youtube_dl/extractor/ruutu.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_urlparse
   6 from ..utils import (
   7     determine_ext,
   8     int_or_none,
   9     xpath_attr,
  10     xpath_text,
  11 )
  12
  13
  14 class RuutuIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?ruutu\.fi/video/(?P<id>\d+)'
  16     _TESTS = [
  17         {
  18             'url': 'http://www.ruutu.fi/video/2058907',
  19             'md5': 'ab2093f39be1ca8581963451b3c0234f',
  20             'info_dict': {
  21                 'id': '2058907',
  22                 'ext': 'mp4',
  23                 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
  24                 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
  25                 'thumbnail': 're:^https?://.*\.jpg$',
  26                 'duration': 114,
  27                 'age_limit': 0,
  28             },
  29         },
  30         {
  31             'url': 'http://www.ruutu.fi/video/2057306',
  32             'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
  33             'info_dict': {
  34                 'id': '2057306',
  35                 'ext': 'mp4',
  36                 'title': 'Superpesis: katso koko kausi Ruudussa',
  37                 'description': 'md5:da2736052fef3b2bd5e0005e63c25eac',
  38                 'thumbnail': 're:^https?://.*\.jpg$',
  39                 'duration': 40,
  40                 'age_limit': 0,
  41             },
  42         },
  43     ]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47
  48         video_xml = self._download_xml(
  49             'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id)
  50
  51         formats = []
  52         processed_urls = []
  53
  54         def extract_formats(node):
  55             for child in node:
  56                 if child.tag.endswith('Files'):
  57                     extract_formats(child)
  58                 elif child.tag.endswith('File'):
  59                     video_url = child.text
  60                     if (not video_url or video_url in processed_urls or
  61                             any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
  62                         return
  63                     processed_urls.append(video_url)
  64                     ext = determine_ext(video_url)
  65                     if ext == 'm3u8':
  66                         formats.extend(self._extract_m3u8_formats(
  67                             video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  68                     elif ext == 'f4m':
  69                         formats.extend(self._extract_f4m_formats(
  70                             video_url, video_id, f4m_id='hds', fatal=False))
  71                     else:
  72                         proto = compat_urllib_parse_urlparse(video_url).scheme
  73                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
  74                             continue
  75                         preference = -1 if proto == 'rtmp' else 1
  76                         label = child.get('label')
  77                         tbr = int_or_none(child.get('bitrate'))
  78                         format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
  79                         if not self._is_valid_url(video_url, video_id, format_id):
  80                             continue
  81                         width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
  82                         formats.append({
  83                             'format_id': format_id,
  84                             'url': video_url,
  85                             'width': width,
  86                             'height': height,
  87                             'tbr': tbr,
  88                             'preference': preference,
  89                         })
  90
  91         extract_formats(video_xml.find('./Clip'))
  92         self._sort_formats(formats)
  93
  94         return {
  95             'id': video_id,
  96             'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
  97             'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
  98             'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
  99             'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
 100             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
 101             'formats': formats,
 102         }