diff options
| author | rzhxeo <rzhxeot7z81b4700@mailcatch.com> | 2013-12-30 06:15:02 +0100 |
|---|---|---|
| committer | rzhxeo <rzhxeot7z81b4700@mailcatch.com> | 2013-12-30 06:15:02 +0100 |
| commit | 19dab5e6cc9e0a7a726af8bb67ca30801c2107b0 (patch) | |
| tree | 1c417757bd6d1e3626da12e5bc952d61f0c808be /youtube_dl/extractor/generic.py | |
| parent | c0f9969b9e297a2c4ceb87017081792e13f4cdc6 (diff) | |
| download | youtube-dl-19dab5e6cc9e0a7a726af8bb67ca30801c2107b0.tar.xz | |
[GenericIE] Outsource embedded blip.tv player video id extraction to BlipTVIE and fix minor errors in RegEx
Diffstat (limited to 'youtube_dl/extractor/generic.py')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 12 |
1 files changed, 4 insertions, 8 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 7a14c98f9..f1b152f62 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -271,16 +271,12 @@ class GenericIE(InfoExtractor): } # Look for embedded blip.tv player - mobj = re.search(r'<meta\s[^>]*https?://api.blip.tv/\w+/redirect/\w+/(\d+)', webpage) + mobj = re.search(r'<meta\s[^>]*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'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage) |