[canalplus] Tweak extractor to support piwiplus (Closes #4046)

This commit is contained in:
Sergey M․ 2014-10-31 20:19:30 +07:00
parent d319948b6a
commit 72975729c8
1 changed files with 24 additions and 7 deletions

View File

@ -11,11 +11,15 @@ from ..utils import (
class CanalplusIE(InfoExtractor): class CanalplusIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))' IE_DESC = 'canalplus.fr and piwiplus.fr'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s' _VALID_URL = r'https?://(?:www\.(?P<site>canal|piwi)plus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
IE_NAME = 'canalplus.fr' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
_SITE_ID_MAP = {
'canal': 'cplus',
'piwi': 'teletoon',
}
_TEST = { _TESTS = [{
'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470', 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
'md5': '3db39fb48b9685438ecf33a1078023e4', 'md5': '3db39fb48b9685438ecf33a1078023e4',
'info_dict': { 'info_dict': {
@ -25,20 +29,33 @@ class CanalplusIE(InfoExtractor):
'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013', 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
'upload_date': '20130826', 'upload_date': '20130826',
}, },
} }, {
'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
'md5': '3db39fb48b9685438ecf33a1078023e4',
'info_dict': {
'id': '1108190',
'ext': 'flv',
'title': 'Le labyrinthe - Boing super ranger',
'description': 'md5:',
'upload_date': '20140724',
},
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.groupdict().get('id') video_id = mobj.groupdict().get('id')
site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
# Beware, some subclasses do not define an id group # Beware, some subclasses do not define an id group
display_id = url_basename(mobj.group('path')) display_id = url_basename(mobj.group('path'))
if video_id is None: if video_id is None:
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id') video_id = self._search_regex(
r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
info_url = self._VIDEO_INFO_TEMPLATE % video_id info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
doc = self._download_xml(info_url, video_id, 'Downloading video XML') doc = self._download_xml(info_url, video_id, 'Downloading video XML')
video_info = [video for video in doc if video.find('ID').text == video_id][0] video_info = [video for video in doc if video.find('ID').text == video_id][0]