]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/canalplus.py
3b1c8887621c8e48a51db1945b9ee93b9c2ab68d
[youtubedl] / youtube_dl / extractor / canalplus.py
1 import re
2 import xml.etree.ElementTree
3
4 from .common import InfoExtractor
5 from ..utils import unified_strdate
6
7 class CanalplusIE(InfoExtractor):
8 _VALID_URL = r'https?://www\.canalplus\.fr/.*?\?vid=(?P<id>\d+)'
9 _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
10 IE_NAME = u'canalplus.fr'
11
12 _TEST = {
13 u'url': u'http://www.canalplus.fr/c-divertissement/pid3351-c-le-petit-journal.html?vid=889861',
14 u'file': u'889861.flv',
15 u'md5': u'590a888158b5f0d6832f84001fbf3e99',
16 u'info_dict': {
17 u'title': u'Le Petit Journal 20/06/13 - La guerre des drone',
18 u'upload_date': u'20130620',
19 },
20 u'skip': u'Requires rtmpdump'
21 }
22
23 def _real_extract(self, url):
24 mobj = re.match(self._VALID_URL, url)
25 video_id = mobj.group('id')
26 info_url = self._VIDEO_INFO_TEMPLATE % video_id
27 info_page = self._download_webpage(info_url,video_id,
28 u'Downloading video info')
29
30 self.report_extraction(video_id)
31 doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
32 video_info = [video for video in doc if video.find('ID').text == video_id][0]
33 infos = video_info.find('INFOS')
34 media = video_info.find('MEDIA')
35 formats = [media.find('VIDEOS/%s' % format)
36 for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
37 video_url = [format.text for format in formats if format is not None][-1]
38
39 return {'id': video_id,
40 'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
41 infos.find('TITRAGE/SOUS_TITRE').text),
42 'url': video_url,
43 'ext': 'flv',
44 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
45 'thumbnail': media.find('IMAGES/GRAND').text,
46 }