2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
8 from ..compat
import compat_urllib_parse_urlparse
23 class RuutuIE(InfoExtractor
):
27 (?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla|audio)/|
28 static\.nelonenmedia\.fi/player/misc/embed_player\.html\?.*?\bnid=
34 'url': 'http://www.ruutu.fi/video/2058907',
35 'md5': 'ab2093f39be1ca8581963451b3c0234f',
39 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
40 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
41 'thumbnail': r
're:^https?://.*\.jpg$',
47 'url': 'http://www.ruutu.fi/video/2057306',
48 'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
52 'title': 'Superpesis: katso koko kausi Ruudussa',
53 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
54 'thumbnail': r
're:^https?://.*\.jpg$',
60 'url': 'http://www.supla.fi/supla/2231370',
61 'md5': 'df14e782d49a2c0df03d3be2a54ef949',
65 'title': 'Osa 1: Mikael Jungner',
66 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
67 'thumbnail': r
're:^https?://.*\.jpg$',
71 # Episode where <SourceFile> is "NOT-USED", but has other
72 # downloadable sources available.
74 'url': 'http://www.ruutu.fi/video/3193728',
75 'only_matching': True,
79 'url': 'https://www.supla.fi/supla/3382410',
80 'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
84 'title': 'Mikä ihmeen poltergeist?',
85 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
86 'thumbnail': r
're:^https?://.*\.jpg$',
89 'expected_warnings': [
90 'HTTP Error 502: Bad Gateway',
91 'Failed to download m3u8 information',
95 'url': 'http://www.supla.fi/audio/2231370',
96 'only_matching': True,
99 'url': 'https://static.nelonenmedia.fi/player/misc/embed_player.html?nid=3618790',
100 'only_matching': True,
104 'url': 'https://www.ruutu.fi/video/3401964',
108 'title': 'Temptation Island Suomi - Kausi 5 - Jakso 17',
109 'description': 'md5:87cf01d5e1e88adf0c8a2937d2bd42ba',
110 'thumbnail': r
're:^https?://.*\.jpg$',
113 'upload_date': '20190508',
114 'series': 'Temptation Island Suomi',
116 'episode_number': 17,
117 'categories': ['Reality ja tositapahtumat', 'Kotimaiset suosikit', 'Romantiikka ja parisuhde'],
120 'skip_download': True,
125 'url': 'https://www.ruutu.fi/video/3618715',
126 'only_matching': True,
129 _API_BASE
= 'https://gatling.nelonenmedia.fi'
132 def _extract_url(cls
, webpage
):
134 lambda: json
.loads(re
.search(
135 r
'jQuery\.extend\(Drupal\.settings, ({.+?})\);', webpage
).group(1), strict
=False))
136 video_id
= traverse_obj(settings
, (
137 'mediaCrossbowSettings', 'file', 'field_crossbow_video_id', 'und', 0, 'value'))
139 return f
'http://www.ruutu.fi/video/{video_id}'
141 def _real_extract(self
, url
):
142 video_id
= self
._match
_id
(url
)
144 video_xml
= self
._download
_xml
(
145 '%s/media-xml-cache' % self
._API
_BASE
, video_id
,
146 query
={'id': video_id}
)
151 def extract_formats(node
):
153 if child
.tag
.endswith('Files'):
154 extract_formats(child
)
155 elif child
.tag
.endswith('File'):
156 video_url
= child
.text
157 if (not video_url
or video_url
in processed_urls
158 or any(p
in video_url
for p
in ('NOT_USED', 'NOT-USED'))):
160 processed_urls
.append(video_url
)
161 ext
= determine_ext(video_url
)
162 auth_video_url
= url_or_none(self
._download
_webpage
(
163 '%s/auth/access/v2' % self
._API
_BASE
, video_id
,
164 note
='Downloading authenticated %s stream URL' % ext
,
165 fatal
=False, query
={'stream': video_url}
))
167 processed_urls
.append(auth_video_url
)
168 video_url
= auth_video_url
170 formats
.extend(self
._extract
_m
3u8_formats
(
171 video_url
, video_id
, 'mp4',
172 entry_protocol
='m3u8_native', m3u8_id
='hls',
175 formats
.extend(self
._extract
_f
4m
_formats
(
176 video_url
, video_id
, f4m_id
='hds', fatal
=False))
178 # video-only and audio-only streams are of different
179 # duration resulting in out of sync issue
181 formats
.extend(self
._extract
_mpd
_formats
(
182 video_url
, video_id
, mpd_id
='dash', fatal
=False))
183 elif ext
== 'mp3' or child
.tag
== 'AudioMediaFile':
185 'format_id': 'audio',
190 proto
= compat_urllib_parse_urlparse(video_url
).scheme
191 if not child
.tag
.startswith('HTTP') and proto
!= 'rtmp':
193 preference
= -1 if proto
== 'rtmp' else 1
194 label
= child
.get('label')
195 tbr
= int_or_none(child
.get('bitrate'))
196 format_id
= '%s-%s' % (proto
, label
if label
else tbr
) if label
or tbr
else proto
197 if not self
._is
_valid
_url
(video_url
, video_id
, format_id
):
199 width
, height
= [int_or_none(x
) for x
in child
.get('resolution', 'x').split('x')[:2]]
201 'format_id': format_id
,
206 'preference': preference
,
209 extract_formats(video_xml
.find('./Clip'))
212 node
= find_xpath_attr(
213 video_xml
, './Clip/PassthroughVariables/variable', 'name', name
)
215 return node
.get('value')
218 if (not self
.get_param('allow_unplayable_formats')
219 and xpath_text(video_xml
, './Clip/DRM', default
=None)):
220 self
.report_drm(video_id
)
221 ns_st_cds
= pv('ns_st_cds')
222 if ns_st_cds
!= 'free':
223 raise ExtractorError('This video is %s.' % ns_st_cds
, expected
=True)
225 self
._sort
_formats
(formats
)
227 themes
= pv('themes')
231 'title': xpath_attr(video_xml
, './/Behavior/Program', 'program_name', 'title', fatal
=True),
232 'description': xpath_attr(video_xml
, './/Behavior/Program', 'description', 'description'),
233 'thumbnail': xpath_attr(video_xml
, './/Behavior/Startpicture', 'href', 'thumbnail'),
234 'duration': int_or_none(xpath_text(video_xml
, './/Runtime', 'duration')) or int_or_none(pv('runtime')),
235 'age_limit': int_or_none(xpath_text(video_xml
, './/AgeLimit', 'age limit')),
236 'upload_date': unified_strdate(pv('date_start')),
237 'series': pv('series_name'),
238 'season_number': int_or_none(pv('season_number')),
239 'episode_number': int_or_none(pv('episode_number')),
240 'categories': themes
.split(',') if themes
else [],