yt_dlp/extractor/tvn24.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     NO_DEFAULT,
   5     unescapeHTML,
   6 )
   7
   8
   9 class TVN24IE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P<id>[^/]+)'
  11     _TESTS = [{
  12         'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html',
  13         'md5': 'fbdec753d7bc29d96036808275f2130c',
  14         'info_dict': {
  15             'id': '1584444',
  16             'ext': 'mp4',
  17             'title': '"Święta mają być wesołe, dlatego, ludziska, wszyscy pod jemiołę"',
  18             'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości Szkła kontaktowego.',
  19             'thumbnail': 're:https?://.*[.]jpeg',
  20         }
  21     }, {
  22         # different layout
  23         'url': 'https://tvnmeteo.tvn24.pl/magazyny/maja-w-ogrodzie,13/odcinki-online,1,4,1,0/pnacza-ptaki-i-iglaki-odc-691-hgtv-odc-29,1771763.html',
  24         'info_dict': {
  25             'id': '1771763',
  26             'ext': 'mp4',
  27             'title': 'Pnącza, ptaki i iglaki (odc. 691 /HGTV odc. 29)',
  28             'thumbnail': 're:https?://.*',
  29         },
  30         'params': {
  31             'skip_download': True,
  32         },
  33     }, {
  34         'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://sport.tvn24.pl/pilka-nozna,105/ligue-1-kamil-glik-rozcial-glowe-monaco-tylko-remisuje-z-bastia,716522.html',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://tvn24bis.pl/poranek,146,m/gen-koziej-w-tvn24-bis-wracamy-do-czasow-zimnej-wojny,715660.html',
  41         'only_matching': True,
  42     }, {
  43         'url': 'https://www.tvn24.pl/magazyn-tvn24/angie-w-jednej-czwartej-polka-od-szarej-myszki-do-cesarzowej-europy,119,2158',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         display_id = self._match_id(url)
  49
  50         webpage = self._download_webpage(url, display_id)
  51
  52         title = self._og_search_title(
  53             webpage, default=None) or self._search_regex(
  54             r'<h\d+[^>]+class=["\']magazineItemHeader[^>]+>(.+?)</h',
  55             webpage, 'title')
  56
  57         def extract_json(attr, name, default=NO_DEFAULT, fatal=True):
  58             return self._parse_json(
  59                 self._search_regex(
  60                     r'\b%s=(["\'])(?P<json>(?!\1).+?)\1' % attr, webpage,
  61                     name, group='json', default=default, fatal=fatal) or '{}',
  62                 display_id, transform_source=unescapeHTML, fatal=fatal)
  63
  64         quality_data = extract_json('data-quality', 'formats')
  65
  66         formats = []
  67         for format_id, url in quality_data.items():
  68             formats.append({
  69                 'url': url,
  70                 'format_id': format_id,
  71                 'height': int_or_none(format_id.rstrip('p')),
  72             })
  73
  74         description = self._og_search_description(webpage, default=None)
  75         thumbnail = self._og_search_thumbnail(
  76             webpage, default=None) or self._html_search_regex(
  77             r'\bdata-poster=(["\'])(?P<url>(?!\1).+?)\1', webpage,
  78             'thumbnail', group='url')
  79
  80         video_id = None
  81
  82         share_params = extract_json(
  83             'data-share-params', 'share params', default=None)
  84         if isinstance(share_params, dict):
  85             video_id = share_params.get('id')
  86
  87         if not video_id:
  88             video_id = self._search_regex(
  89                 r'data-vid-id=["\'](\d+)', webpage, 'video id',
  90                 default=None) or self._search_regex(
  91                 r',(\d+)\.html', url, 'video id', default=display_id)
  92
  93         return {
  94             'id': video_id,
  95             'title': title,
  96             'description': description,
  97             'thumbnail': thumbnail,
  98             'formats': formats,
  99         }