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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class AftonbladetIE(InfoExtractor):
   8     _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
   9     _TEST = {
  10         'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
  11         'info_dict': {
  12             'id': 'article36015',
  13             'ext': 'mp4',
  14             'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
  15             'description': 'Jupiters måne mest aktiv av alla himlakroppar',
  16             'timestamp': 1394142732,
  17             'upload_date': '20140306',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         # find internal video meta data
  26         meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
  27         internal_meta_id = self._html_search_regex(
  28             r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
  29         internal_meta_url = meta_url % internal_meta_id
  30         internal_meta_json = self._download_json(
  31             internal_meta_url, video_id, 'Downloading video meta data')
  32
  33         # find internal video formats
  34         format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
  35         internal_video_id = internal_meta_json['videoId']
  36         internal_formats_url = format_url % internal_video_id
  37         internal_formats_json = self._download_json(
  38             internal_formats_url, video_id, 'Downloading video formats')
  39
  40         formats = []
  41         for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
  42             p = fmt['paths'][0]
  43             formats.append({
  44                 'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
  45                 'ext': 'mp4',
  46                 'width': fmt['width'],
  47                 'height': fmt['height'],
  48                 'tbr': fmt['bitrate'],
  49                 'protocol': 'http',
  50             })
  51         self._sort_formats(formats)
  52
  53         return {
  54             'id': video_id,
  55             'title': internal_meta_json['title'],
  56             'formats': formats,
  57             'thumbnail': internal_meta_json['imageUrl'],
  58             'description': internal_meta_json['shortPreamble'],
  59             'timestamp': internal_meta_json['timePublished'],
  60             'duration': internal_meta_json['duration'],
  61             'view_count': internal_meta_json['views'],
  62         }