7
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-15 01:36:31 +00:00

Allow downloading current thedailyshow episode with youtube-dl :tds

This commit is contained in:
Philipp Hagemeister 2011-09-13 21:51:44 +02:00
parent 5a2ba45e09
commit f166bccc8f

View File

@ -3037,9 +3037,9 @@ class MyVideoIE(InfoExtractor):
self._downloader.trouble(u'\nERROR: Unable to download video')
class ComedyCentralIE(InfoExtractor):
"""Information extractor for blip.tv"""
"""Information extractor for The Daily Show and Colbert Report """
_VALID_URL = r'^(?:https?://)?(www\.)?(thedailyshow|colbertnation)\.com/full-episodes/(.*)$'
_VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
@staticmethod
def suitable(url):
@ -3064,15 +3064,39 @@ class ComedyCentralIE(InfoExtractor):
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
epTitle = mobj.group(3)
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
url = 'http://www.thedailyshow.com/full-episodes/'
else:
url = 'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url)
assert mobj is not None
dlNewest = not mobj.group('episode')
if dlNewest:
epTitle = mobj.group('showname')
else:
epTitle = mobj.group('episode')
req = urllib2.Request(url)
self.report_extraction(epTitle)
try:
html = urllib2.urlopen(req).read()
htmlHandle = urllib2.urlopen(req)
html = htmlHandle.read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
return
if dlNewest:
url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
return
if mobj.group('episode') == '':
self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
return
epTitle = mobj.group('episode')
mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
if len(mMovieParams) == 0: