diff options
author | dst <dstftw@gmail.com> | 2014-01-30 04:26:46 +0700 |
---|---|---|
committer | dst <dstftw@gmail.com> | 2014-01-30 04:26:46 +0700 |
commit | c3f51436bf3b36572b403d3240c947e6961bd25f (patch) | |
tree | 41160e9bba661da70ed51b8ad3f5942b0729abfd | |
parent | 0c708f11cbde6339adbf9a8477f673e25e68e920 (diff) |
Improve some regexes for embedded players
-rw-r--r-- | youtube_dl/extractor/generic.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 48de379b7..e0d51996d 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -254,7 +254,7 @@ class GenericIE(InfoExtractor): # Look for embedded (iframe) Vimeo player mobj = re.search( - r'<iframe[^>]+?src="((?:https?:)?//player.vimeo.com/video/.+?)"', webpage) + r'<iframe[^>]+?src="((?:https?:)?//player\.vimeo\.com/video/.+?)"', webpage) if mobj: player_url = unescapeHTML(mobj.group(1)) surl = smuggle_url(player_url, {'Referer': url}) @@ -262,7 +262,7 @@ class GenericIE(InfoExtractor): # Look for embedded (swf embed) Vimeo player mobj = re.search( - r'<embed[^>]+?src="(https?://(?:www\.)?vimeo.com/moogaloop.swf.+?)"', webpage) + r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) if mobj: return self.url_result(mobj.group(1), 'Vimeo') @@ -332,7 +332,7 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group(1), 'Aparat') # Look for MPORA videos - mobj = re.search(r'<iframe .*?src="(http://mpora\.com/videos/[^"]+)"', webpage) + mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage) if mobj is not None: return self.url_result(mobj.group(1), 'Mpora') @@ -350,7 +350,7 @@ class GenericIE(InfoExtractor): # Look for embedded Huffington Post player mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live.huffingtonpost\.com/.+?)\1', webpage) + r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage) if mobj is not None: return self.url_result(mobj.group('url'), 'HuffPost') |