yt_dlp/extractor/dw.py

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