X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fcomedycentral.py;h=035046120152f264278b4edc4bd5b11e0183da98;hb=a80c96eab0b7c47ddae331ece37faa458be7bb2e;hp=ed3986f313a149f0db4a69dc92762730297ced1a;hpb=251974e44cf3a79fb656fdf290d989d73851642f;p=youtube-dl
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index ed3986f31..035046120 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -7,21 +7,21 @@ from .mtv import MTVServicesInfoExtractor
from ..utils import (
compat_str,
compat_urllib_parse,
-
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 = 'http://comedycentral.com/feeds/mrss/'
_TEST = {
- 'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
- 'md5': '4167875aae411f903b751a21f357f1ee',
+ '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',
@@ -32,33 +32,63 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
class ComedyCentralShowsIE(InfoExtractor):
- IE_DESC = 'The Daily Show / Colbert Report'
+ IE_DESC = 'The Daily Show / The Colbert Report'
# 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"""^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport)
- |(https?://)?(www\.)?
- (?Pthedailyshow|colbertnation)\.com/
- (full-episodes/(?P.*)|
+ _VALID_URL = r'''(?x)^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport)
+ |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.*?)/.*?)))
- $"""
- _TEST = {
- 'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
- 'file': '422212.mp4',
+ extended-interviews/(?P[0-9a-z]+)/(?:playlist_tds_extended_)?(?P.*?)(/.*?)?)))
+ (?:[?#].*|$)'''
+ _TESTS = [{
+ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
'info_dict': {
- "upload_date": "20121214",
- "description": "Kristen Stewart",
- "uploader": "thedailyshow",
- "title": "thedailyshow-kristen-stewart part 1"
+ '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/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/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']
@@ -79,11 +109,6 @@ 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)
@@ -99,14 +124,16 @@ class ComedyCentralShowsIE(InfoExtractor):
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = 'http://www.thedailyshow.com/full-episodes/'
+ url = 'http://thedailyshow.cc.com/full-episodes/'
else:
- url = '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')
@@ -120,9 +147,9 @@ 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)
@@ -130,71 +157,89 @@ class ComedyCentralShowsIE(InfoExtractor):
raise ExtractorError('Invalid redirected URL: ' + url)
if mobj.group('episode') == '':
raise ExtractorError('Redirected URL is still not specific: ' + url)
- epTitle = mobj.group('episode')
+ epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
mMovieParams = re.findall('(?: