2 from __future__ import unicode_literals
6 from .common import InfoExtractor
16 class RTSIE(InfoExtractor):
18 _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+))'
22 'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
23 'md5': '753b877968ad8afaeddccc374d4256a5',
26 'display_id': 'les-enfants-terribles',
29 'title': 'Les Enfants Terribles',
30 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
32 'upload_date': '19680921',
33 'timestamp': -40280400,
34 'thumbnail': 're:^https?://.*\.image',
39 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
40 'md5': 'c148457a27bdc9e5b1ffe081a7a8337b',
43 'display_id': 'entre-ciel-et-mer',
46 'title': 'Les yeux dans les cieux - Mon homard au Canada',
47 'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
48 'uploader': 'Passe-moi les jumelles',
49 'upload_date': '20140404',
50 'timestamp': 1396635300,
51 'thumbnail': 're:^https?://.*\.image',
56 'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
57 'md5': 'b4326fecd3eb64a458ba73c73e91299d',
60 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
63 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
64 'description': 'Hockey - Playoff',
66 'upload_date': '20140403',
67 'timestamp': 1396556882,
68 'thumbnail': 're:^https?://.*\.image',
71 'skip': 'Blocked outside Switzerland',
74 'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
75 'md5': '9bb06503773c07ce83d3cbd793cebb91',
78 'display_id': 'londres-cachee-par-un-epais-smog',
81 'title': 'Londres cachée par un épais smog',
82 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
83 'uploader': 'Le Journal en continu',
84 'upload_date': '20140403',
85 'timestamp': 1396537322,
86 'thumbnail': 're:^https?://.*\.image',
91 'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
92 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
95 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
98 'title': '"Urban Hippie", de Damien Krisl',
99 'description': 'Des Hippies super glam.',
100 'upload_date': '20140403',
101 'timestamp': 1396551600,
105 'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
106 'md5': '968777c8779e5aa2434be96c54e19743',
109 'display_id': 'le-19h30',
114 'uploader': 'Le 19h30',
115 'upload_date': '20141201',
116 'timestamp': 1417458600,
117 'thumbnail': 're:^https?://.*\.image',
122 'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280',
123 'only_matching': True,
127 def _real_extract(self, url):
128 m = re.match(self._VALID_URL, url)
129 video_id = m.group('id') or m.group('id_new')
130 display_id = m.group('display_id') or m.group('display_id_new')
132 def download_json(internal_id):
133 return self._download_json(
134 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
137 all_info = download_json(video_id)
139 # video_id extracted out of URL is not always a real id
140 if 'video' not in all_info and 'audio' not in all_info:
141 page = self._download_webpage(url, display_id)
142 internal_id = self._html_search_regex(
143 r'<(?:video|audio) data-id="([0-9]+)"', page,
145 all_info = download_json(internal_id)
147 info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
149 upload_timestamp = parse_iso8601(info.get('broadcast_date'))
150 duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
151 if isinstance(duration, compat_str):
152 duration = parse_duration(duration)
153 view_count = info.get('plays')
154 thumbnail = unescapeHTML(info.get('preview_image_url'))
156 def extract_bitrate(url):
157 return int_or_none(self._search_regex(
158 r'-([0-9]+)k\.', url, 'bitrate', default=None))
163 'tbr': extract_bitrate(furl),
164 } for fid, furl in info['streams'].items()]
168 'format_id': '%s-%sk' % (media['ext'], media['rate']),
169 'url': 'http://download-video.rts.ch/%s' % media['url'],
170 'tbr': media['rate'] or extract_bitrate(media['url']),
171 } for media in info['media'] if media.get('rate')])
173 self._sort_formats(formats)
177 'display_id': display_id,
179 'title': info['title'],
180 'description': info.get('intro'),
181 'duration': duration,
182 'view_count': view_count,
183 'uploader': info.get('programName'),
184 'timestamp': upload_timestamp,
185 'thumbnail': thumbnail,