]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/rts.py
2 from __future__
import unicode_literals
6 from .srgssr
import SRGSSRIE
7 from ..compat
import compat_str
18 class RTSIE(SRGSSRIE
):
20 _VALID_URL
= r
'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
24 'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
25 'md5': '753b877968ad8afaeddccc374d4256a5',
28 'display_id': 'les-enfants-terribles',
31 'title': 'Les Enfants Terribles',
32 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
34 'upload_date': '19680921',
35 'timestamp': -40280400,
36 'thumbnail': r
're:^https?://.*\.image',
39 'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
42 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
45 'title': 'Passe-moi les jumelles',
47 'playlist_mincount': 4,
50 'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
53 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
56 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
57 'description': 'Hockey - Playoff',
59 'upload_date': '20140403',
60 'timestamp': 1396556882,
61 'thumbnail': r
're:^https?://.*\.image',
66 'skip_download': True,
68 'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
69 'skip': 'Blocked outside Switzerland',
72 'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
73 'md5': '9bb06503773c07ce83d3cbd793cebb91',
76 'display_id': 'londres-cachee-par-un-epais-smog',
79 'title': 'Londres cachée par un épais smog',
80 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
81 'uploader': 'L\'actu en vidéo',
82 'upload_date': '20140403',
83 'timestamp': 1396537322,
84 'thumbnail': r
're:^https?://.*\.image',
87 'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
90 'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
91 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
94 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
97 'title': '"Urban Hippie", de Damien Krisl',
98 'description': 'Des Hippies super glam.',
99 'upload_date': '20140403',
100 'timestamp': 1396551600,
104 # article with videos on rhs
105 'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
108 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
110 'playlist_mincount': 5,
113 'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',
114 'only_matching': True,
118 def _real_extract(self
, url
):
119 m
= self
._match
_valid
_url
(url
)
120 media_id
= m
.group('rts_id') or m
.group('id')
121 display_id
= m
.group('display_id') or media_id
123 def download_json(internal_id
):
124 return self
._download
_json
(
125 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id
,
128 all_info
= download_json(media_id
)
130 # media_id extracted out of URL is not always a real id
131 if 'video' not in all_info
and 'audio' not in all_info
:
134 for item
in all_info
.get('items', []):
135 item_url
= item
.get('url')
138 entries
.append(self
.url_result(item_url
, 'RTS'))
141 page
, urlh
= self
._download
_webpage
_handle
(url
, display_id
)
142 if re
.match(self
._VALID
_URL
, urlh
.geturl()).group('id') != media_id
:
143 return self
.url_result(urlh
.geturl(), 'RTS')
145 # article with videos on rhs
147 r
'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
151 r
'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
154 entries
= [self
.url_result('srgssr:%s' % video_urn
, 'SRGSSR') for video_urn
in videos
]
157 return self
.playlist_result(entries
, media_id
, all_info
.get('title'))
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 title
= info
['title']
173 def extract_bitrate(url
):
174 return int_or_none(self
._search
_regex
(
175 r
'-([0-9]+)k\.', url
, 'bitrate', default
=None))
178 streams
= info
.get('streams', {})
179 for format_id
, format_url
in streams
.items():
180 if format_id
== 'hds_sd' and 'hds' in streams
:
182 if format_id
== 'hls_sd' and 'hls' in streams
:
184 ext
= determine_ext(format_url
)
185 if ext
in ('m3u8', 'f4m'):
186 format_url
= self
._get
_tokenized
_src
(format_url
, media_id
, format_id
)
188 formats
.extend(self
._extract
_f
4m
_formats
(
189 format_url
+ ('?' if '?' not in format_url
else '&') + 'hdcore=3.4.0',
190 media_id
, f4m_id
=format_id
, fatal
=False))
192 formats
.extend(self
._extract
_m
3u8_formats
(
193 format_url
, media_id
, 'mp4', 'm3u8_native', m3u8_id
=format_id
, fatal
=False))
196 'format_id': format_id
,
198 'tbr': extract_bitrate(format_url
),
201 download_base
= 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type
== 'audio' else '')
202 for media
in info
.get('media', []):
203 media_url
= media
.get('url')
204 if not media_url
or re
.match(r
'https?://', media_url
):
206 rate
= media
.get('rate')
207 ext
= media
.get('ext') or determine_ext(media_url
, 'mp4')
210 format_id
+= '-%dk' % rate
212 'format_id': format_id
,
213 'url': urljoin(download_base
, media_url
),
214 'tbr': rate
or extract_bitrate(media_url
),
217 self
._check
_formats
(formats
, media_id
)
218 self
._sort
_formats
(formats
)
220 duration
= info
.get('duration') or info
.get('cutout') or info
.get('cutduration')
221 if isinstance(duration
, compat_str
):
222 duration
= parse_duration(duration
)
226 'display_id': display_id
,
229 'description': info
.get('intro'),
230 'duration': duration
,
231 'view_count': int_or_none(info
.get('plays')),
232 'uploader': info
.get('programName'),
233 'timestamp': parse_iso8601(info
.get('broadcast_date')),
234 'thumbnail': unescapeHTML(info
.get('preview_image_url')),