InfoExtractors: fix some regular expressions where dots weren't escaped

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-05-02 13:39:56 +02:00
parent 4c4f15eb78
commit feecf22511

View File

@ -3554,7 +3554,7 @@ def _real_extract(self, url):
return [info] return [info]
class SteamIE(InfoExtractor): class SteamIE(InfoExtractor):
_VALID_URL = r"""http://store.steampowered.com/ _VALID_URL = r"""http://store\.steampowered\.com/
(agecheck/)? (agecheck/)?
(?P<urltype>video|app)/ #If the page is only for videos or for a game (?P<urltype>video|app)/ #If the page is only for videos or for a game
(?P<gameID>\d+)/? (?P<gameID>\d+)/?
@ -3988,7 +3988,7 @@ def _real_extract(self, url):
return [info] return [info]
class TEDIE(InfoExtractor): class TEDIE(InfoExtractor):
_VALID_URL=r'''http://www.ted.com/ _VALID_URL=r'''http://www\.ted\.com/
( (
((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
| |
@ -4244,7 +4244,7 @@ def _real_extract(self, url):
return [info] return [info]
class TumblrIE(InfoExtractor): class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?).tumblr.com/((post)|(video))/(?P<id>\d*)/(.*?)' _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
def _real_extract(self, url): def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url) m_url = re.match(self._VALID_URL, url)
@ -4254,7 +4254,7 @@ def _real_extract(self, url):
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
re_video = r'src=\\x22(?P<video_url>http://%s.tumblr.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id) re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage) video = re.search(re_video, webpage)
if video is None: if video is None:
self.to_screen("No video founded") self.to_screen("No video founded")
@ -4278,7 +4278,7 @@ def _real_extract(self, url):
}] }]
class BandcampIE(InfoExtractor): class BandcampIE(InfoExtractor):
_VALID_URL = r'http://.*?.bandcamp.com/track/(?P<title>.*)' _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -4303,7 +4303,7 @@ def _real_extract(self, url):
mp3_info = info[u'downloads'][u'mp3-320'] mp3_info = info[u'downloads'][u'mp3-320']
# If we try to use this url it says the link has expired # If we try to use this url it says the link has expired
initial_url = mp3_info[u'url'] initial_url = mp3_info[u'url']
re_url = r'(?P<server>http://(.*?).bandcamp.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$' re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
m_url = re.match(re_url, initial_url) m_url = re.match(re_url, initial_url)
#We build the url we will use to get the final track url #We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js # This url is build in Bandcamp in the script download_bunde_*.js