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 from ..compat import compat_urlparse
   7
   8
   9 class DWIE(InfoExtractor):
  10     IE_NAME = 'dw'
  11     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)'
  12     _TESTS = [{
  13         # video
  14         'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
  15         'md5': '7372046e1815c5a534b43f3c3c36e6e9',
  16         'info_dict': {
  17             'id': '19112290',
  18             'ext': 'mp4',
  19             'title': 'Intelligent light',
  20             'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
  21             'upload_date': '20160311',
  22         }
  23     }, {
  24         # audio
  25         'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
  26         'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
  27         'info_dict': {
  28             'id': '19111941',
  29             'ext': 'mp3',
  30             'title': 'WorldLink: My business',
  31             'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
  32             'upload_date': '20160311',
  33         }
  34     }]
  35
  36     def _real_extract(self, url):
  37         media_id = self._match_id(url)
  38         webpage = self._download_webpage(url, media_id)
  39         hidden_inputs = self._hidden_inputs(webpage)
  40         title = hidden_inputs['media_title']
  41
  42         if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
  43             formats = self._extract_smil_formats(
  44                 'http://www.dw.com/smil/v-%s' % media_id, media_id,
  45                 transform_source=lambda s: s.replace(
  46                     'rtmp://tv-od.dw.de/flash/',
  47                     'http://tv-download.dw.de/dwtv_video/flv/'))
  48             self._sort_formats(formats)
  49         else:
  50             formats = [{'url': hidden_inputs['file_name']}]
  51
  52         return {
  53             'id': media_id,
  54             'title': title,
  55             'description': self._og_search_description(webpage),
  56             'thumbnail': hidden_inputs.get('preview_image'),
  57             'duration': int_or_none(hidden_inputs.get('file_duration')),
  58             'upload_date': hidden_inputs.get('display_date'),
  59             'formats': formats,
  60         }
  61
  62
  63 class DWArticleIE(InfoExtractor):
  64     IE_NAME = 'dw:article'
  65     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
  66     _TEST = {
  67         'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
  68         'md5': '8ca657f9d068bbef74d6fc38b97fc869',
  69         'info_dict': {
  70             'id': '19105868',
  71             'ext': 'mp4',
  72             'title': 'The harsh life of refugees in Idomeni',
  73             'description': 'md5:196015cc7e48ebf474db9399420043c7',
  74             'upload_date': '20160310',
  75         }
  76     }
  77
  78     def _real_extract(self, url):
  79         article_id = self._match_id(url)
  80         webpage = self._download_webpage(url, article_id)
  81         hidden_inputs = self._hidden_inputs(webpage)
  82         media_id = hidden_inputs['media_id']
  83         media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
  84         media_url = compat_urlparse.urljoin(url, media_path)
  85         return self.url_result(media_url, 'DW', media_id)