Basic support for TED

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-02-17 17:13:06 +01:00
parent 906417c7c5
commit 3a468f2d8b
2 changed files with 34 additions and 0 deletions

View file

@ -286,5 +286,14 @@
"title": "test chars: \"'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
}
},
{
"name": "TED",
"url": "http://www.ted.com/talks/dan_dennett_on_our_consciousness.html",
"file": "102.mp4",
"md5": "7bc087e71d16f18f9b8ab9fa62a8a031",
"info_dict": {
"title": "Dan Dennett: The illusion of consciousness"
}
}
]

View file

@ -3968,6 +3968,30 @@ class KeekIE(InfoExtractor):
}
return [info]
class TEDIE(InfoExtractor):
_VALID_URL=r'http://www.ted.com/talks/(?P<videoName>\w+)'
def _real_extract(self, url):
m=re.match(self._VALID_URL, url)
videoName=m.group('videoName')
webpage=self._download_webpage(url, 0, 'Downloading \"%s\" page' % videoName)
#If the url includes the language we get the title translated
title_RE=r'<h1><span id="altHeadline" >(?P<title>[\s\w:/\.\?=\+-]*)</span></h1>'
title=re.search(title_RE, webpage).group('title')
info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
"id":(?P<videoID>[\d]+).*?
"mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
info_match=re.search(info_RE,webpage,re.VERBOSE)
video_id=info_match.group('videoID')
mediaSlug=info_match.group('mediaSlug')
video_url='http://download.ted.com/talks/%s.mp4' % mediaSlug
info = {
'id':video_id,
'url':video_url,
'ext': 'mp4',
'title': title
}
return [info]
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
@ -4015,6 +4039,7 @@ def gen_extractors():
RBMARadioIE(),
EightTracksIE(),
KeekIE(),
TEDIE(),
GenericIE()
]