X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/e8cd8c4bd832446f1971215b9fedc4531555dc1a..382a868cee069f08aacf0b89c9d689ec420d6b2c:/youtube_dl/extractor/comedycentral.py?ds=inline
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index 27bd825..b245389 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -1,70 +1,132 @@
+from __future__ import unicode_literals
+
import re
-from .common import InfoExtractor
from .mtv import MTVServicesInfoExtractor
-from ..utils import (
+from ..compat import (
compat_str,
compat_urllib_parse,
-
+)
+from ..utils import (
ExtractorError,
+ float_or_none,
unified_strdate,
)
class ComedyCentralIE(MTVServicesInfoExtractor):
- _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/
- (video-clips|episodes|cc-studios|video-collections)
+ _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
+ (video-clips|episodes|cc-studios|video-collections|full-episodes)
/(?P
.*)'''
- _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
+ _FEED_URL = '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.',
+ 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
+ 'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
+ 'info_dict': {
+ 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+ 'ext': 'mp4',
+ 'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
+ 'description': 'After a certain point, breastfeeding becomes c**kblocking.',
},
}
- 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="(?Pmgid:.*?)"',
- 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
+class ComedyCentralShowsIE(MTVServicesInfoExtractor):
+ IE_DESC = 'The Daily Show / The Colbert Report'
+ # urls can be abbreviations like :thedailyshow
# 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"""^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport)
- |(https?://)?(www\.)?
- (?Pthedailyshow|colbertnation)\.com/
- (full-episodes/(?P.*)|
+ _VALID_URL = r'''(?x)^(:(?Ptds|thedailyshow)
+ |https?://(:www\.)?
+ (?Pthedailyshow|thecolbertreport)\.(?:cc\.)?com/
+ ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P.*)|
(?P
- (the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?))
- |(watch/(?P[^/]*)/(?P.*)))|
+ (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P[^/?#]+))
+ |(the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?))
+ |(watch/(?P[^/]*)/(?P.*))
+ )|
(?P
- extended-interviews/(?P[0-9]+)/playlist_tds_extended_(?P.*?)/.*?)))
- $"""
- _TEST = {
- u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
- u'file': u'422212.mp4',
- u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d',
- u'info_dict': {
- u"upload_date": u"20121214",
- u"description": u"Kristen Stewart",
- u"uploader": u"thedailyshow",
- u"title": u"thedailyshow-kristen-stewart part 1"
+ extended-interviews/(?P[0-9a-z]+)/
+ (?:playlist_tds_extended_)?(?P[^/?#]*?)
+ (?:/[^/?#]?|[?#]|$))))
+ '''
+ _TESTS = [{
+ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
+ 'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
+ 'info_dict': {
+ 'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
+ 'ext': 'mp4',
+ 'upload_date': '20121213',
+ 'description': 'Kristen Stewart learns to let loose in "On the Road."',
+ 'uploader': 'thedailyshow',
+ 'title': 'thedailyshow kristen-stewart part 1',
}
- }
+ }, {
+ 'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
+ 'info_dict': {
+ 'id': 'sarah-chayes-extended-interview',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'title': 'thedailyshow Sarah Chayes Extended Interview',
+ },
+ 'playlist': [
+ {
+ 'info_dict': {
+ 'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
+ 'ext': 'mp4',
+ 'upload_date': '20150129',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'uploader': 'thedailyshow',
+ 'title': 'thedailyshow sarah-chayes-extended-interview part 1',
+ },
+ },
+ {
+ 'info_dict': {
+ 'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
+ 'ext': 'mp4',
+ 'upload_date': '20150129',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'uploader': 'thedailyshow',
+ 'title': 'thedailyshow sarah-chayes-extended-interview part 2',
+ },
+ },
+ ],
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
+ 'only_matching': True,
+ }]
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
@@ -85,34 +147,21 @@ class ComedyCentralShowsIE(InfoExtractor):
'400': (384, 216),
}
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
- @staticmethod
- def _transform_rtmp_url(rtmp_video_url):
- m = re.match(r'^rtmpe?://.*?/(?Pgsp.comedystor/.*)$', rtmp_video_url)
- if not m:
- raise ExtractorError(u'Cannot transform RTMP url')
- base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
- return base + m.group('finalid')
-
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ mobj = re.match(self._VALID_URL, url)
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = u'http://www.thedailyshow.com/full-episodes/'
+ url = 'http://thedailyshow.cc.com/full-episodes/'
else:
- url = u'http://www.colbertnation.com/full-episodes/'
+ url = 'http://thecolbertreport.cc.com/full-episodes/'
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
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')
@@ -126,81 +175,97 @@ class ComedyCentralShowsIE(InfoExtractor):
epTitle = mobj.group('showname')
else:
epTitle = mobj.group('episode')
+ show_name = mobj.group('showname')
- self.report_extraction(epTitle)
- webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
+ webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
if dlNewest:
url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- raise ExtractorError(u'Invalid redirected URL: ' + url)
+ raise ExtractorError('Invalid redirected URL: ' + url)
if mobj.group('episode') == '':
- raise ExtractorError(u'Redirected URL is still not specific: ' + url)
- epTitle = mobj.group('episode')
+ raise ExtractorError('Redirected URL is still not specific: ' + url)
+ epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
mMovieParams = re.findall('(?: