
@@ -1124,6 +1157,9 @@ class GenericIE(InfoExtractor):
'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
@@ -1408,7 +1444,8 @@ class GenericIE(InfoExtractor):
# 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)(.*?)', webpage, 'video title',
default='video')
@@ -1426,6 +1463,9 @@ class GenericIE(InfoExtractor):
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(
@@ -1539,6 +1579,15 @@ class GenericIE(InfoExtractor):
'id': match.group('id')
}
+ match = re.search(
+ r'''(?sx)
+ ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
+ ]+class=(["']).*?\bwistia_async_(?P[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:
@@ -1905,10 +1954,10 @@ class GenericIE(InfoExtractor):
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)
@@ -1956,13 +2005,27 @@ class GenericIE(InfoExtractor):
# 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')
+ # 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
@@ -2044,6 +2107,7 @@ class GenericIE(InfoExtractor):
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))