X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/1270059fa7cf720bc0533c2cdfe6370923ae4e20..712213a489c35dbaf5120268f1a309dc457cea29:/youtube_dl/extractor/sixplay.py?ds=sidebyside diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index 69951e3..7ec66ec 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -19,29 +19,41 @@ from ..utils import ( class SixPlayIE(InfoExtractor): IE_NAME = '6play' - _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P[0-9]+)' - _TEST = { - 'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450', - 'md5': '42310bffe4ba3982db112b9cd3467328', + _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P[0-9]+)' + _TESTS = [{ + 'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051', + 'md5': '31fcd112637baa0c2ab92c4fcd8baf27', 'info_dict': { - 'id': '11638450', + 'id': '12041051', 'ext': 'mp4', - 'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6', - 'description': 'md5:308853f6a5f9e2d55a30fc0654de415f', - 'duration': 39, - 'series': 'Le meilleur pâtissier', + 'title': 'Le but qui a marqué l\'histoire du football français !', + 'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851', }, - 'params': { - 'skip_download': True, - }, - } + }, { + 'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869', + 'only_matching': True, + }, { + 'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989', + 'only_matching': True, + }, { + 'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787', + 'only_matching': True, + }] def _real_extract(self, url): - video_id = self._match_id(url) + domain, video_id = re.search(self._VALID_URL, url).groups() + service, consumer_name = { + '6play.fr': ('6play', 'm6web'), + 'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'), + 'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'), + 'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'), + }.get(domain, ('6play', 'm6web')) data = self._download_json( - 'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id, - video_id, query={ + 'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/%s/videos/clip_%s' % (service, video_id), + video_id, headers={ + 'x-customer-name': consumer_name + }, query={ 'csa': 5, 'with': 'clips', }) @@ -53,10 +65,11 @@ class SixPlayIE(InfoExtractor): quality_key = qualities(['lq', 'sd', 'hq', 'hd']) formats = [] subtitles = {} - for asset in clip_data['assets']: + assets = clip_data.get('assets') or [] + for asset in assets: asset_url = asset.get('full_physical_path') protocol = asset.get('protocol') - if not asset_url or protocol == 'primetime' or asset_url in urls: + if not asset_url or ((protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264') and not ('_drmnp.ism/' in asset_url or '_unpnp.ism/' in asset_url)) or asset_url in urls: continue urls.append(asset_url) container = asset.get('video_container') @@ -65,20 +78,26 @@ class SixPlayIE(InfoExtractor): subtitles.setdefault('fr', []).append({'url': asset_url}) continue if container == 'm3u8' or ext == 'm3u8': - if protocol == 'usp' and not compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]: - asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url) - formats.extend(self._extract_m3u8_formats( - asset_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - asset_url.replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - formats.extend(self._extract_mpd_formats( - asset_url.replace('.m3u8', '.mpd'), - video_id, mpd_id='dash', fatal=False)) - formats.extend(self._extract_ism_formats( - re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url), - video_id, ism_id='mss', fatal=False)) + if protocol == 'usp': + if compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]: + urlh = self._request_webpage( + asset_url, video_id, fatal=False, + headers=self.geo_verification_headers()) + if not urlh: + continue + asset_url = urlh.geturl() + asset_url = asset_url.replace('_drmnp.ism/', '_unpnp.ism/') + for i in range(3, 0, -1): + asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i) + m3u8_formats = self._extract_m3u8_formats( + asset_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + formats.extend(m3u8_formats) + formats.extend(self._extract_mpd_formats( + asset_url.replace('.m3u8', '.mpd'), + video_id, mpd_id='dash', fatal=False)) + if m3u8_formats: + break else: formats.extend(self._extract_m3u8_formats( asset_url, video_id, 'mp4', 'm3u8_native',