X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsrgssr.py;h=246970c4d98a7d4592deadc1c7744c1504ccefef;hb=853a71b628bbf1626c301dc66f496464ad796b2e;hp=f759e5600e5e33f88e48d3482ad1380d29218aa3;hpb=e09f58b3bc3af6ce1e541fb7d034fe869fba6e82;p=youtube-dl diff --git a/youtube_dl/extractor/srgssr.py b/youtube_dl/extractor/srgssr.py index f759e5600..246970c4d 100644 --- a/youtube_dl/extractor/srgssr.py +++ b/youtube_dl/extractor/srgssr.py @@ -17,25 +17,30 @@ class SRGSSRIE(InfoExtractor): _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'] @@ -43,47 +48,33 @@ class SRGSSRIE(InfoExtractor): created_date = media_data.get('createdDate') or metadata.get('createdDate') timestamp = parse_iso8601(created_date) - thumbnails = [] - if 'Image' in media_data: - for image in media_data['Image']['ImageRepresentations']['ImageRepresentation']: - thumbnails.append({ - 'id': image.get('id'), - 'url': image['url'], - }) + thumbnails = [{ + 'id': image.get('id'), + 'url': image['url'], + } for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])] preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD']) formats = [] - for source in media_data['Playlists']['Playlist']: - assets = {} + for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []): protocol = source.get('@protocol') - if protocol in ('HTTP-HDS', 'HTTP-HLS'): - for quality in source['url']: - 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')) - elif '.m3u8' in asset_url: - formats.extend(self._extract_m3u8_formats(asset_url, media_id, m3u8_id='hls')) - else: - for asset in source['url']: - asset_url = asset['text'] - ext = None - if asset_url.startswith('rtmp'): - ext = self._search_regex(r'([a-z0-9]+):[^/]+', asset_url, 'ext') + for asset in source['url']: + asset_url = asset['text'] + quality = asset['@quality'] + format_id = '%s-%s' % (protocol, quality) + if protocol == 'HTTP-HDS': + formats.extend(self._extract_f4m_formats( + asset_url + '?hdcore=3.4.0', media_id, + f4m_id=format_id, fatal=False)) + elif protocol == 'HTTP-HLS': + formats.extend(self._extract_m3u8_formats( + asset_url, media_id, 'mp4', 'm3u8_native', + m3u8_id=format_id, fatal=False)) + else: formats.append({ - 'format_id': asset['@quality'], + 'format_id': format_id, 'url': asset_url, - 'preference': preference(asset['@quality']), - 'ext': ext, - }) - - 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']) + 'preference': preference(quality), + 'ext': 'flv' if protocol == 'RTMP' else None, }) self._sort_formats(formats) @@ -98,6 +89,7 @@ class SRGSSRIE(InfoExtractor): class SRGSSRPlayIE(InfoExtractor): + IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites' _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 = [{ @@ -122,7 +114,7 @@ class SRGSSRPlayIE(InfoExtractor): 'description': 'md5:88604432b60d5a38787f152dec89cd56', 'timestamp': 1373493600, }, - },{ + }, { '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', @@ -135,8 +127,29 @@ class SRGSSRPlayIE(InfoExtractor): # 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': 'mp4', + 'duration': 1796, + 'title': 'Le 19h30', + 'description': '', + 'uploader': '19h30', + 'upload_date': '20141201', + 'timestamp': 1417458600, + 'thumbnail': 're:^https?://.*\.image', + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + } }] def _real_extract(self, url): bu, media_type, media_id = re.match(self._VALID_URL, url).groups() + # other info can be extracted from url + '&layout=json' return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')