2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
5 from ..compat
import compat_urllib_parse_urlparse
15 class RuutuIE(InfoExtractor
):
16 _VALID_URL
= r
'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P<id>\d+)'
19 'url': 'http://www.ruutu.fi/video/2058907',
20 'md5': 'ab2093f39be1ca8581963451b3c0234f',
24 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
25 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
26 'thumbnail': r
're:^https?://.*\.jpg$',
32 'url': 'http://www.ruutu.fi/video/2057306',
33 'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
37 'title': 'Superpesis: katso koko kausi Ruudussa',
38 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
39 'thumbnail': r
're:^https?://.*\.jpg$',
45 'url': 'http://www.supla.fi/supla/2231370',
46 'md5': 'df14e782d49a2c0df03d3be2a54ef949',
50 'title': 'Osa 1: Mikael Jungner',
51 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
52 'thumbnail': r
're:^https?://.*\.jpg$',
56 # Episode where <SourceFile> is "NOT-USED", but has other
57 # downloadable sources available.
59 'url': 'http://www.ruutu.fi/video/3193728',
60 'only_matching': True,
64 def _real_extract(self
, url
):
65 video_id
= self
._match
_id
(url
)
67 video_xml
= self
._download
_xml
(
68 'https://gatling.nelonenmedia.fi/media-xml-cache', video_id
,
69 query
={'id': video_id
})
74 def extract_formats(node
):
76 if child
.tag
.endswith('Files'):
77 extract_formats(child
)
78 elif child
.tag
.endswith('File'):
79 video_url
= child
.text
80 if (not video_url
or video_url
in processed_urls
or
81 any(p
in video_url
for p
in ('NOT_USED', 'NOT-USED'))):
83 processed_urls
.append(video_url
)
84 ext
= determine_ext(video_url
)
86 formats
.extend(self
._extract
_m
3u8_formats
(
87 video_url
, video_id
, 'mp4', m3u8_id
='hls', fatal
=False))
89 formats
.extend(self
._extract
_f
4m
_formats
(
90 video_url
, video_id
, f4m_id
='hds', fatal
=False))
92 # video-only and audio-only streams are of different
93 # duration resulting in out of sync issue
95 formats
.extend(self
._extract
_mpd
_formats
(
96 video_url
, video_id
, mpd_id
='dash', fatal
=False))
98 proto
= compat_urllib_parse_urlparse(video_url
).scheme
99 if not child
.tag
.startswith('HTTP') and proto
!= 'rtmp':
101 preference
= -1 if proto
== 'rtmp' else 1
102 label
= child
.get('label')
103 tbr
= int_or_none(child
.get('bitrate'))
104 format_id
= '%s-%s' % (proto
, label
if label
else tbr
) if label
or tbr
else proto
105 if not self
._is
_valid
_url
(video_url
, video_id
, format_id
):
107 width
, height
= [int_or_none(x
) for x
in child
.get('resolution', 'x').split('x')[:2]]
109 'format_id': format_id
,
114 'preference': preference
,
117 extract_formats(video_xml
.find('./Clip'))
119 drm
= xpath_text(video_xml
, './Clip/DRM', default
=None)
120 if not formats
and drm
:
121 raise ExtractorError('This video is DRM protected.', expected
=True)
123 self
._sort
_formats
(formats
)
127 'title': xpath_attr(video_xml
, './/Behavior/Program', 'program_name', 'title', fatal
=True),
128 'description': xpath_attr(video_xml
, './/Behavior/Program', 'description', 'description'),
129 'thumbnail': xpath_attr(video_xml
, './/Behavior/Startpicture', 'href', 'thumbnail'),
130 'duration': int_or_none(xpath_text(video_xml
, './/Runtime', 'duration')),
131 'age_limit': int_or_none(xpath_text(video_xml
, './/AgeLimit', 'age limit')),