yt_dlp/extractor/ruutu.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_urlparse
   6 from ..utils import (
   7     determine_ext,
   8     ExtractorError,
   9     find_xpath_attr,
  10     int_or_none,
  11     traverse_obj,
  12     try_call,
  13     unified_strdate,
  14     url_or_none,
  15     xpath_attr,
  16     xpath_text,
  17 )
  18
  19
  20 class RuutuIE(InfoExtractor):
  21     _VALID_URL = r'''(?x)
  22                     https?://
  23                         (?:
  24                             (?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla|audio)/|
  25                             static\.nelonenmedia\.fi/player/misc/embed_player\.html\?.*?\bnid=
  26                         )
  27                         (?P<id>\d+)
  28                     '''
  29     _TESTS = [
  30         {
  31             'url': 'http://www.ruutu.fi/video/2058907',
  32             'md5': 'ab2093f39be1ca8581963451b3c0234f',
  33             'info_dict': {
  34                 'id': '2058907',
  35                 'ext': 'mp4',
  36                 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
  37                 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
  38                 'thumbnail': r're:^https?://.*\.jpg$',
  39                 'duration': 114,
  40                 'age_limit': 0,
  41             },
  42         },
  43         {
  44             'url': 'http://www.ruutu.fi/video/2057306',
  45             'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
  46             'info_dict': {
  47                 'id': '2057306',
  48                 'ext': 'mp4',
  49                 'title': 'Superpesis: katso koko kausi Ruudussa',
  50                 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
  51                 'thumbnail': r're:^https?://.*\.jpg$',
  52                 'duration': 40,
  53                 'age_limit': 0,
  54             },
  55         },
  56         {
  57             'url': 'http://www.supla.fi/supla/2231370',
  58             'md5': 'df14e782d49a2c0df03d3be2a54ef949',
  59             'info_dict': {
  60                 'id': '2231370',
  61                 'ext': 'mp4',
  62                 'title': 'Osa 1: Mikael Jungner',
  63                 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
  64                 'thumbnail': r're:^https?://.*\.jpg$',
  65                 'age_limit': 0,
  66             },
  67         },
  68         # Episode where <SourceFile> is "NOT-USED", but has other
  69         # downloadable sources available.
  70         {
  71             'url': 'http://www.ruutu.fi/video/3193728',
  72             'only_matching': True,
  73         },
  74         {
  75             # audio podcast
  76             'url': 'https://www.supla.fi/supla/3382410',
  77             'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
  78             'info_dict': {
  79                 'id': '3382410',
  80                 'ext': 'mp3',
  81                 'title': 'Mikä ihmeen poltergeist?',
  82                 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
  83                 'thumbnail': r're:^https?://.*\.jpg$',
  84                 'age_limit': 0,
  85             },
  86             'expected_warnings': [
  87                 'HTTP Error 502: Bad Gateway',
  88                 'Failed to download m3u8 information',
  89             ],
  90         },
  91         {
  92             'url': 'http://www.supla.fi/audio/2231370',
  93             'only_matching': True,
  94         },
  95         {
  96             'url': 'https://static.nelonenmedia.fi/player/misc/embed_player.html?nid=3618790',
  97             'only_matching': True,
  98         },
  99         {
 100             # episode
 101             'url': 'https://www.ruutu.fi/video/3401964',
 102             'info_dict': {
 103                 'id': '3401964',
 104                 'ext': 'mp4',
 105                 'title': 'Temptation Island Suomi - Kausi 5 - Jakso 17',
 106                 'description': 'md5:87cf01d5e1e88adf0c8a2937d2bd42ba',
 107                 'thumbnail': r're:^https?://.*\.jpg$',
 108                 'duration': 2582,
 109                 'age_limit': 12,
 110                 'upload_date': '20190508',
 111                 'series': 'Temptation Island Suomi',
 112                 'season_number': 5,
 113                 'episode_number': 17,
 114                 'categories': ['Reality ja tositapahtumat', 'Kotimaiset suosikit', 'Romantiikka ja parisuhde'],
 115             },
 116             'params': {
 117                 'skip_download': True,
 118             },
 119         },
 120         {
 121             # premium
 122             'url': 'https://www.ruutu.fi/video/3618715',
 123             'only_matching': True,
 124         },
 125     ]
 126     _API_BASE = 'https://gatling.nelonenmedia.fi'
 127
 128     @classmethod
 129     def _extract_url(cls, webpage):
 130         settings = try_call(
 131             lambda: json.loads(re.search(
 132                 r'jQuery\.extend\(Drupal\.settings, ({.+?})\);', webpage).group(1), strict=False))
 133         video_id = traverse_obj(settings, (
 134             'mediaCrossbowSettings', 'file', 'field_crossbow_video_id', 'und', 0, 'value'))
 135         if video_id:
 136             return f'http://www.ruutu.fi/video/{video_id}'
