[comedycentral] Fix thedailyshow / thecolbertreport (Fixes #2600, #2596)

This commit is contained in:
Philipp Hagemeister 2014-03-25 04:00:52 +01:00
parent 02e4482e22
commit 99b380c33b

View File

@ -7,8 +7,8 @@
from ..utils import (
compat_str,
compat_urllib_parse,
ExtractorError,
int_or_none,
unified_strdate,
)
@ -32,31 +32,32 @@ 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"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
|(https?://)?(www\.)?
(?P<showname>thedailyshow|colbertnation)\.com/
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
|https?://(:www\.)?
(?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
(full-episodes/(?P<episode>.*)|
(?P<clip>
(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
(?P<interview>
extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
$"""
$'''
_TEST = {
'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
'file': '422212.mp4',
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
'info_dict': {
"upload_date": "20121214",
"description": "Kristen Stewart",
"uploader": "thedailyshow",
"title": "thedailyshow-kristen-stewart part 1"
'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
'ext': 'mp4',
'upload_date': '20121213',
'description': 'Kristen Stewart learns to let loose in "On the Road."',
'uploader': 'thedailyshow',
'title': 'thedailyshow-kristen-stewart part 1',
}
}
@ -79,11 +80,6 @@ class ComedyCentralShowsIE(InfoExtractor):
'400': (384, 216),
}
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
@staticmethod
def _transform_rtmp_url(rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
@ -99,9 +95,9 @@ def _real_extract(self, url):
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
@ -120,8 +116,8 @@ def _real_extract(self, url):
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)
if dlNewest:
url = htmlHandle.geturl()
@ -130,10 +126,9 @@ def _real_extract(self, url):
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').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
@ -146,55 +141,68 @@ def _real_extract(self, url):
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
uri = mMovieParams[0][1]
indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
idoc = self._download_xml(indexUrl, epTitle,
'Downloading show index',
'unable to download episode index')
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')
results = []
title = idoc.find('./channel/title').text
description = idoc.find('./channel/description').text
itemEls = idoc.findall('.//item')
for partNum,itemEl in enumerate(itemEls):
mediaId = itemEl.findall('./guid')[0].text
shortMediaId = mediaId.split(':')[-1]
showId = mediaId.split(':')[-2].replace('.com', '')
officialTitle = itemEl.findall('./title')[0].text
officialDate = unified_strdate(itemEl.findall('./pubDate')[0].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')
configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
compat_urllib_parse.urlencode({'uri': mediaId}))
cdoc = self._download_xml(configUrl, epTitle,
'Downloading configuration for %s' % shortMediaId)
content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
duration = int_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)
if len(turls) == 0:
self._downloader.report_error('unable to download ' + mediaId + ': No videos found')
continue
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'),
'format_id': format,
'height': h,
'width': w,
})
formats.append({
'format_id': 'rtmp-%s' % format,
'url': rtmp_video_url,
'ext': self._video_extensions.get(format, 'mp4'),
'height': h,
'width': w,
})
self._sort_formats(formats)
effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1)
results.append({
'id': shortMediaId,
virtual_id = show_name + '-' + epTitle + ' part ' + compat_str(part_num + 1)
entries.append({
'id': guid,
'title': virtual_id,
'formats': formats,
'uploader': showId,
'upload_date': officialDate,
'title': effTitle,
'thumbnail': None,
'description': compat_str(officialTitle),
'uploader': show_name,
'upload_date': upload_date,
'duration': duration,
'thumbnail': thumbnail,
'description': description,
})
return results
return {
'_type': 'playlist',
'entries': entries,
'title': title,
'description': description,
}