yt_dlp/extractor/tv2.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..networking.exceptions import HTTPError
   5 from ..utils import (
   6     ExtractorError,
   7     determine_ext,
   8     float_or_none,
   9     int_or_none,
  10     js_to_json,
  11     parse_iso8601,
  12     remove_end,
  13     strip_or_none,
  14     try_get,
  15 )
  16
  17
  18 class TV2IE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?tv2\.no/v(?:ideo)?\d*/(?:[^?#]+/)*(?P<id>\d+)'
  20     _TESTS = [{
  21         'url': 'http://www.tv2.no/v/1791207/',
  22         'info_dict': {
  23             'id': '1791207',
  24             'ext': 'mp4',
  25             'title': 'Her kolliderer romsonden med asteroiden ',
  26             'description': 'En romsonde har krasjet inn i en asteroide i verdensrommet. Kollisjonen skjedde klokken 01:14 natt til tirsdag 27. september norsk tid. \n\nNasa kaller det sitt første forsøk på planetforsvar.',
  27             'timestamp': 1664238190,
  28             'upload_date': '20220927',
  29             'duration': 146,
  30             'thumbnail': r're:^https://.*$',
  31             'view_count': int,
  32             'categories': list,
  33         },
  34     }, {
  35         'url': 'http://www.tv2.no/v2/916509',
  36         'only_matching': True,
  37     }, {
  38         'url': 'https://www.tv2.no/video/nyhetene/her-kolliderer-romsonden-med-asteroiden/1791207/',
  39         'only_matching': True,
  40     }]
  41     _PROTOCOLS = ('HLS', 'DASH')
  42     _GEO_COUNTRIES = ['NO']
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         asset = self._download_json('https://sumo.tv2.no/rest/assets/' + video_id, video_id,
  47                                     'Downloading metadata JSON')
  48         title = asset['title']
  49         is_live = asset.get('live') is True
  50
  51         formats = []
  52         format_urls = []
  53         for protocol in self._PROTOCOLS:
  54             try:
  55                 data = self._download_json(f'https://api.sumo.tv2.no/play/{video_id}?stream={protocol}',
  56                                            video_id, 'Downloading playabck JSON',
  57                                            headers={'content-type': 'application/json'},
  58                                            data=b'{"device":{"id":"1-1-1","name":"Nettleser (HTML)"}}')['playback']
  59             except ExtractorError as e:
  60                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
  61                     error = self._parse_json(e.cause.response.read().decode(), video_id)['error']
  62                     error_code = error.get('code')
  63                     if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
  64                         self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
  65                     elif error_code == 'SESSION_NOT_AUTHENTICATED':
  66                         self.raise_login_required()
  67                     raise ExtractorError(error['description'])
  68                 raise
  69             items = data.get('streams', [])
  70             for item in items:
  71                 video_url = item.get('url')
  72                 if not video_url or video_url in format_urls:
  73                     continue
  74                 format_id = '{}-{}'.format(protocol.lower(), item.get('type'))
  75                 if not self._is_valid_url(video_url, video_id, format_id):
  76                     continue
  77                 format_urls.append(video_url)
  78                 ext = determine_ext(video_url)
  79                 if ext == 'f4m':
  80                     formats.extend(self._extract_f4m_formats(
  81                         video_url, video_id, f4m_id=format_id, fatal=False))
  82                 elif ext == 'm3u8':
  83                     if not data.get('drmProtected'):
  84                         formats.extend(self._extract_m3u8_formats(
  85                             video_url, video_id, 'mp4', live=is_live, m3u8_id=format_id, fatal=False))
  86                 elif ext == 'mpd':
  87                     formats.extend(self._extract_mpd_formats(
  88                         video_url, video_id, format_id, fatal=False))
  89                 elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
  90                     pass
  91                 else:
  92                     formats.append({
  93                         'url': video_url,
  94                         'format_id': format_id,
  95                     })
  96         if not formats and data.get('drmProtected'):
  97             self.report_drm(video_id)
  98
  99         thumbnails = [{
 100             'id': thumb_type,
 101             'url': thumb_url,
 102         } for thumb_type, thumb_url in (asset.get('images') or {}).items()]
 103
 104         return {
 105             'id': video_id,
