diff options
author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-11-24 21:18:35 +0100 |
---|---|---|
committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-11-24 21:18:35 +0100 |
commit | 66cfab4226296c1596fbf37c27758bbdb6846d53 (patch) | |
tree | e0b8a6ab7401c9d4aed5c1e9501d5f4e9fec9e78 /youtube_dl/extractor/comedycentral.py | |
parent | 6d88bc37a32d5d624c09d68cd19e64e6095fa5de (diff) |
[comedycentral] Add support for comedycentral.com videos (closes #1824)
It's a subclass of MTVIE
The extractor for colbertnation.com and thedailyshow.com is called now ComedyCentralShowsIE
Diffstat (limited to 'youtube_dl/extractor/comedycentral.py')
-rw-r--r-- | youtube_dl/extractor/comedycentral.py | 33 |
1 files changed, 32 insertions, 1 deletions
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 69b2beece..725849d2e 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -2,6 +2,7 @@ import re import xml.etree.ElementTree from .common import InfoExtractor +from .mtv import MTVIE, _media_xml_tag from ..utils import ( compat_str, compat_urllib_parse, @@ -11,7 +12,37 @@ from ..utils import ( ) -class ComedyCentralIE(InfoExtractor): +class ComedyCentralIE(MTVIE): + _VALID_URL = r'http://www.comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)' + _FEED_URL = u'http://comedycentral.com/feeds/mrss/' + + _TEST = { + u'url': u'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', + u'md5': u'4167875aae411f903b751a21f357f1ee', + u'info_dict': { + u'id': u'cef0cbb3-e776-4bc9-b62e-8016deccb354', + u'ext': u'mp4', + u'title': u'Uncensored - Greg Fitzsimmons - Too Good of a Mother', + u'description': u'After a certain point, breastfeeding becomes c**kblocking.', + }, + } + # Overwrite MTVIE properties we don't want + _TESTS = [] + + def _get_thumbnail_url(self, uri, itemdoc): + search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) + return itemdoc.find(search_path).attrib['url'] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + title = mobj.group('title') + webpage = self._download_webpage(url, title) + mgid = self._search_regex(r'data-mgid="(?P<mgid>mgid:.*?)"', + webpage, u'mgid') + return self._get_videos_info(mgid) + + +class ComedyCentralShowsIE(InfoExtractor): IE_DESC = u'The Daily Show / Colbert Report' # urls can be abbreviations like :thedailyshow or :colbert # urls for episodes like: |