yt_dlp/extractor/ruutu.py

   1 import json
   2 import re
   3 import urllib.parse
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     determine_ext,
   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$',
  39                 'duration': 114,
  40                 'age_limit': 0,
  41                 'upload_date': '20150508',
  42             },
  43         },
  44         {
  45             'url': 'http://www.ruutu.fi/video/2057306',
  46             'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
  47             'info_dict': {
  48                 'id': '2057306',
  49                 'ext': 'mp4',
  50                 'title': 'Superpesis: katso koko kausi Ruudussa',
  51                 'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
  52                 'thumbnail': r're:^https?://.*\.jpg$',
  53                 'duration': 40,
  54                 'age_limit': 0,
  55                 'upload_date': '20150507',
  56                 'series': 'Superpesis',
  57                 'categories': ['Urheilu'],
  58             },
  59         },
  60         {
  61             'url': 'http://www.supla.fi/supla/2231370',
  62             'md5': 'df14e782d49a2c0df03d3be2a54ef949',
  63             'info_dict': {
  64                 'id': '2231370',
  65                 'ext': 'mp4',
  66                 'title': 'Osa 1: Mikael Jungner',
  67                 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
  68                 'thumbnail': r're:^https?://.*\.jpg$',
  69                 'age_limit': 0,
  70                 'upload_date': '20151012',
  71                 'series': 'Läpivalaisu',
  72             },
  73         },
  74         # Episode where <SourceFile> is "NOT-USED", but has other
  75         # downloadable sources available.
  76         {
  77             'url': 'http://www.ruutu.fi/video/3193728',
  78             'only_matching': True,
  79         },
  80         {
  81             # audio podcast
  82             'url': 'https://www.supla.fi/supla/3382410',
  83             'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
  84             'info_dict': {
  85                 'id': '3382410',
  86                 'ext': 'mp3',
  87                 'title': 'Mikä ihmeen poltergeist?',
  88                 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
  89                 'thumbnail': r're:^https?://.*\.jpg$',
  90                 'age_limit': 0,
  91                 'upload_date': '20190320',
  92                 'series': 'Mysteeritarinat',
  93                 'duration': 1324,
  94             },
  95             'expected_warnings': [
  96                 'HTTP Error 502: Bad Gateway',
  97                 'Failed to download m3u8 information',
  98             ],
  99         },
 100         {
 101             'url': 'http://www.supla.fi/audio/2231370',
 102             'only_matching': True,
 103         },
 104         {
 105             'url': 'https://static.nelonenmedia.fi/player/misc/embed_player.html?nid=3618790',
 106             'only_matching': True,
 107         },
 108         {
 109             # episode
 110             'url': 'https://www.ruutu.fi/video/3401964',
 111             'info_dict': {
 112                 'id': '3401964',
 113                 'ext': 'mp4',
 114                 'title': 'Temptation Island Suomi - Kausi 5 - Jakso 17',
 115                 'description': 'md5:87cf01d5e1e88adf0c8a2937d2bd42ba',
 116                 'thumbnail': r're:^https?://.*\.jpg$',
 117                 'duration': 2582,
 118                 'age_limit': 12,
 119                 'upload_date': '20190508',
 120                 'series': 'Temptation Island Suomi',
 121                 'season_number': 5,
 122                 'episode_number': 17,
 123                 'categories': ['Reality ja tositapahtumat', 'Kotimaiset suosikit', 'Romantiikka ja parisuhde'],
 124             },
 125             'params': {
 126                 'skip_download': True,
 127             },
 128         },
 129         {
 130             # premium
 131             'url': 'https://www.ruutu.fi/video/3618715',
 132             'only_matching': True,
 133         },
 134     ]
 135     _API_BASE = 'https://gatling.nelonenmedia.fi'
 136
 137     @classmethod
 138     def _extract_embed_urls(cls, url, webpage):
 139         # nelonen.fi
 140         settings = try_call(
 141             lambda: json.loads(re.search(
 142                 r'jQuery\.extend\(Drupal\.settings, ({.+?})\);', webpage).group(1), strict=False))
 143         if settings:
 144             video_id = traverse_obj(settings, (
 145                 'mediaCrossbowSettings', 'file', 'field_crossbow_video_id', 'und', 0, 'value'))
 146             if video_id:
 147                 return [f'http://www.ruutu.fi/video/{video_id}']
 148         # hs.fi and is.fi
 149         settings = try_call(
 150             lambda: json.loads(re.search(
 151                 '(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
 152                 webpage).group(1), strict=False))
 153         if settings:
 154             video_ids = set(traverse_obj(settings, (
 155                 'props', 'pageProps', 'page', 'assetData', 'splitBody', ..., 'video', 'sourceId')) or [])
 156             if video_ids:
 157                 return [f'http://www.ruutu.fi/video/{v}' for v in video_ids]
 158             video_id = traverse_obj(settings, (