 106             'url': video_url,
 107             'title': title,
 108             'description': strip_or_none(asset.get('description')),
 109             'thumbnails': thumbnails,
 110             'timestamp': parse_iso8601(asset.get('live_broadcast_time') or asset.get('update_time')),
 111             'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')),
 112             'view_count': int_or_none(asset.get('views')),
 113             'categories': asset.get('tags', '').split(','),
 114             'formats': formats,
 115             'is_live': is_live,
 116         }
 117
 118
 119 class TV2ArticleIE(InfoExtractor):
 120     _VALID_URL = r'https?://(?:www\.)?tv2\.no/(?!v(?:ideo)?\d*/)[^?#]+/(?P<id>\d+)'
 121     _TESTS = [{
 122         'url': 'https://www.tv2.no/underholdning/forraeder/katarina-flatland-angrer-etter-forraeder-exit/15095188/',
 123         'info_dict': {
 124             'id': '15095188',
 125             'title': 'Katarina Flatland angrer etter Forræder-exit',
 126             'description': 'SANDEFJORD (TV 2): Katarina Flatland (33) måtte følge i sine fars fotspor, da hun ble forvist fra Forræder.',
 127         },
 128         'playlist_count': 2,
 129     }, {
 130         'url': 'http://www.tv2.no/a/6930542',
 131         'only_matching': True,
 132     }]
 133
 134     def _real_extract(self, url):
 135         playlist_id = self._match_id(url)
 136
 137         webpage = self._download_webpage(url, playlist_id)
 138
 139         # Old embed pattern (looks unused nowadays)
 140         assets = re.findall(r'data-assetid=["\'](\d+)', webpage)
 141
 142         if not assets:
 143             # New embed pattern
 144             for v in re.findall(r'(?s)(?:TV2ContentboxVideo|TV2\.TV2Video)\(({.+?})\)', webpage):
 145                 video = self._parse_json(
 146                     v, playlist_id, transform_source=js_to_json, fatal=False)
 147                 if not video:
 148                     continue
 149                 asset = video.get('assetId')
 150                 if asset:
 151                     assets.append(asset)
 152
 153         entries = [
 154             self.url_result(f'http://www.tv2.no/v/{asset_id}', 'TV2')
 155             for asset_id in assets]
 156
 157         title = remove_end(self._og_search_title(webpage), ' - TV2.no')
 158         description = remove_end(self._og_search_description(webpage), ' - TV2.no')
 159
 160         return self.playlist_result(entries, playlist_id, title, description)
 161
 162
 163 class KatsomoIE(InfoExtractor):
 164     _WORKING = False
 165     _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
 166     _TESTS = [{
 167         'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
 168         'info_dict': {
 169             'id': '1181321',
 170             'ext': 'mp4',
 171             'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
 172             'description': 'Päätöksen teki Pelicansin hallitus.',
 173             'timestamp': 1575116484,
 174             'upload_date': '20191130',
 175             'duration': 37.12,
 176             'view_count': int,
 177             'categories': list,
 178         },
 179         'params': {
 180             # m3u8 download
 181             'skip_download': True,
 182         },
 183     }, {
 184         'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
 185         'only_matching': True,
 186     }, {
 187         'url': 'https://www.mtvuutiset.fi/video/prog1311159',
 188         'only_matching': True,
 189     }, {
 190         'url': 'https://www.katsomo.fi/#!/jakso/1311159',
 191         'only_matching': True,
 192     }]
 193     _API_DOMAIN = 'api.katsomo.fi'
 194     _PROTOCOLS = ('HLS', 'MPD')
 195     _GEO_COUNTRIES = ['FI']
 196
 197     def _real_extract(self, url):
 198         video_id = self._match_id(url)
 199         api_base = f'http://{self._API_DOMAIN}/api/web/asset/{video_id}'
 200
 201         asset = self._download_json(
 202             api_base + '.json', video_id,
 203             'Downloading metadata JSON')['asset']
 204         title = asset.get('subtitle') or asset['title']
 205         is_live = asset.get('live') is True
 206
 207         formats = []
 208         format_urls = []
 209         for protocol in self._PROTOCOLS:
 210             try:
 211                 data = self._download_json(
 212                     api_base + f'/play.json?protocol={protocol}&videoFormat=SMIL+ISMUSP',
 213                     video_id, 'Downloading play JSON')['playback']
 214             except ExtractorError as e:
 215                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
 216                     error = self._parse_json(e.cause.response.read().decode(), video_id)['error']
 217                     error_code = error.get('code')
 218                     if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
