depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-22 08:47:41 +00:00
Code Issues Releases Wiki Activity

Add support for comedycentral clips (closes #233)

Browse source 
Support individual clips, not just full episodes.
break up now monstrous _VALID_URL regex over multiple lines to improve readability,
pass re.VERBOSE flag when using regex to ignore the whitespace
This commit is contained in:
nto 2012-12-11 21:38:16 -06:00
parent a4680a590f
commit ca6849e65d
1 changed files with 33 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
youtube_dl/InfoExtractors.py
View file

@ -2397,7 +2397,19 @@ class MyVideoIE(InfoExtractor):
class ComedyCentralIE(InfoExtractor): class ComedyCentralIE(InfoExtractor):
"""Information extractor for The Daily Show and Colbert Report """ """Information extractor for The Daily Show and Colbert Report """
_VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$' # urls can be abbreviations like :thedailyshow or :colbert
# urls for episodes like:
# or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
# or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
# or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
_VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
|(https?://)?(www\.)?
(?P<showname>thedailyshow|colbertnation)\.com/
(full-episodes/(?P<episode>.*)|
(?P<clip>
(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
$"""
IE_NAME = u'comedycentral' IE_NAME = u'comedycentral'
_available_formats = ['3500', '2200', '1700', '1200', '750', '400'] _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
@ -2419,6 +2431,10 @@ class ComedyCentralIE(InfoExtractor):
'400': '384x216', '400': '384x216',
} }
def suitable(self, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None
def report_extraction(self, episode_id): def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
@ -2439,7 +2455,7 @@ class ComedyCentralIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return return
@ -2449,14 +2465,21 @@ class ComedyCentralIE(InfoExtractor):
url = u'http://www.thedailyshow.com/full-episodes/' url = u'http://www.thedailyshow.com/full-episodes/'
else: else:
url = u'http://www.colbertnation.com/full-episodes/' url = u'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url, re.VERBOSE)
assert mobj is not None assert mobj is not None
dlNewest = not mobj.group('episode') if mobj.group('clip'):
if dlNewest: if mobj.group('showname') == 'thedailyshow':
epTitle = mobj.group('showname') epTitle = mobj.group('tdstitle')
else:
epTitle = mobj.group('cntitle')
dlNewest = False
else: else:
epTitle = mobj.group('episode') dlNewest = not mobj.group('episode')
if dlNewest:
epTitle = mobj.group('showname')
else:
epTitle = mobj.group('episode')
req = compat_urllib_request.Request(url) req = compat_urllib_request.Request(url)
self.report_extraction(epTitle) self.report_extraction(epTitle)
@ -2468,7 +2491,7 @@ class ComedyCentralIE(InfoExtractor):
return return
if dlNewest: if dlNewest:
url = htmlHandle.geturl() url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
return return
@ -2477,14 +2500,14 @@ class ComedyCentralIE(InfoExtractor):
return return
epTitle = mobj.group('episode') epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html) mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html)
if len(mMovieParams) == 0: if len(mMovieParams) == 0:
# The Colbert Report embeds the information in a without # The Colbert Report embeds the information in a without
# a URL prefix; so extract the alternate reference # a URL prefix; so extract the alternate reference
# and then add the URL prefix manually. # and then add the URL prefix manually.
altMovieParams = re.findall('data-mgid="([^"]*episode.*?:.*?)"', html) altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html)
if len(altMovieParams) == 0: if len(altMovieParams) == 0:
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
return return