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