yt_dlp/extractor/dumpert.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     int_or_none,
   5     qualities,
   6 )
   7
   8
   9 class DumpertIE(InfoExtractor):
  10     _VALID_URL = r'''(?x)
  11         (?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:
  12             (?:mediabase|embed|item)/|
  13             [^#]*[?&]selectedId=
  14         )(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'''
  15     _TESTS = [{
  16         'url': 'https://www.dumpert.nl/item/6646981_951bc60f',
  17         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
  18         'info_dict': {
  19             'id': '6646981/951bc60f',
  20             'ext': 'mp4',
  21             'title': 'Ik heb nieuws voor je',
  22             'description': 'Niet schrikken hoor',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'duration': 9,
  25             'view_count': int,
  26             'like_count': int,
  27         },
  28     }, {
  29         'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7',
  30         'only_matching': True,
  31     }, {
  32         'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f',
  33         'only_matching': True,
  34     }, {
  35         'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7',
  36         'only_matching': True,
  37     }, {
  38         'url': 'https://www.dumpert.nl/item/100031688_b317a185',
  39         'info_dict': {
  40             'id': '100031688/b317a185',
  41             'ext': 'mp4',
  42             'title': 'Epic schijnbeweging',
  43             'description': '<p>Die zag je niet eh</p>',
  44             'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
  45             'duration': 12,
  46             'view_count': int,
  47             'like_count': int,
  48         },
  49         'params': {'skip_download': 'm3u8'},
  50     }, {
  51         'url': 'https://www.dumpert.nl/toppers?selectedId=100031688_b317a185',
  52         'only_matching': True,
  53     }, {
  54         'url': 'https://www.dumpert.nl/latest?selectedId=100031688_b317a185',
  55         'only_matching': True,
  56     }, {
  57         'url': 'https://www.dumpert.nl/?selectedId=100031688_b317a185',
  58         'only_matching': True,
  59     }, {
  60         'url': 'https://www.dumpert.nl/toppers/dag?selectedId=100086074_f5cef3ac',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url).replace('_', '/')
  66         item = self._download_json(
  67             'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'),
  68             video_id)['items'][0]
  69         title = item['title']
  70         media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO')
  71
  72         quality = qualities(['flv', 'mobile', 'tablet', '720p', '1080p'])
  73         formats = []
  74         for variant in media.get('variants', []):
  75             uri = variant.get('uri')
  76             if not uri:
  77                 continue
  78             version = variant.get('version')
  79             preference = quality(version)
  80             if determine_ext(uri) == 'm3u8':
  81                 formats.extend(self._extract_m3u8_formats(
  82                     uri, video_id, 'mp4', m3u8_id=version, quality=preference))
  83             else:
  84                 formats.append({
  85                     'url': uri,
  86                     'format_id': version,
  87                     'quality': preference,
  88                 })
  89
  90         thumbnails = []
  91         stills = item.get('stills') or {}
  92         for t in ('thumb', 'still'):
  93             for s in ('', '-medium', '-large'):
  94                 still_id = t + s
  95                 still_url = stills.get(still_id)
  96                 if not still_url:
  97                     continue
  98                 thumbnails.append({
  99                     'id': still_id,
 100                     'url': still_url,
 101                 })
 102
 103         stats = item.get('stats') or {}
 104
 105         return {
 106             'id': video_id,
 107             'title': title,
 108             'description': item.get('description'),
 109             'thumbnails': thumbnails,
 110             'formats': formats,
 111             'duration': int_or_none(media.get('duration')),
 112             'like_count': int_or_none(stats.get('kudos_total')),
 113             'view_count': int_or_none(stats.get('views_total')),
 114         }