 219                         self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
 220                     elif error_code == 'SESSION_NOT_AUTHENTICATED':
 221                         self.raise_login_required()
 222                     raise ExtractorError(error['description'])
 223                 raise
 224             items = try_get(data, lambda x: x['items']['item'])
 225             if not items:
 226                 continue
 227             if not isinstance(items, list):
 228                 items = [items]
 229             for item in items:
 230                 if not isinstance(item, dict):
 231                     continue
 232                 video_url = item.get('url')
 233                 if not video_url or video_url in format_urls:
 234                     continue
 235                 format_id = '{}-{}'.format(protocol.lower(), item.get('mediaFormat'))
 236                 if not self._is_valid_url(video_url, video_id, format_id):
 237                     continue
 238                 format_urls.append(video_url)
 239                 ext = determine_ext(video_url)
 240                 if ext == 'f4m':
 241                     formats.extend(self._extract_f4m_formats(
 242                         video_url, video_id, f4m_id=format_id, fatal=False))
 243                 elif ext == 'm3u8':
 244                     if not data.get('drmProtected'):
 245                         formats.extend(self._extract_m3u8_formats(
 246                             video_url, video_id, 'mp4', live=is_live, m3u8_id=format_id, fatal=False))
 247                 elif ext == 'mpd':
 248                     formats.extend(self._extract_mpd_formats(
 249                         video_url, video_id, format_id, fatal=False))
 250                 elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
 251                     pass
 252                 else:
 253                     formats.append({
 254                         'url': video_url,
 255                         'format_id': format_id,
 256                         'tbr': int_or_none(item.get('bitrate')),
 257                         'filesize': int_or_none(item.get('fileSize')),
 258                     })
 259         if not formats and data.get('drmProtected'):
 260             self.report_drm(video_id)
 261
 262         thumbnails = [{
 263             'id': thumbnail.get('@type'),
 264             'url': thumbnail.get('url'),
 265         } for _, thumbnail in (asset.get('imageVersions') or {}).items()]
 266
 267         return {
 268             'id': video_id,
 269             'url': video_url,
 270             'title': title,
 271             'description': strip_or_none(asset.get('description')),
 272             'thumbnails': thumbnails,
 273             'timestamp': parse_iso8601(asset.get('createTime')),
 274             'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')),
 275             'view_count': int_or_none(asset.get('views')),
 276             'categories': asset.get('keywords', '').split(','),
 277             'formats': formats,
 278             'is_live': is_live,
 279         }
 280
 281
 282 class MTVUutisetArticleIE(InfoExtractor):
 283     _WORKING = False
 284     _VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
 285     _TESTS = [{
 286         'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
 287         'info_dict': {
 288             'id': '1311159',
 289             'ext': 'mp4',
 290             'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
 291             'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
 292             'timestamp': 1600608966,
 293             'upload_date': '20200920',
 294             'duration': 153.7886666,
 295             'view_count': int,
 296             'categories': list,
 297         },
 298         'params': {
 299             # m3u8 download
 300             'skip_download': True,
 301         },
 302     }, {
 303         # multiple Youtube embeds
 304         'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
 305         'only_matching': True,
 306     }]
 307
 308     def _real_extract(self, url):
 309         article_id = self._match_id(url)
 310         article = self._download_json(
 311             'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id,
 312             article_id)
 313
 314         def entries():
 315             for video in (article.get('videos') or []):
 316                 video_type = video.get('videotype')
 317                 video_url = video.get('url')
 318                 if not (video_url and video_type in ('katsomo', 'youtube')):
 319                     continue
 320                 yield self.url_result(
 321                     video_url, video_type.capitalize(), video.get('video_id'))
 322
 323         return self.playlist_result(
 324             entries(), article_id, article.get('title'), article.get('description'))