1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-30 21:12:54 +01:00

Add CanalplusIE (closes #59 and closes #918)

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-07-13 12:10:35 +02:00
parent b0e72bcf34
commit ffca4b5c32
2 changed files with 47 additions and 0 deletions

View File

@ -6,6 +6,7 @@ from .bandcamp import BandcampIE
from .bliptv import BlipTVIE, BlipTVUserIE from .bliptv import BlipTVIE, BlipTVUserIE
from .breakcom import BreakIE from .breakcom import BreakIE
from .brightcove import BrightcoveIE from .brightcove import BrightcoveIE
from .canalplus import CanalplusIE
from .collegehumor import CollegeHumorIE from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE from .comedycentral import ComedyCentralIE
from .criterion import CriterionIE from .criterion import CriterionIE

View File

@ -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<id>\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,
}