yt_dlp/extractor/internazionale.py

   1 from .common import InfoExtractor
   2 from ..utils import unified_timestamp
   3
   4
   5 class InternazionaleIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
   7     _TESTS = [{
   8         'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood',
   9         'md5': '3e39d32b66882c1218e305acbf8348ca',
  10         'info_dict': {
  11             'id': '265968',
  12             'display_id': 'richard-linklater-racconta-una-scena-di-boyhood',
  13             'ext': 'mp4',
  14             'title': 'Richard Linklater racconta una scena di Boyhood',
  15             'description': 'md5:efb7e5bbfb1a54ae2ed5a4a015f0e665',
  16             'timestamp': 1424354635,
  17             'upload_date': '20150219',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19         },
  20     }, {
  21         'url': 'https://www.internazionale.it/video/2018/08/29/telefono-stare-con-noi-stessi',
  22         'md5': '9db8663704cab73eb972d1cee0082c79',
  23         'info_dict': {
  24             'id': '761344',
  25             'display_id': 'telefono-stare-con-noi-stessi',
  26             'ext': 'mp4',
  27             'title': 'Usiamo il telefono per evitare di stare con noi stessi',
  28             'description': 'md5:75ccfb0d6bcefc6e7428c68b4aa1fe44',
  29             'timestamp': 1535528954,
  30             'upload_date': '20180829',
  31             'thumbnail': r're:^https?://.*\.jpg$',
  32         },
  33     }]
  34
  35     def _real_extract(self, url):
  36         display_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(url, display_id)
  39
  40         DATA_RE = r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1'
  41
  42         title = self._search_regex(
  43             DATA_RE % 'video-title', webpage, 'title', default=None,
  44             group='value') or self._og_search_title(webpage)
  45
  46         video_id = self._search_regex(
  47             DATA_RE % 'job-id', webpage, 'video id', group='value')
  48         video_path = self._search_regex(
  49             DATA_RE % 'video-path', webpage, 'video path', group='value')
  50         video_available_abroad = self._search_regex(
  51             DATA_RE % 'video-available_abroad', webpage,
  52             'video available aboard', default='1', group='value')
  53         video_available_abroad = video_available_abroad == '1'
  54
  55         video_base = 'https://video{}.internazionale.it/{}/{}.'.format(
  56             '' if video_available_abroad else '-ita', video_path, video_id)
  57
  58         formats = self._extract_m3u8_formats(
  59             video_base + 'm3u8', display_id, 'mp4',
  60             entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
  61         formats.extend(self._extract_mpd_formats(
  62             video_base + 'mpd', display_id, mpd_id='dash', fatal=False))
  63
  64         timestamp = unified_timestamp(self._html_search_meta(
  65             'article:published_time', webpage, 'timestamp'))
  66
  67         return {
  68             'id': video_id,
  69             'display_id': display_id,
  70             'title': title,
  71             'thumbnail': self._og_search_thumbnail(webpage),
  72             'description': self._og_search_description(webpage),
  73             'timestamp': timestamp,
  74             'formats': formats,
  75         }