youtube_dl/extractor/aftonbladet.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import datetime
   5 import re
   6
   7 from .common import InfoExtractor
   8
   9
  10 class AftonbladetIE(InfoExtractor):
  11     _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
  12     _TEST = {
  13         'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
  14         'info_dict': {
  15             'id': 'article36015',
  16             'ext': 'mp4',
  17             'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
  18             'description': 'Jupiters måne mest aktiv av alla himlakroppar',
  19             'upload_date': '20140306',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.search(self._VALID_URL, url)
  25
  26         video_id = mobj.group('video_id')
  27         webpage = self._download_webpage(url, video_id)
  28
  29         # find internal video meta data
  30         META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
  31         internal_meta_id = self._html_search_regex(
  32             r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
  33         internal_meta_url = META_URL % internal_meta_id
  34         internal_meta_json = self._download_json(
  35             internal_meta_url, video_id, 'Downloading video meta data')
  36
  37         # find internal video formats
  38         FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
  39         internal_video_id = internal_meta_json['videoId']
  40         internal_formats_url = FORMATS_URL % internal_video_id
  41         internal_formats_json = self._download_json(
  42             internal_formats_url, video_id, 'Downloading video formats')
  43
  44         formats = []
  45         for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
  46             p = fmt['paths'][0]
  47             formats.append({
  48                 'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
  49                 'ext': 'mp4',
  50                 'width': fmt['width'],
  51                 'height': fmt['height'],
  52                 'tbr': fmt['bitrate'],
  53                 'protocol': 'http',
  54             })
  55         self._sort_formats(formats)
  56
  57         timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished'])
  58         upload_date = timestamp.strftime('%Y%m%d')
  59
  60         return {
  61             'id': video_id,
  62             'title': internal_meta_json['title'],
  63             'formats': formats,
  64             'thumbnail': internal_meta_json['imageUrl'],
  65             'description': internal_meta_json['shortPreamble'],
  66             'upload_date': upload_date,
  67             'duration': internal_meta_json['duration'],
  68             'view_count': internal_meta_json['views'],
  69         }