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