yt_dlp/extractor/ukcolumn.py

   1 from .common import InfoExtractor
   2 from .vimeo import VimeoIE
   3 from .youtube import YoutubeIE
   4 from ..utils import (
   5     ExtractorError,
   6     unescapeHTML,
   7     urljoin,
   8 )
   9
  10
  11 class UkColumnIE(InfoExtractor):
  12     _WORKING = False
  13     IE_NAME = 'ukcolumn'
  14     _VALID_URL = r'(?i)https?://(?:www\.)?ukcolumn\.org(/index\.php)?/(?:video|ukcolumn-news)/(?P<id>[-a-z0-9]+)'
  15
  16     _TESTS = [{
  17         'url': 'https://www.ukcolumn.org/ukcolumn-news/uk-column-news-28th-april-2021',
  18         'info_dict': {
  19             'id': '541632443',
  20             'ext': 'mp4',
  21             'title': 'UK Column News - 28th April 2021',
  22             'uploader_id': 'ukcolumn',
  23             'uploader': 'UK Column',
  24         },
  25         'add_ie': [VimeoIE.ie_key()],
  26         'expected_warnings': ['Unable to download JSON metadata'],
  27         'params': {
  28             'skip_download': 'Handled by Vimeo',
  29         },
  30     }, {
  31         'url': 'https://www.ukcolumn.org/video/insight-eu-military-unification',
  32         'info_dict': {
  33             'id': 'Fzbnb9t7XAw',
  34             'ext': 'mp4',
  35             'title': 'Insight: EU Military Unification',
  36             'uploader_id': 'ukcolumn',
  37             'description': 'md5:29a207965271af89baa0bc191f5de576',
  38             'uploader': 'UK Column',
  39             'upload_date': '20170514',
  40         },
  41         'add_ie': [YoutubeIE.ie_key()],
  42         'params': {
  43             'skip_download': 'Handled by Youtube',
  44         },
  45     }, {
  46         'url': 'https://www.ukcolumn.org/index.php/ukcolumn-news/uk-column-news-30th-april-2021',
  47         'only_matching': True,
  48     }]
  49
  50     def _real_extract(self, url):
  51         display_id = self._match_id(url)
  52         webpage = self._download_webpage(url, display_id)
  53
  54         oembed_url = urljoin(url, unescapeHTML(self._search_regex(
  55             r'<iframe[^>]+src=(["\'])(?P<url>/media/oembed\?url=.+?)\1',
  56             webpage, 'OEmbed URL', group='url')))
  57         oembed_webpage = self._download_webpage(
  58             oembed_url, display_id, note='Downloading OEmbed page')
  59
  60         ie, video_url = YoutubeIE, YoutubeIE._extract_url(oembed_webpage)
  61         if not video_url:
  62             ie, video_url = VimeoIE, VimeoIE._extract_url(url, oembed_webpage)
  63         if not video_url:
  64             raise ExtractorError('No embedded video found')
  65
  66         return {
  67             '_type': 'url_transparent',
  68             'title': self._og_search_title(webpage),
  69             'url': video_url,
  70             'ie_key': ie.ie_key(),
  71         }