compat_str,
compat_urllib_parse,
ExtractorError,
- int_or_none,
+ float_or_none,
unified_strdate,
)
_TEST = {
'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
- 'md5': '4167875aae411f903b751a21f357f1ee',
+ 'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
'info_dict': {
'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
'ext': 'mp4',
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
|https?://(:www\.)?
(?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
- (full-episodes/(?P<episode>.*)|
+ ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
(?P<clip>
- (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
- |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
+ (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+))
+ |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
+ |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
+ )|
(?P<interview>
- extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
- $'''
+ extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
+ (?:[?#].*|$)'''
_TEST = {
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
'upload_date': '20121213',
'description': 'Kristen Stewart learns to let loose in "On the Road."',
'uploader': 'thedailyshow',
- 'title': 'thedailyshow-kristen-stewart part 1',
+ 'title': 'thedailyshow kristen-stewart part 1',
}
}
assert mobj is not None
if mobj.group('clip'):
- if mobj.group('showname') == 'thedailyshow':
+ if mobj.group('videotitle'):
+ epTitle = mobj.group('videotitle')
+ elif mobj.group('showname') == 'thedailyshow':
epTitle = mobj.group('tdstitle')
else:
epTitle = mobj.group('cntitle')
raise ExtractorError('Invalid redirected URL: ' + url)
if mobj.group('episode') == '':
raise ExtractorError('Redirected URL is still not specific: ' + url)
- epTitle = mobj.group('episode').rpartition('/')[-1]
+ epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
if len(mMovieParams) == 0:
# a URL prefix; so extract the alternate reference
# and then add the URL prefix manually.
- altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
+ altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
raise ExtractorError('unable to find Flash URL in webpage ' + url)
else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
uri = mMovieParams[0][1]
+ # Correct cc.com in uri
+ uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
+
index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
idoc = self._download_xml(
index_url, epTitle,
thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
- duration = int_or_none(content.attrib.get('duration'))
+ duration = float_or_none(content.attrib.get('duration'))
mediagen_url = content.attrib['url']
- guid = itemEl.find('.//guid').text.rpartition(':')[-1]
+ guid = itemEl.find('./guid').text.rpartition(':')[-1]
cdoc = self._download_xml(
mediagen_url, epTitle,
})
formats.append({
'format_id': 'rtmp-%s' % format,
- 'url': rtmp_video_url,
+ 'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
'ext': self._video_extensions.get(format, 'mp4'),
'height': h,
'width': w,
})
self._sort_formats(formats)
- virtual_id = show_name + '-' + epTitle + ' part ' + compat_str(part_num + 1)
+ virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
entries.append({
'id': guid,
'title': virtual_id,
return {
'_type': 'playlist',
'entries': entries,
- 'title': title,
+ 'title': show_name + ' ' + title,
'description': description,
}