From ffca4b5c32280e416131faf43afa0cb26c55c8b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sat, 13 Jul 2013 12:10:35 +0200 Subject: [PATCH] Add CanalplusIE (closes #59 and closes #918) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/canalplus.py | 46 +++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) create mode 100644 youtube_dl/extractor/canalplus.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 494b1b9d3..cdbd880c7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -6,6 +6,7 @@ from .bliptv import BlipTVIE, BlipTVUserIE from .breakcom import BreakIE from .brightcove import BrightcoveIE +from .canalplus import CanalplusIE from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE from .criterion import CriterionIE diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py new file mode 100644 index 000000000..3b1c88876 --- /dev/null +++ b/youtube_dl/extractor/canalplus.py @@ -0,0 +1,46 @@ +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import unified_strdate + +class CanalplusIE(InfoExtractor): + _VALID_URL = r'https?://www\.canalplus\.fr/.*?\?vid=(?P\d+)' + _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s' + IE_NAME = u'canalplus.fr' + + _TEST = { + u'url': u'http://www.canalplus.fr/c-divertissement/pid3351-c-le-petit-journal.html?vid=889861', + u'file': u'889861.flv', + u'md5': u'590a888158b5f0d6832f84001fbf3e99', + u'info_dict': { + u'title': u'Le Petit Journal 20/06/13 - La guerre des drone', + u'upload_date': u'20130620', + }, + u'skip': u'Requires rtmpdump' + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + info_url = self._VIDEO_INFO_TEMPLATE % video_id + info_page = self._download_webpage(info_url,video_id, + u'Downloading video info') + + self.report_extraction(video_id) + doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8')) + video_info = [video for video in doc if video.find('ID').text == video_id][0] + infos = video_info.find('INFOS') + media = video_info.find('MEDIA') + formats = [media.find('VIDEOS/%s' % format) + for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']] + video_url = [format.text for format in formats if format is not None][-1] + + return {'id': video_id, + 'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text, + infos.find('TITRAGE/SOUS_TITRE').text), + 'url': video_url, + 'ext': 'flv', + 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text), + 'thumbnail': media.find('IMAGES/GRAND').text, + }