MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-24 21:56:53 +01:00
Code Issues Projects Releases Wiki Activity

[UstreamIE] [generic] Added support for Ustream embed URLs (Fixes #2694)

Browse Source
This commit is contained in:
anovicecodemonkey 2014-04-05 00:53:09 +10:30
parent 6344fa04bb
commit 5c38625259
2 changed files with 34 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
youtube_dl/extractor/generic.py
View File

@ -184,6 +184,15 @@ class GenericIE(InfoExtractor):
'description': 'md5:ddb2a40ecd6b6a147e400e535874947b', 'description': 'md5:ddb2a40ecd6b6a147e400e535874947b',
} }
}, },
# Embeded Ustream video
{
'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
'md5': '27b99cdb639c9b12a79bca876a073417',
'info_dict': {
'uploader': 'AU SPA: The NSA and Privacy',
'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
}
},
# nowvideo embed hidden behind percent encoding # nowvideo embed hidden behind percent encoding
{ {
'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/', 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
@ -556,6 +565,12 @@ def _real_extract(self, url):
if mobj is not None: if mobj is not None:
return self.url_result(mobj.group('url'), 'TED') return self.url_result(mobj.group('url'), 'TED')
# Look for embedded Ustream videos
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Ustream')
# Look for embedded arte.tv player # Look for embedded arte.tv player
mobj = re.search( mobj = re.search(
r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"', r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',

21
youtube_dl/extractor/ustream.py
View File

@ -11,9 +11,9 @@
class UstreamIE(InfoExtractor): class UstreamIE(InfoExtractor):
_VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)' _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed)/(?P<videoID>\d+)'
IE_NAME = 'ustream' IE_NAME = 'ustream'
_TEST = { _TESTS = [{
'url': 'http://www.ustream.tv/recorded/20274954', 'url': 'http://www.ustream.tv/recorded/20274954',
'file': '20274954.flv', 'file': '20274954.flv',
'md5': '088f151799e8f572f84eb62f17d73e5c', 'md5': '088f151799e8f572f84eb62f17d73e5c',
@ -21,10 +21,27 @@ class UstreamIE(InfoExtractor):
"uploader": "Young Americans for Liberty", "uploader": "Young Americans for Liberty",
"title": "Young Americans for Liberty February 7, 2012 2:28 AM", "title": "Young Americans for Liberty February 7, 2012 2:28 AM",
}, },
},
{
'url': 'http://www.ustream.tv/embed/17357891',
'file': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman-45734260.flv',
'md5': '27b99cdb639c9b12a79bca876a073417',
'info_dict': {
"uploader": "AU SPA: The NSA and Privacy",
"title": "NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman"
},
} }
]
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
if m.group('type') == 'embed':
video_id = m.group('videoID')
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')
video_id = m.group('videoID') video_id = m.group('videoID')
video_url = 'http://tcdn.ustream.tv/video/%s' % video_id video_url = 'http://tcdn.ustream.tv/video/%s' % video_id