Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/dumpert.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     qualities,
   8 )
   9
  10
  11 class DumpertIE(InfoExtractor):
  12     _VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'
  13     _TESTS = [{
  14         'url': 'https://www.dumpert.nl/item/6646981_951bc60f',
  15         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
  16         'info_dict': {
  17             'id': '6646981/951bc60f',
  18             'ext': 'mp4',
  19             'title': 'Ik heb nieuws voor je',
  20             'description': 'Niet schrikken hoor',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22         }
  23     }, {
  24         'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7',
  25         'only_matching': True,
  26     }, {
  27         'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f',
  28         'only_matching': True,
  29     }, {
  30         'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url).replace('_', '/')
  36         item = self._download_json(
  37             'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'),
  38             video_id)['items'][0]
  39         title = item['title']
  40         media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO')
  41
  42         quality = qualities(['flv', 'mobile', 'tablet', '720p'])
  43         formats = []
  44         for variant in media.get('variants', []):
  45             uri = variant.get('uri')
  46             if not uri:
  47                 continue
  48             version = variant.get('version')
  49             formats.append({
  50                 'url': uri,
  51                 'format_id': version,
  52                 'quality': quality(version),
  53             })
  54         self._sort_formats(formats)
  55
  56         thumbnails = []
  57         stills = item.get('stills') or {}
  58         for t in ('thumb', 'still'):
  59             for s in ('', '-medium', '-large'):
  60                 still_id = t + s
  61                 still_url = stills.get(still_id)
  62                 if not still_url:
  63                     continue
  64                 thumbnails.append({
  65                     'id': still_id,
  66                     'url': still_url,
  67                 })
  68
  69         stats = item.get('stats') or {}
  70
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'description': item.get('description'),
  75             'thumbnails': thumbnails,
  76             'formats': formats,
  77             'duration': int_or_none(media.get('duration')),
  78             'like_count': int_or_none(stats.get('kudos_total')),
  79             'view_count': int_or_none(stats.get('views_total')),
  80         }