 159                 'props', 'pageProps', 'page', 'assetData', 'mainVideo', 'sourceId'))
 160             if video_id:
 161                 return [f'http://www.ruutu.fi/video/{video_id}']
 162
 163     def _real_extract(self, url):
 164         video_id = self._match_id(url)
 165
 166         video_xml = self._download_xml(
 167             f'{self._API_BASE}/media-xml-cache', video_id,
 168             query={'id': video_id})
 169
 170         formats = []
 171         processed_urls = []
 172
 173         def extract_formats(node):
 174             for child in node:
 175                 if child.tag.endswith('Files'):
 176                     extract_formats(child)
 177                 elif child.tag.endswith('File'):
 178                     video_url = child.text
 179                     if (not video_url or video_url in processed_urls
 180                             or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
 181                         continue
 182                     processed_urls.append(video_url)
 183                     ext = determine_ext(video_url)
 184                     auth_video_url = url_or_none(self._download_webpage(
 185                         f'{self._API_BASE}/auth/access/v2', video_id,
 186                         note=f'Downloading authenticated {ext} stream URL',
 187                         fatal=False, query={'stream': video_url}))
 188                     if auth_video_url:
 189                         processed_urls.append(auth_video_url)
 190                         video_url = auth_video_url
 191                     if ext == 'm3u8':
 192                         formats.extend(self._extract_m3u8_formats(
 193                             video_url, video_id, 'mp4',
 194                             entry_protocol='m3u8_native', m3u8_id='hls',
 195                             fatal=False))
 196                     elif ext == 'f4m':
 197                         formats.extend(self._extract_f4m_formats(
 198                             video_url, video_id, f4m_id='hds', fatal=False))
 199                     elif ext == 'mpd':
 200                         # video-only and audio-only streams are of different
 201                         # duration resulting in out of sync issue
 202                         continue
 203                         formats.extend(self._extract_mpd_formats(
 204                             video_url, video_id, mpd_id='dash', fatal=False))
 205                     elif ext == 'mp3' or child.tag == 'AudioMediaFile':
 206                         formats.append({
 207                             'format_id': 'audio',
 208                             'url': video_url,
 209                             'vcodec': 'none',
 210                         })
 211                     else:
 212                         proto = urllib.parse.urlparse(video_url).scheme
 213                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
 214                             continue
 215                         preference = -1 if proto == 'rtmp' else 1
 216                         label = child.get('label')
 217                         tbr = int_or_none(child.get('bitrate'))
 218                         format_id = f'{proto}-{label if label else tbr}' if label or tbr else proto
 219                         if not self._is_valid_url(video_url, video_id, format_id):
 220                             continue
 221                         width, height = (int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2])
 222                         formats.append({
 223                             'format_id': format_id,
 224                             'url': video_url,
 225                             'width': width,
 226                             'height': height,
 227                             'tbr': tbr,
 228                             'preference': preference,
 229                         })
 230
 231         extract_formats(video_xml.find('./Clip'))
 232
 233         def pv(name):
 234             value = try_call(lambda: find_xpath_attr(
 235                 video_xml, './Clip/PassthroughVariables/variable', 'name', name).get('value'))
 236             if value != 'NA':
 237                 return value or None
 238
 239         if not formats:
 240             if (not self.get_param('allow_unplayable_formats')
 241                     and xpath_text(video_xml, './Clip/DRM', default=None)):
 242                 self.report_drm(video_id)
 243             ns_st_cds = pv('ns_st_cds')
 244             if ns_st_cds != 'free':
 245                 raise ExtractorError(f'This video is {ns_st_cds}.', expected=True)
 246
 247         themes = pv('themes')
 248
 249         return {
 250             'id': video_id,
 251             'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
 252             'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
 253             'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
 254             'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')) or int_or_none(pv('runtime')),
 255             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
 256             'upload_date': unified_strdate(pv('date_start')),
 257             'series': pv('series_name'),
 258             'season_number': int_or_none(pv('season_number')),
 259             'episode_number': int_or_none(pv('episode_number')),
 260             'categories': themes.split(',') if themes else None,
 261             'formats': formats,
 262         }