2 from __future__ import unicode_literals
4 from .common import InfoExtractor
5 from ..compat import compat_urllib_parse_urlparse
14 class RuutuIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P<id>\d+)'
18 'url': 'http://www.ruutu.fi/video/2058907',
19 'md5': 'ab2093f39be1ca8581963451b3c0234f',
23 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
24 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
25 'thumbnail': 're:^https?://.*\.jpg$',
31 'url': 'http://www.ruutu.fi/video/2057306',
32 'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
36 'title': 'Superpesis: katso koko kausi Ruudussa',
37 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
38 'thumbnail': 're:^https?://.*\.jpg$',
44 'url': 'http://www.supla.fi/supla/2231370',
45 'md5': 'df14e782d49a2c0df03d3be2a54ef949',
49 'title': 'Osa 1: Mikael Jungner',
50 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
51 'thumbnail': 're:^https?://.*\.jpg$',
57 def _real_extract(self, url):
58 video_id = self._match_id(url)
60 video_xml = self._download_xml(
61 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id)
66 def extract_formats(node):
68 if child.tag.endswith('Files'):
69 extract_formats(child)
70 elif child.tag.endswith('File'):
71 video_url = child.text
72 if (not video_url or video_url in processed_urls or
73 any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
75 processed_urls.append(video_url)
76 ext = determine_ext(video_url)
78 formats.extend(self._extract_m3u8_formats(
79 video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
81 formats.extend(self._extract_f4m_formats(
82 video_url, video_id, f4m_id='hds', fatal=False))
84 proto = compat_urllib_parse_urlparse(video_url).scheme
85 if not child.tag.startswith('HTTP') and proto != 'rtmp':
87 preference = -1 if proto == 'rtmp' else 1
88 label = child.get('label')
89 tbr = int_or_none(child.get('bitrate'))
90 format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
91 if not self._is_valid_url(video_url, video_id, format_id):
93 width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
95 'format_id': format_id,
100 'preference': preference,
103 extract_formats(video_xml.find('./Clip'))
104 self._sort_formats(formats)
108 'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
109 'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
110 'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
111 'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
112 'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),