X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fcomedycentral.py;h=ed3986f313a149f0db4a69dc92762730297ced1a;hb=cd8662de220911f89960550ef02c1e3bae327922;hp=1bb359046b958b5554371ca4aa602696efe8fe8f;hpb=825e0984e27f0c626c4d072066e0c9cae9069704;p=youtube-dl.git
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index 1bb359046..ed3986f31 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -1,7 +1,9 @@
+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,
@@ -11,9 +13,26 @@ from ..utils import (
)
-class ComedyCentralIE(InfoExtractor):
- """Information extractor for The Daily Show and Colbert Report """
+class ComedyCentralIE(MTVServicesInfoExtractor):
+ _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/
+ (video-clips|episodes|cc-studios|video-collections)
+ /(?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',
+ '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 / 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
@@ -25,8 +44,21 @@ class ComedyCentralIE(InfoExtractor):
(full-episodes/(?P.*)|
(?P
(the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?))
- |(watch/(?P[^/]*)/(?P.*)))))
+ |(watch/(?P[^/]*)/(?P.*)))|
+ (?P
+ extended-interviews/(?P[0-9]+)/playlist_tds_extended_(?P.*?)/.*?)))
$"""
+ _TEST = {
+ 'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
+ 'file': '422212.mp4',
+ 'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
+ 'info_dict': {
+ "upload_date": "20121214",
+ "description": "Kristen Stewart",
+ "uploader": "thedailyshow",
+ "title": "thedailyshow-kristen-stewart part 1"
+ }
+ }
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
@@ -39,12 +71,12 @@ class ComedyCentralIE(InfoExtractor):
'400': 'mp4',
}
_video_dimensions = {
- '3500': '1280x720',
- '2200': '960x540',
- '1700': '768x432',
- '1200': '640x360',
- '750': '512x288',
- '400': '384x216',
+ '3500': (1280, 720),
+ '2200': (960, 540),
+ '1700': (768, 432),
+ '1200': (640, 360),
+ '750': (512, 288),
+ '400': (384, 216),
}
@classmethod
@@ -52,22 +84,24 @@ class ComedyCentralIE(InfoExtractor):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
- def _print_formats(self, formats):
- print('Available formats:')
- for x in formats:
- print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
-
+ @staticmethod
+ def _transform_rtmp_url(rtmp_video_url):
+ m = re.match(r'^rtmpe?://.*?/(?Pgsp\.comedystor/.*)$', 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://www.thedailyshow.com/full-episodes/'
else:
- url = u'http://www.colbertnation.com/full-episodes/'
+ url = 'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
assert mobj is not None
@@ -77,6 +111,9 @@ class ComedyCentralIE(InfoExtractor):
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:
@@ -90,9 +127,9 @@ class ComedyCentralIE(InfoExtractor):
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)
+ raise ExtractorError('Redirected URL is still not specific: ' + url)
epTitle = mobj.group('episode')
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 = {
+ formats = []
+ for format, rtmp_video_url in turls:
+ w, h = self._video_dimensions.get(format, (None, None))
+ formats.append({
+ 'url': self._transform_rtmp_url(rtmp_video_url),
+ 'ext': self._video_extensions.get(format, 'mp4'),
+ 'format_id': format,
+ 'height': h,
+ 'width': w,
+ })
+
+ effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1)
+ results.append({
'id': shortMediaId,
- 'url': video_url,
+ 'formats': formats,
'uploader': showId,
'upload_date': officialDate,
'title': effTitle,
- 'ext': 'mp4',
- 'format': format,
'thumbnail': None,
- 'description': officialTitle,
- }
- results.append(info)
+ 'description': compat_str(officialTitle),
+ })
return results