yt_dlp/extractor/dumpert.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     qualities,
   5 )
   6
   7
   8 class DumpertIE(InfoExtractor):
   9     _VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'
  10     _TESTS = [{
  11         'url': 'https://www.dumpert.nl/item/6646981_951bc60f',
  12         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
  13         'info_dict': {
  14             'id': '6646981/951bc60f',
  15             'ext': 'mp4',
  16             'title': 'Ik heb nieuws voor je',
  17             'description': 'Niet schrikken hoor',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19         }
  20     }, {
  21         'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7',
  22         'only_matching': True,
  23     }, {
  24         'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f',
  25         'only_matching': True,
  26     }, {
  27         'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url).replace('_', '/')
  33         item = self._download_json(
  34             'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'),
  35             video_id)['items'][0]
  36         title = item['title']
  37         media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO')
  38
  39         quality = qualities(['flv', 'mobile', 'tablet', '720p'])
  40         formats = []
  41         for variant in media.get('variants', []):
  42             uri = variant.get('uri')
  43             if not uri:
  44                 continue
  45             version = variant.get('version')
  46             formats.append({
  47                 'url': uri,
  48                 'format_id': version,
  49                 'quality': quality(version),
  50             })
  51
  52         thumbnails = []
  53         stills = item.get('stills') or {}
  54         for t in ('thumb', 'still'):
  55             for s in ('', '-medium', '-large'):
  56                 still_id = t + s
  57                 still_url = stills.get(still_id)
  58                 if not still_url:
  59                     continue
  60                 thumbnails.append({
  61                     'id': still_id,
  62                     'url': still_url,
  63                 })
  64
  65         stats = item.get('stats') or {}
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'description': item.get('description'),
  71             'thumbnails': thumbnails,
  72             'formats': formats,
  73             'duration': int_or_none(media.get('duration')),
  74             'like_count': int_or_none(stats.get('kudos_total')),
  75             'view_count': int_or_none(stats.get('views_total')),
  76         }