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$',
  53                 'age_limit': 0,
  54             },
  55         },
  56         # Episode where <SourceFile> is "NOT-USED", but has other
  57         # downloadable sources available.
  58         {
  59             'url': 'http://www.ruutu.fi/video/3193728',
  60             'only_matching': True,
  61         },
  62         {
  63             # audio podcast
  64             'url': 'https://www.supla.fi/supla/3382410',
  65             'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
  66             'info_dict': {
  67                 'id': '3382410',
  68                 'ext': 'mp3',
  69                 'title': 'Mikä ihmeen poltergeist?',
  70                 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
  71                 'thumbnail': r're:^https?://.*\.jpg$',
  72                 'age_limit': 0,
  73             },
  74             'expected_warnings': ['HTTP Error 502: Bad Gateway'],
  75         }
  76     ]
  77
  78     def _real_extract(self, url):
  79         video_id = self._match_id(url)
  80
  81         video_xml = self._download_xml(
  82             'https://gatling.nelonenmedia.fi/media-xml-cache', video_id,
  83             query={'id': video_id})
  84
  85         formats = []
  86         processed_urls = []
  87
  88         def extract_formats(node):
  89             for child in node:
  90                 if child.tag.endswith('Files'):
  91                     extract_formats(child)
  92                 elif child.tag.endswith('File'):
  93                     video_url = child.text
  94                     if (not video_url or video_url in processed_urls
  95                             or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
  96                         continue
  97                     processed_urls.append(video_url)
  98                     ext = determine_ext(video_url)
  99                     if ext == 'm3u8':
 100                         formats.extend(self._extract_m3u8_formats(
 101                             video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
 102                     elif ext == 'f4m':
 103                         formats.extend(self._extract_f4m_formats(
 104                             video_url, video_id, f4m_id='hds', fatal=False))
 105                     elif ext == 'mpd':
 106                         # video-only and audio-only streams are of different
 107                         # duration resulting in out of sync issue
 108                         continue
 109                         formats.extend(self._extract_mpd_formats(
 110                             video_url, video_id, mpd_id='dash', fatal=False))
 111                     elif ext == 'mp3' or child.tag == 'AudioMediaFile':
 112                         formats.append({
 113                             'format_id': 'audio',
 114                             'url': video_url,
 115                             'vcodec': 'none',
 116                         })
 117                     else:
 118                         proto = compat_urllib_parse_urlparse(video_url).scheme
 119                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
 120                             continue
 121                         preference = -1 if proto == 'rtmp' else 1
 122                         label = child.get('label')
 123                         tbr = int_or_none(child.get('bitrate'))
 124                         format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
 125                         if not self._is_valid_url(video_url, video_id, format_id):
 126                             continue
 127                         width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
 128                         formats.append({
 129                             'format_id': format_id,
 130                             'url': video_url,
 131                             'width': width,
 132                             'height': height,
 133                             'tbr': tbr,
 134                             'preference': preference,
 135                         })
 136
 137         extract_formats(video_xml.find('./Clip'))
 138
 139         drm = xpath_text(video_xml, './Clip/DRM', default=None)
 140         if not formats and drm:
 141             raise ExtractorError('This video is DRM protected.', expected=True)
 142
 143         self._sort_formats(formats)
 144
 145         return {
 146             'id': video_id,
 147             'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
 148             'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
 149             'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
 150             'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
 151             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
 152             'formats': formats,
 153         }