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'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
  17     _TEST = {
  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
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('id')
  38         display_id = mobj.group('display_id')
  39
  40         data = self._download_json(
  41             'http://api.dbtv.no/discovery/%s' % video_id, display_id)
  42
  43         video = data['playlist'][0]
  44
  45         formats = [{
  46             'url': f['URL'],
  47             'vcodec': f.get('container'),
  48             'width': int_or_none(f.get('width')),
  49             'height': int_or_none(f.get('height')),
  50             'vbr': float_or_none(f.get('rate'), 1000),
  51             'filesize': int_or_none(f.get('size')),
  52         } for f in video['renditions'] if 'URL' in f]
  53
  54         if not formats:
  55             for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]:
  56                 if url_key in video:
  57                     formats.append({
  58                         'url': video[url_key],
  59                         'format_id': format_id,
  60                     })
  61
  62         self._sort_formats(formats)
  63
  64         return {
  65             'id': compat_str(video['id']),
  66             'display_id': display_id,
  67             'title': video['title'],
  68             'description': clean_html(video['desc']),
  69             'thumbnail': video.get('splash') or video.get('thumb'),
  70             'timestamp': float_or_none(video.get('publishedAt'), 1000),
  71             'duration': float_or_none(video.get('length'), 1000),
  72             'view_count': int_or_none(video.get('views')),
  73             'categories': video.get('tags'),
  74             'formats': formats,
  75         }