yt_dlp/extractor/internazionale.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import unified_timestamp
   6
   7
   8 class InternazionaleIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  10     _TESTS = [{
  11         'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood',
  12         'md5': '3e39d32b66882c1218e305acbf8348ca',
  13         'info_dict': {
  14             'id': '265968',
  15             'display_id': 'richard-linklater-racconta-una-scena-di-boyhood',
  16             'ext': 'mp4',
  17             'title': 'Richard Linklater racconta una scena di Boyhood',
  18             'description': 'md5:efb7e5bbfb1a54ae2ed5a4a015f0e665',
  19             'timestamp': 1424354635,
  20             'upload_date': '20150219',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22         },
  23     }, {
  24         'url': 'https://www.internazionale.it/video/2018/08/29/telefono-stare-con-noi-stessi',
  25         'md5': '9db8663704cab73eb972d1cee0082c79',
  26         'info_dict': {
  27             'id': '761344',
  28             'display_id': 'telefono-stare-con-noi-stessi',
  29             'ext': 'mp4',
  30             'title': 'Usiamo il telefono per evitare di stare con noi stessi',
  31             'description': 'md5:75ccfb0d6bcefc6e7428c68b4aa1fe44',
  32             'timestamp': 1535528954,
  33             'upload_date': '20180829',
  34             'thumbnail': r're:^https?://.*\.jpg$',
  35         },
  36     }]
  37
  38     def _real_extract(self, url):
  39         display_id = self._match_id(url)
  40
  41         webpage = self._download_webpage(url, display_id)
  42
  43         DATA_RE = r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1'
  44
  45         title = self._search_regex(
  46             DATA_RE % 'video-title', webpage, 'title', default=None,
  47             group='value') or self._og_search_title(webpage)
  48
  49         video_id = self._search_regex(
  50             DATA_RE % 'job-id', webpage, 'video id', group='value')
  51         video_path = self._search_regex(
  52             DATA_RE % 'video-path', webpage, 'video path', group='value')
  53         video_available_abroad = self._search_regex(
  54             DATA_RE % 'video-available_abroad', webpage,
  55             'video available aboard', default='1', group='value')
  56         video_available_abroad = video_available_abroad == '1'
  57
  58         video_base = 'https://video%s.internazionale.it/%s/%s.' % \
  59             ('' if video_available_abroad else '-ita', video_path, video_id)
  60
  61         formats = self._extract_m3u8_formats(
  62             video_base + 'm3u8', display_id, 'mp4',
  63             entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
  64         formats.extend(self._extract_mpd_formats(
  65             video_base + 'mpd', display_id, mpd_id='dash', fatal=False))
  66         self._sort_formats(formats)
  67
  68         timestamp = unified_timestamp(self._html_search_meta(
  69             'article:published_time', webpage, 'timestamp'))
  70
  71         return {
  72             'id': video_id,
  73             'display_id': display_id,
  74             'title': title,
  75             'thumbnail': self._og_search_thumbnail(webpage),
  76             'description': self._og_search_description(webpage),
  77             'timestamp': timestamp,
  78             'formats': formats,
  79         }