0
0
Fork 0

[comedycentral] Remove IEs for *.cc.com except tosh.cc.com

All other subdomains now redirects to cc.com/* URLs
main
Yen Chi Hsuan 2016-07-26 11:06:50 +08:00
parent 712c7530ff
commit cc99d4f826
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
1 changed files with 35 additions and 245 deletions

View File

@ -1,17 +1,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .mtv import MTVServicesInfoExtractor from .mtv import MTVServicesInfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
float_or_none,
unified_strdate,
)
class ComedyCentralIE(MTVServicesInfoExtractor): class ComedyCentralIE(MTVServicesInfoExtractor):
@ -26,8 +15,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
'ext': 'mp4', 'ext': 'mp4',
'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother', 'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
'description': 'After a certain point, breastfeeding becomes c**kblocking.', 'description': 'After a certain point, breastfeeding becomes c**kblocking.',
'timestamp': 1376798400,
'upload_date': '20130818',
}, },
}, { }, {
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
@ -35,244 +26,43 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
}] }]
class ComedyCentralShowsIE(MTVServicesInfoExtractor): class ToshIE(MTVServicesInfoExtractor):
IE_DESC = 'The Daily Show / The Colbert Report' IE_DESC = 'Tosh.0'
# urls can be abbreviations like :thedailyshow _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
# urls for episodes like: _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
# 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'''(?x)^(:(?P<shortname>tds|thedailyshow)
|https?://(:www\.)?
(?P<showname>thedailyshow|thecolbertreport|tosh)\.(?:cc\.)?com/
((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
(?P<clip>
(?:(?:guests/[^/]+|videos|video-(?:clips|playlists)|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
|(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
)|
(?P<interview>
extended-interviews/(?P<interID>[0-9a-z]+)/
(?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
(?:/[^/?#]?|[?#]|$))))
'''
_TESTS = [{ _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,
}, {
'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans', 'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
'info_dict': {
'description': 'Tosh asked fans to share their summer plans.',
'title': 'Twitter Users Share Summer Plans',
},
'playlist': [{
'md5': 'f269e88114c1805bb6d7653fecea9e06',
'info_dict': {
'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
'ext': 'mp4',
'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
'description': 'Tosh asked fans to share their summer plans.',
'thumbnail': 're:^https?://.*\.jpg',
# It's really reported to be published on year 2077
'upload_date': '20770610',
'timestamp': 3390510600,
'subtitles': {
'en': 'mincount:3',
},
},
}]
}, {
'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
'only_matching': True, 'only_matching': True,
}] }]
_available_formats = ['3500', '2200', '1700', '1200', '750', '400'] @classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
_video_extensions = { new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
'3500': 'mp4', new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
'2200': 'mp4', return new_urls
'1700': 'mp4',
'1200': 'mp4',
'750': 'mp4',
'400': 'mp4',
}
_video_dimensions = {
'3500': (1280, 720),
'2200': (960, 540),
'1700': (768, 432),
'1200': (640, 360),
'750': (512, 288),
'400': (384, 216),
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj.group('shortname'):
return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes')
if mobj.group('clip'):
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')
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('Invalid redirected URL: ' + url)
if 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('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
if len(mMovieParams) == 0:
# The Colbert Report embeds the information in a without
# a URL prefix; so extract the alternate reference
# and then add the URL prefix manually.
altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
raise ExtractorError('unable to find Flash URL in webpage ' + url)
else:
mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])]
uri = mMovieParams[0][1]
# Correct cc.com in uri
uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse_urlencode({'uri': uri}))
idoc = self._download_xml(
index_url, epTitle,
'Downloading show index', 'Unable to download episode index')
title = idoc.find('./channel/title').text
description = idoc.find('./channel/description').text
entries = []
item_els = idoc.findall('.//item')
for part_num, itemEl in enumerate(item_els):
upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
duration = float_or_none(content.attrib.get('duration'))
mediagen_url = content.attrib['url']
guid = itemEl.find('./guid').text.rpartition(':')[-1]
cdoc = self._download_xml(
mediagen_url, epTitle,
'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
turls = []
for rendition in cdoc.findall('.//rendition'):
finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
turls.append(finfo)
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,
})
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)
subtitles = self._extract_subtitles(cdoc, guid)
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,
'subtitles': subtitles,
})
return {
'_type': 'playlist',
'id': epTitle,
'entries': entries,
'title': show_name + ' ' + title,
'description': description,
}
class ComedyCentralTVIE(MTVServicesInfoExtractor): class ComedyCentralTVIE(MTVServicesInfoExtractor):