 137
 138     def _real_extract(self, url):
 139         video_id = self._match_id(url)
 140
 141         video_xml = self._download_xml(
 142             '%s/media-xml-cache' % self._API_BASE, video_id,
 143             query={'id': video_id})
 144
 145         formats = []
 146         processed_urls = []
 147
 148         def extract_formats(node):
 149             for child in node:
 150                 if child.tag.endswith('Files'):
 151                     extract_formats(child)
 152                 elif child.tag.endswith('File'):
 153                     video_url = child.text
 154                     if (not video_url or video_url in processed_urls
 155                             or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
 156                         continue
 157                     processed_urls.append(video_url)
 158                     ext = determine_ext(video_url)
 159                     auth_video_url = url_or_none(self._download_webpage(
 160                         '%s/auth/access/v2' % self._API_BASE, video_id,
 161                         note='Downloading authenticated %s stream URL' % ext,
 162                         fatal=False, query={'stream': video_url}))
 163                     if auth_video_url:
 164                         processed_urls.append(auth_video_url)
 165                         video_url = auth_video_url
 166                     if ext == 'm3u8':
 167                         formats.extend(self._extract_m3u8_formats(
 168                             video_url, video_id, 'mp4',
 169                             entry_protocol='m3u8_native', m3u8_id='hls',
 170                             fatal=False))
 171                     elif ext == 'f4m':
 172                         formats.extend(self._extract_f4m_formats(
 173                             video_url, video_id, f4m_id='hds', fatal=False))
 174                     elif ext == 'mpd':
 175                         # video-only and audio-only streams are of different
 176                         # duration resulting in out of sync issue
 177                         continue
 178                         formats.extend(self._extract_mpd_formats(
 179                             video_url, video_id, mpd_id='dash', fatal=False))
 180                     elif ext == 'mp3' or child.tag == 'AudioMediaFile':
 181                         formats.append({
 182                             'format_id': 'audio',
 183                             'url': video_url,
 184                             'vcodec': 'none',
 185                         })
 186                     else:
 187                         proto = compat_urllib_parse_urlparse(video_url).scheme
 188                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
 189                             continue
 190                         preference = -1 if proto == 'rtmp' else 1
 191                         label = child.get('label')
 192                         tbr = int_or_none(child.get('bitrate'))
 193                         format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
 194                         if not self._is_valid_url(video_url, video_id, format_id):
 195                             continue
 196                         width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
 197                         formats.append({
 198                             'format_id': format_id,
 199                             'url': video_url,
 200                             'width': width,
 201                             'height': height,
 202                             'tbr': tbr,
 203                             'preference': preference,
 204                         })
 205
 206         extract_formats(video_xml.find('./Clip'))
 207
 208         def pv(name):
 209             node = find_xpath_attr(
 210                 video_xml, './Clip/PassthroughVariables/variable', 'name', name)
 211             if node is not None:
 212                 return node.get('value')
 213
 214         if not formats:
 215             if (not self.get_param('allow_unplayable_formats')
 216                     and xpath_text(video_xml, './Clip/DRM', default=None)):
 217                 self.report_drm(video_id)
 218             ns_st_cds = pv('ns_st_cds')
 219             if ns_st_cds != 'free':
 220                 raise ExtractorError('This video is %s.' % ns_st_cds, expected=True)
 221
 222         self._sort_formats(formats)
 223
 224         themes = pv('themes')
 225
 226         return {
 227             'id': video_id,
 228             'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
 229             'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
 230             'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
 231             'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')) or int_or_none(pv('runtime')),
 232             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
 233             'upload_date': unified_strdate(pv('date_start')),
 234             'series': pv('series_name'),
 235             'season_number': int_or_none(pv('season_number')),
 236             'episode_number': int_or_none(pv('episode_number')),
 237             'categories': themes.split(',') if themes else [],
 238             'formats': formats,
 239         }