X-Git-Url: https://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsrgssr.py;h=563851b3f74353ef6a672025395ef6e9fb920e11;hb=b19ad2fb53c43c573d22663a739d192509bd8097;hp=addf4d26eef61767bdd0f5a41b288b73d5948e4e;hpb=1ef1563649374568870e9334cce7055f7c83a817;p=youtube-dl.git diff --git a/youtube_dl/extractor/srgssr.py b/youtube_dl/extractor/srgssr.py index addf4d26e..563851b3f 100644 --- a/youtube_dl/extractor/srgssr.py +++ b/youtube_dl/extractor/srgssr.py @@ -12,30 +12,34 @@ from ..utils import ( class SRGSSRIE(InfoExtractor): - _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=)?urn:(?Psrf|rts|rsi|rtr|swi):(?:[^:]+:)?(?Pvideo|audio):(?P[0-9a-f\-]{36}|\d+)' + _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?Psrf|rts|rsi|rtr|swi):(?:[^:]+:)?(?Pvideo|audio):(?P[0-9a-f\-]{36}|\d+)' _ERRORS = { 'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.', 'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.', -# 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.', + # 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.', 'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.', 'LEGAL': 'The video cannot be transmitted for legal reasons.', 'STARTDATE': 'This video is not yet available. Please try again later.', } - def _real_extract(self, url): - bu, media_type, media_id = re.match(self._VALID_URL, url).groups() - + def get_media_data(self, bu, media_type, media_id): media_data = self._download_json( 'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id), media_id)[media_type.capitalize()] if media_data.get('block') and media_data['block'] in self._ERRORS: - raise ExtractorError( - '%s said: %s' % ( - self.IE_NAME, - self._ERRORS[media_data['block']]), - expected=True) + raise ExtractorError('%s said: %s' % (self.IE_NAME, self._ERRORS[media_data['block']]), expected=True) + + return media_data + + def _real_extract(self, url): + bu, media_type, media_id = re.match(self._VALID_URL, url).groups() + + if bu == 'rts': + return self.url_result('rts:%s' % media_id, 'RTS') + + media_data = self.get_media_data(bu, media_type, media_id) metadata = media_data['AssetMetadatas']['AssetMetadata'][0] title = metadata['title'] @@ -44,11 +48,12 @@ class SRGSSRIE(InfoExtractor): timestamp = parse_iso8601(created_date) thumbnails = [] - for image in media_data['Image']['ImageRepresentations']['ImageRepresentation']: - thumbnails.append({ - 'id': image.get('id'), - 'url': image['url'], - }) + if 'Image' in media_data: + for image in media_data['Image']['ImageRepresentations']['ImageRepresentation']: + thumbnails.append({ + 'id': image.get('id'), + 'url': image['url'], + }) preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD']) formats = [] @@ -60,9 +65,13 @@ class SRGSSRIE(InfoExtractor): assets[quality['@quality']] = quality['text'] asset_url = assets.get('HD') or assets.get('HQ') or assets.get('SD') or assets.get('MQ') or assets.get('LQ') if '.f4m' in asset_url: - formats.extend(self._extract_f4m_formats(asset_url + '?hdcore=3.4.0', media_id, f4m_id='hds')) + f4m_formats = formats.extend(self._extract_f4m_formats(asset_url + '?hdcore=3.4.0', media_id, f4m_id='hds', fatal=False)) + if f4m_formats: + formats.extend(f4m_formats) elif '.m3u8' in asset_url: - formats.extend(self._extract_m3u8_formats(asset_url, media_id, m3u8_id='hls')) + m3u8_formats = formats.extend(self._extract_m3u8_formats(asset_url, media_id, m3u8_id='hls', fatal=False)) + if m3u8_formats: + formats.extend(m3u8_formats) else: for asset in source['url']: asset_url = asset['text'] @@ -70,16 +79,17 @@ class SRGSSRIE(InfoExtractor): if asset_url.startswith('rtmp'): ext = self._search_regex(r'([a-z0-9]+):[^/]+', asset_url, 'ext') formats.append({ + 'format_id': asset['@quality'], 'url': asset_url, 'preference': preference(asset['@quality']), 'ext': ext, }) - downloads = media_data.get('Downloads') - if downloads: - for source in downloads['Download']: + if 'Downloads' in media_data: + for source in media_data['Downloads']['Download']: for asset in source['url']: formats.append({ + 'format_id': asset['@quality'], 'url': asset['text'], 'preference': preference(asset['@quality']) }) @@ -96,7 +106,7 @@ class SRGSSRIE(InfoExtractor): class SRGSSRPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www|play)\.)?(?Psrf|rts|rsi|rtr|swi)\.ch/play/(?:tv|radio)/[^/]+/(?Pvideo|audio)/[^?]+\?id=(?P[0-9a-f\-]{36}|\d+)' + _VALID_URL = r'https?://(?:(?:www|play)\.)?(?Psrf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/[^/]+/(?Pvideo|audio)/[^?]+\?id=(?P[0-9a-f\-]{36}|\d+)' _TESTS = [{ 'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', @@ -121,10 +131,37 @@ class SRGSSRPlayIE(InfoExtractor): 'timestamp': 1373493600, }, }, { - 'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', - 'only_matching': True, + 'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc', + 'info_dict': { + 'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc', + 'ext': 'mp3', + 'upload_date': '20151013', + 'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem', + 'timestamp': 1444750398, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + 'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260', + 'md5': '67a2a9ae4e8e62a68d0e9820cc9782df', + 'info_dict': { + 'id': '6348260', + 'display_id': '6348260', + 'ext': 'flv', + 'duration': 1796, + 'title': 'Le 19h30', + 'description': '', + 'uploader': '19h30', + 'upload_date': '20141201', + 'timestamp': 1417458600, + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, + }, }] def _real_extract(self, url): bu, media_type, media_id = re.match(self._VALID_URL, url).groups() - return self.url_result('urn:%s:%s:%s' % (bu, media_type, media_id), 'SRGSSR') + # other info can be extracted from url + '&layout=json' + return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')