X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9815bb0a551468e4939cacfffbc2d5cb8dd12431..43dfe443c76727639f9b6037664d62cdca08fe1b:/youtube_dl/extractor/ted.py diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index ccad1c7..4c11f7a 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -14,6 +14,15 @@ class TEDIE(InfoExtractor): (/lang/(.*?))? # The url may contain the language /(?P\w+) # Here goes the name and then ".html" ''' + _TEST = { + u'url': u'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html', + u'file': u'102.mp4', + u'md5': u'2d76ee1576672e0bd8f187513267adf6', + u'info_dict': { + u"description": u"md5:c6fa72e6eedbd938c9caf6b2702f5922", + u"title": u"Dan Dennett: The illusion of consciousness" + } + } @classmethod def suitable(cls, url): @@ -58,7 +67,7 @@ class TEDIE(InfoExtractor): webpage = self._download_webpage(url, video_id, 'Downloading \"%s\" page' % video_name) self.report_extraction(video_name) # If the url includes the language we get the title translated - title = self._html_search_regex(r'(?P.*)</span>', + title = self._html_search_regex(r'<span .*?id="altHeadline".+?>(?P<title>.*)</span>', webpage, 'title') json_data = self._search_regex(r'<script.*?>var talkDetails = ({.*?})</script>', webpage, 'json data')