_ Git - youtube-dl/blob - youtube_dl/extractor/dw.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import int_or_none
   6
   7
   8 class DWIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)'
  10     _TEST = {
  11         'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
  12         'md5': '7372046e1815c5a534b43f3c3c36e6e9',
  13         'info_dict': {
  14             'id': '19112290',
  15             'ext': 'mp4',
  16             'title': 'Intelligent light',
  17             'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
  18             'upload_date': '20160311',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         formats = self._extract_smil_formats(
  26             'http://www.dw.com/smil/v-%s' % video_id, video_id,
  27             transform_source=lambda s: s.replace(
  28                 'rtmp://tv-od.dw.de/flash/',
  29                 'http://tv-download.dw.de/dwtv_video/flv/'))
  30
  31         webpage = self._download_webpage(url, video_id)
  32         hidden_inputs = self._hidden_inputs(webpage)
  33         title = hidden_inputs['media_title']
  34
  35         return {
  36             'id': video_id,
  37             'title': title,
  38             'description': self._og_search_description(webpage),
  39             'thumbnail': hidden_inputs.get('preview_image'),
  40             'duration': int_or_none(hidden_inputs.get('file_duration')),
  41             'upload_date': hidden_inputs.get('display_date'),
  42             'formats': formats,
  43         }