0
0
Fork 0

[parliamentliveuk] fix extraction(closes #9137)

main
Remita Amine 2016-09-08 20:45:13 +01:00
parent b717837190
commit 4614ad7b59
1 changed files with 22 additions and 35 deletions

View File

@ -1,53 +1,40 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
class ParliamentLiveUKIE(InfoExtractor): class ParliamentLiveUKIE(InfoExtractor):
IE_NAME = 'parliamentlive.tv' IE_NAME = 'parliamentlive.tv'
IE_DESC = 'UK parliament videos' IE_DESC = 'UK parliament videos'
_VALID_URL = r'https?://www\.parliamentlive\.tv/Main/Player\.aspx\?(?:[^&]+&)*?meetingId=(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?parliamentlive\.tv/Event/Index/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TEST = { _TEST = {
'url': 'http://www.parliamentlive.tv/Main/Player.aspx?meetingId=15121&player=windowsmedia', 'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
'info_dict': { 'info_dict': {
'id': '15121', 'id': 'c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
'ext': 'asf', 'ext': 'mp4',
'title': 'hoc home affairs committee, 18 mar 2014.pm', 'title': 'Home Affairs Committee',
'description': 'md5:033b3acdf83304cd43946b2d5e5798d1', 'uploader_id': 'FFMPEG-01',
'timestamp': 1422696664,
'upload_date': '20150131',
}, },
'params': {
'skip_download': True, # Requires mplayer (mms)
}
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id') webpage = self._download_webpage(
webpage = self._download_webpage(url, video_id) 'http://vodplayer.parliamentlive.tv/?mid=' + video_id, video_id)
widget_config = self._parse_json(self._search_regex(
asx_url = self._html_search_regex( r'kWidgetConfig\s*=\s*({.+});',
r'embed.*?src="([^"]+)" name="MediaPlayer"', webpage, webpage, 'kaltura widget config'), video_id)
'metadata URL') kaltura_url = 'kaltura:%s:%s' % (widget_config['wid'][1:], widget_config['entry_id'])
asx = self._download_xml(asx_url, video_id, 'Downloading ASX metadata') event_title = self._download_json(
video_url = asx.find('.//REF').attrib['HREF'] 'http://parliamentlive.tv/Event/GetShareVideo/' + video_id, video_id)['event']['title']
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 { return {
'_type': 'url_transparent',
'id': video_id, 'id': video_id,
'ext': 'asf', 'title': event_title,
'url': video_url, 'description': '',
'title': title, 'url': kaltura_url,
'description': description, 'ie_key': 'Kaltura',
} }