summaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/parliamentliveuk.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2014-03-21 01:42:28 +0100
committerPhilipp Hagemeister <[email protected]>2014-03-21 01:42:28 +0100
commit1b124d19422b107a6279355b9a727f31694e325f (patch)
tree155855d7b011765be0f3ed9ba401fdce5d9dd5be /youtube_dl/extractor/parliamentliveuk.py
parent747373d4ae1e380105b7157e622effddf5fcb747 (diff)
downloadyoutube-dl-1b124d19422b107a6279355b9a727f31694e325f.tar.gz
youtube-dl-1b124d19422b107a6279355b9a727f31694e325f.zip
[parliamentliveuk] Add extractor
Diffstat (limited to 'youtube_dl/extractor/parliamentliveuk.py')
-rw-r--r--youtube_dl/extractor/parliamentliveuk.py57
1 files changed, 57 insertions, 0 deletions
diff --git a/youtube_dl/extractor/parliamentliveuk.py b/youtube_dl/extractor/parliamentliveuk.py
new file mode 100644
index 000000000..02dca14c0
--- /dev/null
+++ b/youtube_dl/extractor/parliamentliveuk.py
@@ -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,
+ }