Raphaël G. Git Repositories - youtubedl/blob - 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     ExtractorError,
   9     int_or_none,
  10     xpath_attr,
  11     xpath_text,
  12 )
  13
  14
  15 class RuutuIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P<id>\d+)'
  17     _TESTS = [
  18         {
  19             'url': 'http://www.ruutu.fi/video/2058907',
  20             'md5': 'ab2093f39be1ca8581963451b3c0234f',
  21             'info_dict': {
  22                 'id': '2058907',
  23                 'ext': 'mp4',
  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$',
  27                 'duration': 114,
  28                 'age_limit': 0,
  29             },
  30         },
  31         {
  32             'url': 'http://www.ruutu.fi/video/2057306',
  33             'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
  34             'info_dict': {
  35                 'id': '2057306',
  36                 'ext': 'mp4',
  37                 'title': 'Superpesis: katso koko kausi Ruudussa',
  38                 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
  39                 'thumbnail': r're:^https?://.*\.jpg$',
  40                 'duration': 40,
  41                 'age_limit': 0,
  42             },
  43         },
  44         {
  45             'url': 'http://www.supla.fi/supla/2231370',
  46             'md5': 'df14e782d49a2c0df03d3be2a54ef949',
  47             'info_dict': {
  48                 'id': '2231370',
  49                 'ext': 'mp4',
  50                 'title': 'Osa 1: Mikael Jungner',
  51                 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
  52                 'thumbnail': r're:^https?://.*\.jpg$',
  53                 'age_limit': 0,
  54             },
  55         },
  56         # Episode where <SourceFile> is "NOT-USED", but has other
  57         # downloadable sources available.
  58         {
  59             'url': 'http://www.ruutu.fi/video/3193728',
  60             'only_matching': True,
  61         },
  62     ]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66
  67         video_xml = self._download_xml(
  68             'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id)
  69
  70         formats = []
  71         processed_urls = []
  72
  73         def extract_formats(node):
  74             for child in node:
  75                 if child.tag.endswith('Files'):
  76                     extract_formats(child)
  77                 elif child.tag.endswith('File'):
  78                     video_url = child.text
  79                     if (not video_url or video_url in processed_urls or
  80                             any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
  81                         continue
  82                     processed_urls.append(video_url)
  83                     ext = determine_ext(video_url)
  84                     if ext == 'm3u8':
  85                         formats.extend(self._extract_m3u8_formats(
  86                             video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  87                     elif ext == 'f4m':
  88                         formats.extend(self._extract_f4m_formats(
  89                             video_url, video_id, f4m_id='hds', fatal=False))
  90                     elif ext == 'mpd':
  91                         # video-only and audio-only streams are of different
  92                         # duration resulting in out of sync issue
  93                         continue
  94                         formats.extend(self._extract_mpd_formats(
  95                             video_url, video_id, mpd_id='dash', fatal=False))
  96                     else:
  97                         proto = compat_urllib_parse_urlparse(video_url).scheme
  98                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
  99                             continue
 100                         preference = -1 if proto == 'rtmp' else 1
 101                         label = child.get('label')
 102                         tbr = int_or_none(child.get('bitrate'))
 103                         format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
 104                         if not self._is_valid_url(video_url, video_id, format_id):
 105                             continue
 106                         width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
 107                         formats.append({
 108                             'format_id': format_id,
 109                             'url': video_url,
 110                             'width': width,
 111                             'height': height,
 112                             'tbr': tbr,
 113                             'preference': preference,
 114                         })
 115
 116         extract_formats(video_xml.find('./Clip'))
 117
 118         drm = xpath_text(video_xml, './Clip/DRM', default=None)
 119         if not formats and drm:
 120             raise ExtractorError('This video is DRM protected.', expected=True)
 121
 122         self._sort_formats(formats)
 123
 124         return {
 125             'id': video_id,
 126             'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
 127             'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
 128             'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
 129             'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
 130             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
 131             'formats': formats,
 132         }