]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/canalplus.py
release 2014.05.05
[yt-dlp.git] / youtube_dl / extractor / canalplus.py
CommitLineData
ad94a6fe 1# encoding: utf-8
b075d25b
S
2from __future__ import unicode_literals
3
ffca4b5c 4import re
ffca4b5c
JMF
5
6from .common import InfoExtractor
7from ..utils import unified_strdate
8
69545c2a 9
ffca4b5c 10class CanalplusIE(InfoExtractor):
ad94a6fe 11 _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
ffca4b5c 12 _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
b075d25b 13 IE_NAME = 'canalplus.fr'
ffca4b5c
JMF
14
15 _TEST = {
b075d25b 16 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
113c7d3e 17 'md5': '3db39fb48b9685438ecf33a1078023e4',
b075d25b
S
18 'info_dict': {
19 'id': '922470',
20 'ext': 'flv',
21 'title': 'Zapping - 26/08/13',
22 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
23 'upload_date': '20130826',
ad94a6fe 24 },
ffca4b5c
JMF
25 }
26
27 def _real_extract(self, url):
28 mobj = re.match(self._VALID_URL, url)
b075d25b
S
29 video_id = mobj.group('id')
30
ad94a6fe
JMF
31 if video_id is None:
32 webpage = self._download_webpage(url, mobj.group('path'))
b075d25b
S
33 video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
34
ffca4b5c 35 info_url = self._VIDEO_INFO_TEMPLATE % video_id
b075d25b 36 doc = self._download_xml(info_url, video_id, 'Downloading video XML')
ffca4b5c 37
ffca4b5c 38 video_info = [video for video in doc if video.find('ID').text == video_id][0]
ffca4b5c 39 media = video_info.find('MEDIA')
b075d25b
S
40 infos = video_info.find('INFOS')
41
42 preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']
43
44 formats = [
45 {
46 'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text,
47 'format_id': fmt.tag,
48 'ext': 'mp4' if fmt.tag == 'HLS' else 'flv',
49 'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1,
50 } for fmt in media.find('VIDEOS') if fmt.text
51 ]
52 self._sort_formats(formats)
53
54 return {
55 'id': video_id,
56 'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
57 infos.find('TITRAGE/SOUS_TITRE').text),
58 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
59 'thumbnail': media.find('IMAGES/GRAND').text,
60 'description': infos.find('DESCRIPTION').text,
61 'view_count': int(infos.find('NB_VUES').text),
62 'like_count': int(infos.find('NB_LIKES').text),
63 'comment_count': int(infos.find('NB_COMMENTS').text),
64 'formats': formats,
65 }