yt_dlp/extractor/twentymin.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     try_get,
   5 )
   6
   7
   8 class TwentyMinutenIE(InfoExtractor):
   9     IE_NAME = '20min'
  10     _VALID_URL = r'''(?x)
  11                     https?://
  12                         (?:www\.)?20min\.ch/
  13                         (?:
  14                             videotv/*\?.*?\bvid=|
  15                             videoplayer/videoplayer\.html\?.*?\bvideoId@
  16                         )
  17                         (?P<id>\d+)
  18                     '''
  19     _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:(?:https?:)?//)?(?:www\.)?20min\.ch/videoplayer/videoplayer.html\?.*?\bvideoId@\d+.*?)\1']
  20     _TESTS = [{
  21         'url': 'http://www.20min.ch/videotv/?vid=469148&cid=2',
  22         'md5': 'e7264320db31eed8c38364150c12496e',
  23         'info_dict': {
  24             'id': '469148',
  25             'ext': 'mp4',
  26             'title': '85 000 Franken für 15 perfekte Minuten',
  27             'thumbnail': r're:https?://.*\.jpg$',
  28         },
  29     }, {
  30         'url': 'http://www.20min.ch/videoplayer/videoplayer.html?params=client@twentyDE|videoId@523629',
  31         'info_dict': {
  32             'id': '523629',
  33             'ext': 'mp4',
  34             'title': 'So kommen Sie bei Eis und Schnee sicher an',
  35             'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  36             'thumbnail': r're:https?://.*\.jpg$',
  37         },
  38         'params': {
  39             'skip_download': True,
  40         },
  41     }, {
  42         'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738',
  43         'only_matching': True,
  44     }]
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48
  49         video = self._download_json(
  50             f'http://api.20min.ch/video/{video_id}/show',
  51             video_id)['content']
  52
  53         title = video['title']
  54
  55         formats = [{
  56             'format_id': format_id,
  57             'url': f'http://podcast.20min-tv.ch/podcast/20min/{video_id}{p}.mp4',
  58             'quality': quality,
  59         } for quality, (format_id, p) in enumerate([('sd', ''), ('hd', 'h')])]
  60
  61         description = video.get('lead')
  62         thumbnail = video.get('thumbnail')
  63
  64         def extract_count(kind):
  65             return try_get(
  66                 video,
  67                 lambda x: int_or_none(x['communityobject'][f'thumbs_{kind}']))
  68
  69         like_count = extract_count('up')
  70         dislike_count = extract_count('down')
  71
  72         return {
  73             'id': video_id,
  74             'title': title,
  75             'description': description,
  76             'thumbnail': thumbnail,
  77             'like_count': like_count,
  78             'dislike_count': dislike_count,
  79             'formats': formats,
  80         }