X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fcomedycentral.py;h=035046120152f264278b4edc4bd5b11e0183da98;hb=af8812bb9b50586dd228c624b1bc569639070254;hp=1bb359046b958b5554371ca4aa602696efe8fe8f;hpb=ea63e4998bd8ed84f7479d1283eea4074ac8dba6;p=youtube-dl.git
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index 1bb359046..035046120 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -1,32 +1,94 @@
+from __future__ import unicode_literals
+
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
+from .mtv import MTVServicesInfoExtractor
from ..utils import (
compat_str,
compat_urllib_parse,
-
ExtractorError,
+ float_or_none,
unified_strdate,
)
-class ComedyCentralIE(InfoExtractor):
- """Information extractor for The Daily Show and Colbert Report """
+class ComedyCentralIE(MTVServicesInfoExtractor):
+ _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.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.',
+ },
+ }
+
+class ComedyCentralShowsIE(InfoExtractor):
+ 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.*)))))
- $"""
+ (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P[^/?#]+))
+ |(the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?))
+ |(watch/(?P[^/]*)/(?P.*))
+ )|
+ (?P
+ extended-interviews/(?P[0-9a-z]+)/(?:playlist_tds_extended_)?(?P.*?)(/.*?)?)))
+ (?:[?#].*|$)'''
+ _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/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']
@@ -39,141 +101,145 @@ class ComedyCentralIE(InfoExtractor):
'400': 'mp4',
}
_video_dimensions = {
- '3500': '1280x720',
- '2200': '960x540',
- '1700': '768x432',
- '1200': '640x360',
- '750': '512x288',
- '400': '384x216',
+ '3500': (1280, 720),
+ '2200': (960, 540),
+ '1700': (768, 432),
+ '1200': (640, 360),
+ '750': (512, 288),
+ '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
-
- def _print_formats(self, formats):
- print('Available formats:')
- for x in formats:
- print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
-
+ @staticmethod
+ def _transform_rtmp_url(rtmp_video_url):
+ m = re.match(r'^rtmpe?://.*?/(?Pgsp\.comedystor/.*)$', rtmp_video_url)
+ if not m:
+ raise ExtractorError('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)
+ raise ExtractorError('Invalid URL: %s' % 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')
dlNewest = False
+ elif mobj.group('interview'):
+ epTitle = mobj.group('interview_title')
+ dlNewest = False
else:
dlNewest = not mobj.group('episode')
if dlNewest:
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('(?:gsp.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/'
- video_url = base + m.group('finalid')
-
- effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
- info = {
- 'id': shortMediaId,
- 'url': video_url,
- 'uploader': showId,
- 'upload_date': officialDate,
- 'title': effTitle,
- 'ext': 'mp4',
- 'format': format,
- 'thumbnail': None,
- 'description': officialTitle,
- }
- results.append(info)
-
- return results
+ formats = []
+ for format, rtmp_video_url in turls:
+ w, h = self._video_dimensions.get(format, (None, None))
+ formats.append({
+ 'format_id': 'vhttp-%s' % format,
+ 'url': self._transform_rtmp_url(rtmp_video_url),
+ 'ext': self._video_extensions.get(format, 'mp4'),
+ 'height': h,
+ 'width': w,
+
+ 'format_note': 'HTTP 400 at the moment (patches welcome!)',
+ 'preference': -100,
+ })
+ formats.append({
+ 'format_id': 'rtmp-%s' % format,
+ '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)
+ entries.append({
+ 'id': guid,
+ 'title': virtual_id,
+ 'formats': formats,
+ 'uploader': show_name,
+ 'upload_date': upload_date,
+ 'duration': duration,
+ 'thumbnail': thumbnail,
+ 'description': description,
+ })
+
+ return {
+ '_type': 'playlist',
+ 'entries': entries,
+ 'title': show_name + ' ' + title,
+ 'description': description,
+ }