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 (
   6     int_or_none,
   7     unified_strdate,
   8 )
   9 from ..compat import compat_urlparse
  10
  11
  12 class DWIE(InfoExtractor):
  13     IE_NAME = 'dw'
  14     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)'
  15     _TESTS = [{
  16         # video
  17         'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
  18         'md5': '7372046e1815c5a534b43f3c3c36e6e9',
  19         'info_dict': {
  20             'id': '19112290',
  21             'ext': 'mp4',
  22             'title': 'Intelligent light',
  23             'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
  24             'upload_date': '20160311',
  25         }
  26     }, {
  27         # audio
  28         'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
  29         'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
  30         'info_dict': {
  31             'id': '19111941',
  32             'ext': 'mp3',
  33             'title': 'WorldLink: My business',
  34             'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
  35             'upload_date': '20160311',
  36         }
  37     }, {
  38         # DW documentaries, only last for one or two weeks
  39         'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
  40         'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
  41         'info_dict': {
  42             'id': '19274438',
  43             'ext': 'mp4',
  44             'title': 'Welcome to the 90s – Hip Hop',
  45             'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
  46             'upload_date': '20160521',
  47         },
  48         'skip': 'Video removed',
  49     }]
  50
  51     def _real_extract(self, url):
  52         media_id = self._match_id(url)
  53         webpage = self._download_webpage(url, media_id)
  54         hidden_inputs = self._hidden_inputs(webpage)
  55         title = hidden_inputs['media_title']
  56         media_id = hidden_inputs.get('media_id') or media_id
  57
  58         if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
  59             formats = self._extract_smil_formats(
  60                 'http://www.dw.com/smil/v-%s' % media_id, media_id,
  61                 transform_source=lambda s: s.replace(
  62                     'rtmp://tv-od.dw.de/flash/',
  63                     'http://tv-download.dw.de/dwtv_video/flv/'))
  64             self._sort_formats(formats)
  65         else:
  66             formats = [{'url': hidden_inputs['file_name']}]
  67
  68         upload_date = hidden_inputs.get('display_date')
  69         if not upload_date:
  70             upload_date = self._html_search_regex(
  71                 r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage,
  72                 'upload date', default=None)
  73             upload_date = unified_strdate(upload_date)
  74
  75         return {
  76             'id': media_id,
  77             'title': title,
  78             'description': self._og_search_description(webpage),
  79             'thumbnail': hidden_inputs.get('preview_image'),
  80             'duration': int_or_none(hidden_inputs.get('file_duration')),
  81             'upload_date': upload_date,
  82             'formats': formats,
  83         }
  84
  85
  86 class DWArticleIE(InfoExtractor):
  87     IE_NAME = 'dw:article'
  88     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
  89     _TEST = {
  90         'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
  91         'md5': '8ca657f9d068bbef74d6fc38b97fc869',
  92         'info_dict': {
  93             'id': '19105868',
  94             'ext': 'mp4',
  95             'title': 'The harsh life of refugees in Idomeni',
  96             'description': 'md5:196015cc7e48ebf474db9399420043c7',
  97             'upload_date': '20160310',
  98         }
  99     }
 100
 101     def _real_extract(self, url):
 102         article_id = self._match_id(url)
 103         webpage = self._download_webpage(url, article_id)
 104         hidden_inputs = self._hidden_inputs(webpage)
 105         media_id = hidden_inputs['media_id']
 106         media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
 107         media_url = compat_urlparse.urljoin(url, media_path)
 108         return self.url_result(media_url, 'DW', media_id)