From 1b86cc41cf3f7db5893597b4b1956104a77147f7 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Mon, 24 Feb 2014 01:15:51 +0100 Subject: [PATCH] Add support for embed.ly --- youtube_dl/extractor/generic.py | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 9a2e54d149..e84c022a58 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -102,6 +102,18 @@ class GenericIE(InfoExtractor): 'title': '2cc213299525360.mov', # that's what we get }, }, + # embed.ly video + { + 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/', + 'info_dict': { + 'id': '9ODmcdjQcHQ', + 'ext': 'mp4', + }, + # No need to test YoutubeIE here + 'params': { + 'skip_download': True, + }, + }, ] def report_download_webpage(self, video_id): @@ -381,6 +393,14 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'HuffPost') + # Look for embed.ly + mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P[^"\']+)', webpage) + if mobj is not None: + return self.url_result(mobj.group('url')) + mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P[^&]+)', webpage) + if mobj is not None: + return self.url_result(compat_urllib_parse.unquote(mobj.group('url'))) + # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: