diff options
| -rw-r--r-- | test/tests.json | 18 | ||||
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 32 |
2 files changed, 46 insertions, 4 deletions
diff --git a/test/tests.json b/test/tests.json index 5c46af2c8..a3c31ae51 100644 --- a/test/tests.json +++ b/test/tests.json @@ -286,5 +286,23 @@ "title": "test chars: \"'/\\รค<>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" + } + }, + { + "name": "MySpass", + "url": "http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/", + "file": "11741.mp4", + "md5": "0b49f4844a068f8b33f4b7c88405862b", + "info_dict": { + "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2" + } } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 57d5e9d36..fe9bd97d0 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3968,13 +3968,36 @@ class KeekIE(InfoExtractor): } return [info] -class MyspassIE(InfoExtractor): +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] + +class MySpassIE(InfoExtractor): _VALID_URL = r'http://www.myspass.de/.*' - IE_NAME = u'myspass' def _real_extract(self, url): META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' - + # video id is the last path element of the URL # usually there is a trailing slash, so also try the second but last url_path = compat_urllib_parse_urlparse(url).path @@ -4072,7 +4095,8 @@ def gen_extractors(): RBMARadioIE(), EightTracksIE(), KeekIE(), - MyspassIE(), + TEDIE(), + MySpassIE(), GenericIE() ] |