yt_dlp/extractor/alsace20tv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     dict_get,
   5     get_element_by_class,
   6     int_or_none,
   7     unified_strdate,
   8     url_or_none,
   9 )
  10
  11
  12 class Alsace20TVBaseIE(InfoExtractor):
  13     def _extract_video(self, video_id, url=None):
  14         info = self._download_json(
  15             'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
  16             video_id) or {}
  17         title = info.get('titre')
  18
  19         formats = []
  20         for res, fmt_url in (info.get('files') or {}).items():
  21             formats.extend(
  22                 self._extract_smil_formats(fmt_url, video_id, fatal=False)
  23                 if '/smil:_' in fmt_url
  24                 else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
  25         self._sort_formats(formats)
  26
  27         webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
  28         thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
  29         upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
  30         upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
  31         return {
  32             'id': video_id,
  33             'title': title,
  34             'formats': formats,
  35             'description': clean_html(get_element_by_class('wysiwyg', webpage)),
  36             'upload_date': upload_date,
  37             'thumbnail': thumbnail,
  38             'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
  39             'view_count': int_or_none(info.get('nb_vues')),
  40         }
  41
  42
  43 class Alsace20TVIE(Alsace20TVBaseIE):
  44     _VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
  45     _TESTS = [{
  46         'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
  47         'info_dict': {
  48             'id': 'lyNHCXpYJh',
  49             'ext': 'mp4',
  50             'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
  51             'title': 'Votre JT du jeudi 3 février',
  52             'upload_date': '20220203',
  53             'thumbnail': r're:https?://.+\.jpg',
  54             'duration': 1073,
  55             'view_count': int,
  56         },
  57     }]
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61         return self._extract_video(video_id, url)
  62
  63
  64 class Alsace20TVEmbedIE(Alsace20TVBaseIE):
  65     _VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
  66     _TESTS = [{
  67         'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
  68         # 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
  69         'info_dict': {
  70             'id': 'lyNHCXpYJh',
  71             'ext': 'mp4',
  72             'title': 'Votre JT du jeudi 3 février',
  73             'upload_date': '20220203',
  74             'thumbnail': r're:https?://.+\.jpg',
  75             'view_count': int,
  76         },
  77         'params': {
  78             'format': 'bestvideo',
  79         },
  80     }]
  81
  82     def _real_extract(self, url):
  83         video_id = self._match_id(url)
  84         return self._extract_video(video_id)