From 1b124d19422b107a6279355b9a727f31694e325f Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 21 Mar 2014 01:42:28 +0100 Subject: [PATCH] [parliamentliveuk] Add extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/parliamentliveuk.py | 57 ++++++++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 youtube_dl/extractor/parliamentliveuk.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 01791338b..80b1e128a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -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 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[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)(.*?)', + webpage, 'description') + + return { + 'id': video_id, + 'ext': 'asf', + 'url': video_url, + 'title': title, + 'description': description, + }