From 19dab5e6cc9e0a7a726af8bb67ca30801c2107b0 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Mon, 30 Dec 2013 06:15:02 +0100 Subject: [PATCH] [GenericIE] Outsource embedded blip.tv player video id extraction to BlipTVIE and fix minor errors in RegEx --- youtube_dl/extractor/generic.py | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 7a14c98f9b..f1b152f623 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -271,16 +271,12 @@ def _real_extract(self, url): } # Look for embedded blip.tv player - mobj = re.search(r']*https?://api.blip.tv/\w+/redirect/\w+/(\d+)', webpage) + mobj = re.search(r']*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) if mobj: - return self.url_result('http://blip.tv/seo/-'+mobj.group(1), 'BlipTV') - mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*https?://(?:\w+\.)?blip.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', webpage) + return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') + mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage) if mobj: - player_url = 'http://blip.tv/play/%s.x?p=1' % mobj.group(1) - player_page = self._download_webpage(player_url, mobj.group(1)) - blip_video_id = self._search_regex(r'data-episode-id="(\d+)', player_page, u'blip_video_id', fatal=False) - if blip_video_id: - return self.url_result('http://blip.tv/seo/-'+blip_video_id, 'BlipTV') + return self.url_result(mobj.group(1), 'BlipTV') # Look for Bandcamp pages with custom domain mobj = re.search(r']*?content="(.*?bandcamp\.com.*?)"', webpage)