diff options
| author | Jaime Marquínez Ferrándiz <jaimeMF@users.noreply.github.com> | 2014-01-29 14:58:14 -0800 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaimeMF@users.noreply.github.com> | 2014-01-29 14:58:14 -0800 |
| commit | 251974e44cf3a79fb656fdf290d989d73851642f (patch) | |
| tree | bc3986eed0a95bccb0e68deb52edb9ef7064a5ef | |
| parent | 0c708f11cbde6339adbf9a8477f673e25e68e920 (diff) | |
| parent | 57b62883586487df5adc8a45d91969eea14309b7 (diff) | |
Merge pull request #2272 from dstftw/master
Improve some regexes
| -rw-r--r-- | youtube_dl/extractor/comedycentral.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 8 |
2 files changed, 6 insertions, 6 deletions
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 3333d433b..ed3986f31 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -14,7 +14,7 @@ from ..utils import ( class ComedyCentralIE(MTVServicesInfoExtractor): - _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/ + _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/ (video-clips|episodes|cc-studios|video-collections) /(?P<title>.*)''' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' @@ -86,7 +86,7 @@ class ComedyCentralShowsIE(InfoExtractor): @staticmethod def _transform_rtmp_url(rtmp_video_url): - m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url) + m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url) if not m: raise ExtractorError('Cannot transform RTMP url') base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' 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') |