import re
from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
from ..utils import (
ExtractorError,
HEADRequest,
unified_strdate,
- url_basename,
qualities,
+ int_or_none,
)
class CanalplusIE(InfoExtractor):
IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
- _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
- _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:
+ (?:(?:www|m)\.)?canalplus\.fr|
+ (?:www\.)?piwiplus\.fr|
+ (?:www\.)?d8\.tv|
+ (?:www\.)?d17\.tv|
+ (?:www\.)?itele\.fr
+ )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
+ player\.canalplus\.fr/#/(?P<id>\d+)
+ )
+
+ '''
+ _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
_SITE_ID_MAP = {
- 'canalplus.fr': 'cplus',
- 'piwiplus.fr': 'teletoon',
- 'd8.tv': 'd8',
- 'itele.fr': 'itele',
+ 'canalplus': 'cplus',
+ 'piwiplus': 'teletoon',
+ 'd8': 'd8',
+ 'd17': 'd17',
+ 'itele': 'itele',
}
_TESTS = [{
- 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
- 'md5': 'b3481d7ca972f61e37420798d0a9d934',
+ 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
+ 'md5': '41f438a4904f7664b91b4ed0dec969dc',
'info_dict': {
- 'id': '1263092',
- 'ext': 'flv',
- 'title': 'Le Zapping - 13/05/15',
- 'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
- 'upload_date': '20150513',
+ 'id': '1192814',
+ 'ext': 'mp4',
+ 'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014",
+ 'description': "Toute l'année 2014 dans un Zapping exceptionnel !",
+ 'upload_date': '20150105',
},
}, {
'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
},
'skip': 'Only works from France',
}, {
- 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+ 'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231',
'info_dict': {
- 'id': '966289',
- 'ext': 'flv',
- 'title': 'Campagne intime - Documentaire exceptionnel',
- 'description': 'md5:d2643b799fb190846ae09c61e59a859f',
- 'upload_date': '20131108',
+ 'id': '1390231',
+ 'ext': 'mp4',
+ 'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité",
+ 'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6',
+ 'upload_date': '20160512',
+ },
+ 'params': {
+ 'skip_download': True,
},
- 'skip': 'videos get deleted after a while',
}, {
- 'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
- 'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
+ 'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224',
'info_dict': {
- 'id': '1213714',
- 'ext': 'flv',
- 'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
- 'description': 'md5:8216206ec53426ea6321321f3b3c16db',
- 'upload_date': '20150211',
+ 'id': '1398334',
+ 'ext': 'mp4',
+ 'title': "L'invité de Bruce Toussaint du 07/06/2016 - ",
+ 'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324',
+ 'upload_date': '20160607',
},
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'http://m.canalplus.fr/?vid=1398231',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
+ 'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.groupdict().get('id')
+ video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid')
- site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
+ site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
# Beware, some subclasses do not define an id group
- display_id = url_basename(mobj.group('path'))
+ display_id = mobj.group('display_id') or video_id
if video_id is None:
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
- r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
+ [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
+ webpage, 'video id', group='id')
info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
- doc = self._download_xml(info_url, video_id, 'Downloading video XML')
+ video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
- video_info = [video for video in doc if video.find('ID').text == video_id][0]
- media = video_info.find('MEDIA')
- infos = video_info.find('INFOS')
+ if isinstance(video_data, list):
+ video_data = [video for video in video_data if video.get('ID') == video_id][0]
+ media = video_data['MEDIA']
+ infos = video_data['INFOS']
- preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
+ preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
- fmt_url = next(iter(media.find('VIDEOS'))).text
+ fmt_url = next(iter(media.get('VIDEOS')))
if '/geo' in fmt_url.lower():
response = self._request_webpage(
HEADRequest(fmt_url), video_id,
expected=True)
formats = []
- for fmt in media.find('VIDEOS'):
- format_url = fmt.text
+ for format_id, format_url in media['VIDEOS'].items():
if not format_url:
continue
- format_id = fmt.tag
if format_id == 'HLS':
- hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
- for fmt in hls_formats:
- fmt['preference'] = preference(format_id)
- formats.extend(hls_formats)
+ formats.extend(self._extract_m3u8_formats(
+ format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
elif format_id == 'HDS':
- hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
- for fmt in hds_formats:
- fmt['preference'] = preference(format_id)
- formats.extend(hds_formats)
+ formats.extend(self._extract_f4m_formats(
+ format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
else:
formats.append({
- 'url': format_url,
+ # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
+ 'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
'format_id': format_id,
'preference': preference(format_id),
})
self._sort_formats(formats)
+ thumbnails = [{
+ 'id': image_id,
+ 'url': image_url,
+ } for image_id, image_url in media.get('images', {}).items()]
+
+ titrage = infos['TITRAGE']
+
return {
'id': video_id,
'display_id': display_id,
- 'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
- infos.find('TITRAGE/SOUS_TITRE').text),
- 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
- 'thumbnail': media.find('IMAGES/GRAND').text,
- 'description': infos.find('DESCRIPTION').text,
- 'view_count': int(infos.find('NB_VUES').text),
- 'like_count': int(infos.find('NB_LIKES').text),
- 'comment_count': int(infos.find('NB_COMMENTS').text),
+ 'title': '%s - %s' % (titrage['TITRE'],
+ titrage['SOUS_TITRE']),
+ 'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
+ 'thumbnails': thumbnails,
+ 'description': infos.get('DESCRIPTION'),
+ 'duration': int_or_none(infos.get('DURATION')),
+ 'view_count': int_or_none(infos.get('NB_VUES')),
+ 'like_count': int_or_none(infos.get('NB_LIKES')),
+ 'comment_count': int_or_none(infos.get('NB_COMMENTS')),
'formats': formats,
}
Rapsys Git / youtubedl / blobdiff