yt_dlp/extractor/dw.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     unified_strdate,
   5     url_or_none,
   6 )
   7 from ..compat import compat_urlparse
   8
   9
  10 class DWIE(InfoExtractor):
  11     IE_NAME = 'dw'
  12     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)'
  13     _TESTS = [{
  14         # video
  15         'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
  16         'md5': 'fb9dfd9520811d3ece80f04befd73428',
  17         'info_dict': {
  18             'id': '19112290',
  19             'ext': 'mp4',
  20             'title': 'Intelligent light',
  21             'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
  22             'upload_date': '20160605',
  23         }
  24     }, {
  25         # audio
  26         'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
  27         'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
  28         'info_dict': {
  29             'id': '19111941',
  30             'ext': 'mp3',
  31             'title': 'WorldLink: My business',
  32             'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
  33             'upload_date': '20160311',
  34         }
  35     }, {
  36         # DW documentaries, only last for one or two weeks
  37         'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
  38         'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
  39         'info_dict': {
  40             'id': '19274438',
  41             'ext': 'mp4',
  42             'title': 'Welcome to the 90s – Hip Hop',
  43             'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
  44             'upload_date': '20160521',
  45         },
  46         'skip': 'Video removed',
  47     }]
  48
  49     def _real_extract(self, url):
  50         media_id = self._match_id(url)
  51         webpage = self._download_webpage(url, media_id)
  52         hidden_inputs = self._hidden_inputs(webpage)
  53         title = hidden_inputs['media_title']
  54         media_id = hidden_inputs.get('media_id') or media_id
  55
  56         direct_url = url_or_none(hidden_inputs.get('file_name'))
  57         if direct_url:
  58             formats = [{'url': hidden_inputs['file_name']}]
  59         else:
  60             formats = self._extract_smil_formats(
  61                 'http://www.dw.com/smil/v-%s' % media_id, media_id,
  62                 transform_source=lambda s: s.replace(
  63                     'rtmp://tv-od.dw.de/flash/',
  64                     'http://tv-download.dw.de/dwtv_video/flv/'))
  65
  66         upload_date = hidden_inputs.get('display_date')
  67         if not upload_date:
  68             upload_date = self._html_search_regex(
  69                 r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage,
  70                 'upload date', default=None)
  71             upload_date = unified_strdate(upload_date)
  72
  73         return {
  74             'id': media_id,
  75             'title': title,
  76             'description': self._og_search_description(webpage),
  77             'thumbnail': hidden_inputs.get('preview_image'),
  78             'duration': int_or_none(hidden_inputs.get('file_duration')),
  79             'upload_date': upload_date,
  80             'formats': formats,
  81         }
  82
  83
  84 class DWArticleIE(InfoExtractor):
  85     IE_NAME = 'dw:article'
  86     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
  87     _TEST = {
  88         'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
  89         'md5': '8ca657f9d068bbef74d6fc38b97fc869',
  90         'info_dict': {
  91             'id': '19105868',
  92             'ext': 'mp4',
  93             'title': 'The harsh life of refugees in Idomeni',
  94             'description': 'md5:196015cc7e48ebf474db9399420043c7',
  95             'upload_date': '20160310',
  96         }
  97     }
  98
  99     def _real_extract(self, url):
 100         article_id = self._match_id(url)
 101         webpage = self._download_webpage(url, article_id)
 102         hidden_inputs = self._hidden_inputs(webpage)
 103         media_id = hidden_inputs['media_id']
 104         media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
 105         media_url = compat_urlparse.urljoin(url, media_path)
 106         return self.url_result(media_url, 'DW', media_id)