X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/33cd347759d6d999325ebf3c69b7ed5692c343b2..fe979149c83b5a935f7d28baf75848a9137316fd:/youtube_dl/extractor/canalplus.py?ds=sidebyside diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 3b1c888..61463f2 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -1,46 +1,168 @@ +# encoding: utf-8 +from __future__ import unicode_literals + import re -import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import unified_strdate +from ..compat import compat_urllib_parse_urlparse +from ..utils import ( + ExtractorError, + HEADRequest, + unified_strdate, + qualities, + int_or_none, +) + class CanalplusIE(InfoExtractor): - _VALID_URL = r'https?://www\.canalplus\.fr/.*?\?vid=(?P\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' + IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv' + _VALID_URL = r'''(?x) + https?:// + (?: + (?: + (?:(?:www|m)\.)?canalplus\.fr| + (?:www\.)?piwiplus\.fr| + (?:www\.)?d8\.tv| + (?:www\.)?d17\.tv| + (?:www\.)?itele\.fr + )/(?:(?:[^/]+/)*(?P[^/?#&]+))?(?:\?.*\bvid=(?P\d+))?| + player\.canalplus\.fr/#/(?P\d+) + ) + + ''' + _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json' + _SITE_ID_MAP = { + 'canalplus': 'cplus', + 'piwiplus': 'teletoon', + 'd8': 'd8', + 'd17': 'd17', + 'itele': 'itele', } + _TESTS = [{ + 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814', + 'md5': '41f438a4904f7664b91b4ed0dec969dc', + 'info_dict': { + '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', + 'info_dict': { + 'id': '1108190', + 'ext': 'flv', + 'title': 'Le labyrinthe - Boing super ranger', + 'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff', + 'upload_date': '20140724', + }, + 'skip': 'Only works from France', + }, { + 'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231', + 'info_dict': { + '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, + }, + }, { + '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': '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.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, - } + video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid') + + 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 = 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']+?videoId=(["\'])(?P\d+)', r'id=["\']canal_video_player(?P\d+)'], + webpage, 'video id', group='id') + + info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id) + video_data = self._download_json(info_url, video_id, 'Downloading video JSON') + + 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']) + + fmt_url = next(iter(media.get('VIDEOS'))) + if '/geo' in fmt_url.lower(): + response = self._request_webpage( + HEADRequest(fmt_url), video_id, + 'Checking if the video is georestricted') + if '/blocage' in response.geturl(): + raise ExtractorError( + 'The video is not available in your country', + expected=True) + + formats = [] + for format_id, format_url in media['VIDEOS'].items(): + if not format_url: + continue + if format_id == 'HLS': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False)) + elif format_id == 'HDS': + formats.extend(self._extract_f4m_formats( + format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False)) + else: + formats.append({ + # 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' % (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, + }