2 from __future__ import unicode_literals
6 from .srgssr import SRGSSRIE
9 compat_urllib_parse_urlparse,
20 class RTSIE(SRGSSRIE):
22 _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
26 'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
27 'md5': 'f254c4b26fb1d3c183793d52bc40d3e7',
30 'display_id': 'les-enfants-terribles',
33 'title': 'Les Enfants Terribles',
34 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
36 'upload_date': '19680921',
37 'timestamp': -40280400,
38 'thumbnail': 're:^https?://.*\.image',
43 'skip_download': True,
47 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
48 'md5': 'f1077ac5af686c76528dc8d7c5df29ba',
51 'display_id': '5742494',
54 'title': 'Les yeux dans les cieux - Mon homard au Canada',
55 'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
56 'uploader': 'Passe-moi les jumelles',
57 'upload_date': '20140404',
58 'timestamp': 1396635300,
59 'thumbnail': 're:^https?://.*\.image',
64 'skip_download': True,
68 'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
69 'md5': 'b4326fecd3eb64a458ba73c73e91299d',
72 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
75 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
76 'description': 'Hockey - Playoff',
78 'upload_date': '20140403',
79 'timestamp': 1396556882,
80 'thumbnail': 're:^https?://.*\.image',
83 'skip': 'Blocked outside Switzerland',
86 'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
87 'md5': '9f713382f15322181bb366cc8c3a4ff0',
90 'display_id': 'londres-cachee-par-un-epais-smog',
93 'title': 'Londres cachée par un épais smog',
94 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
95 'uploader': 'Le Journal en continu',
96 'upload_date': '20140403',
97 'timestamp': 1396537322,
98 'thumbnail': 're:^https?://.*\.image',
103 'skip_download': True,
107 'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
108 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
111 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
114 'title': '"Urban Hippie", de Damien Krisl',
115 'description': 'Des Hippies super glam.',
116 'upload_date': '20140403',
117 'timestamp': 1396551600,
121 # article with videos on rhs
122 'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
125 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
127 'playlist_mincount': 5,
131 def _real_extract(self, url):
132 m = re.match(self._VALID_URL, url)
133 media_id = m.group('rts_id') or m.group('id')
134 display_id = m.group('display_id') or media_id
136 def download_json(internal_id):
137 return self._download_json(
138 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
141 all_info = download_json(media_id)
143 # media_id extracted out of URL is not always a real id
144 if 'video' not in all_info and 'audio' not in all_info:
145 page = self._download_webpage(url, display_id)
147 # article with videos on rhs
149 r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
153 r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
156 entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
157 return self.playlist_result(entries, media_id, self._og_search_title(page))
159 internal_id = self._html_search_regex(
160 r'<(?:video|audio) data-id="([0-9]+)"', page,
162 all_info = download_json(internal_id)
164 media_type = 'video' if 'video' in all_info else 'audio'
167 self.get_media_data('rts', media_type, media_id)
169 info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
171 upload_timestamp = parse_iso8601(info.get('broadcast_date'))
172 duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
173 if isinstance(duration, compat_str):
174 duration = parse_duration(duration)
175 view_count = info.get('plays')
176 thumbnail = unescapeHTML(info.get('preview_image_url'))
178 def extract_bitrate(url):
179 return int_or_none(self._search_regex(
180 r'-([0-9]+)k\.', url, 'bitrate', default=None))
183 for format_id, format_url in info['streams'].items():
184 if format_id == 'hds_sd' and 'hds' in info['streams']:
186 if format_id == 'hls_sd' and 'hls' in info['streams']:
188 if format_url.endswith('.f4m'):
189 token = self._download_xml(
190 'http://tp.srgssr.ch/token/akahd.xml?stream=%s/*' % compat_urllib_parse_urlparse(format_url).path,
191 media_id, 'Downloading %s token' % format_id)
192 auth_params = xpath_text(token, './/authparams', 'auth params')
195 formats.extend(self._extract_f4m_formats(
196 '%s?%s&hdcore=3.4.0&plugin=aasp-3.4.0.132.66' % (format_url, auth_params),
197 media_id, f4m_id=format_id, fatal=False))
198 elif format_url.endswith('.m3u8'):
199 formats.extend(self._extract_m3u8_formats(
200 format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
203 'format_id': format_id,
205 'tbr': extract_bitrate(format_url),
210 'format_id': '%s-%sk' % (media['ext'], media['rate']),
211 'url': 'http://download-video.rts.ch/%s' % media['url'],
212 'tbr': media['rate'] or extract_bitrate(media['url']),
213 } for media in info['media'] if media.get('rate')])
215 self._check_formats(formats, media_id)
216 self._sort_formats(formats)
220 'display_id': display_id,
222 'title': info['title'],
223 'description': info.get('intro'),
224 'duration': duration,
225 'view_count': view_count,
226 'uploader': info.get('programName'),
227 'timestamp': upload_timestamp,
228 'thumbnail': thumbnail,