Compare commits

...

4 Commits

Author SHA1 Message Date
Philipp Hagemeister
1f91bd15c3 release 2014.03.21.3 2014-03-21 02:10:35 +01:00
Philipp Hagemeister
11a15be4ce [cspan] Add support for newer videos (Fixes #2577) 2014-03-21 02:10:24 +01:00
Philipp Hagemeister
14e17e18cb release 2014.03.21.2 2014-03-21 01:42:45 +01:00
Philipp Hagemeister
1b124d1942 [parliamentliveuk] Add extractor 2014-03-21 01:42:28 +01:00
4 changed files with 74 additions and 5 deletions

View File

@@ -174,6 +174,7 @@ from .nowness import NownessIE
from .nowvideo import NowVideoIE
from .ooyala import OoyalaIE
from .orf import ORFIE
from .parliamentliveuk import ParliamentLiveUKIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE
from .playvid import PlayvidIE

View File

@@ -10,9 +10,9 @@ from ..utils import (
class CSpanIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>\d+)'
_VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
IE_DESC = 'C-SPAN'
_TEST = {
_TESTS = [{
'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
'md5': '8e44ce11f0f725527daccc453f553eb0',
'info_dict': {
@@ -22,13 +22,24 @@ class CSpanIE(InfoExtractor):
'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
},
'skip': 'Regularly fails on travis, for unknown reasons',
}
}, {
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
# For whatever reason, the served vide oalternates between
# two different ones
#'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c',
'info_dict': {
'id': '340723',
'ext': 'mp4',
'title': 'International Health Care Models',
'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
page_id = mobj.group('id')
webpage = self._download_webpage(url, page_id)
video_id = self._search_regex(r'data-progid=\'(\d+)\'>', webpage, 'video id')
video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
description = self._html_search_regex(
[

View File

@@ -0,0 +1,57 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unified_strdate,
)
class ParliamentLiveUKIE(InfoExtractor):
IE_NAME = 'parliamentlive.tv'
IE_DESC = 'UK parliament videos'
_VALID_URL = r'https?://www\.parliamentlive\.tv/Main/Player\.aspx\?(?:[^&]+&)*?meetingId=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.parliamentlive.tv/Main/Player.aspx?meetingId=15121&player=windowsmedia',
'info_dict': {
'id': '15121',
'ext': 'asf',
'title': 'hoc home affairs committee, 18 mar 2014.pm',
'description': 'md5:033b3acdf83304cd43946b2d5e5798d1',
},
'params': {
'skip_download': True, # Requires mplayer (mms)
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
asx_url = self._html_search_regex(
r'embed.*?src="([^"]+)" name="MediaPlayer"', webpage,
'metadata URL')
asx = self._download_xml(asx_url, video_id, 'Downloading ASX metadata')
video_url = asx.find('.//REF').attrib['HREF']
title = self._search_regex(
r'''(?x)player\.setClipDetails\(
(?:(?:[0-9]+|"[^"]+"),\s*){2}
"([^"]+",\s*"[^"]+)"
''',
webpage, 'title').replace('", "', ', ')
description = self._html_search_regex(
r'(?s)<span id="MainContentPlaceHolder_CaptionsBlock_WitnessInfo">(.*?)</span>',
webpage, 'description')
return {
'id': video_id,
'ext': 'asf',
'url': video_url,
'title': title,
'description': description,
}

View File

@@ -1,2 +1,2 @@
__version__ = '2014.03.21.1'
__version__ = '2014.03.21.3'