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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     float_or_none,
  10     int_or_none,
  11     clean_html,
  12 )
  13
  14
  15 class DBTVIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
  17     _TESTS = [{
  18         'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
  19         'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
  20         'info_dict': {
  21             'id': '33100',
  22             'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
  23             'ext': 'mp4',
  24             'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
  25             'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
  26             'thumbnail': 're:https?://.*\.jpg$',
  27             'timestamp': 1404039863.438,
  28             'upload_date': '20140629',
  29             'duration': 69.544,
  30             'view_count': int,
  31             'categories': list,
  32         }
  33     }, {
  34         'url': 'http://dbtv.no/3649835190001',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43         video_id = mobj.group('id')
  44         display_id = mobj.group('display_id') or video_id
  45
  46         data = self._download_json(
  47             'http://api.dbtv.no/discovery/%s' % video_id, display_id)
  48
  49         video = data['playlist'][0]
  50
  51         formats = [{
  52             'url': f['URL'],
  53             'vcodec': f.get('container'),
  54             'width': int_or_none(f.get('width')),
  55             'height': int_or_none(f.get('height')),
  56             'vbr': float_or_none(f.get('rate'), 1000),
  57             'filesize': int_or_none(f.get('size')),
  58         } for f in video['renditions'] if 'URL' in f]
  59
  60         if not formats:
  61             for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]:
  62                 if url_key in video:
  63                     formats.append({
  64                         'url': video[url_key],
  65                         'format_id': format_id,
  66                     })
  67
  68         self._sort_formats(formats)
  69
  70         return {
  71             'id': compat_str(video['id']),
  72             'display_id': display_id,
  73             'title': video['title'],
  74             'description': clean_html(video['desc']),
  75             'thumbnail': video.get('splash') or video.get('thumb'),
  76             'timestamp': float_or_none(video.get('publishedAt'), 1000),
  77             'duration': float_or_none(video.get('length'), 1000),
  78             'view_count': int_or_none(video.get('views')),
  79             'categories': video.get('tags'),
  80             'formats': formats,
  81         }