yt_dlp/extractor/ukcolumn.py

   1 from __future__ import unicode_literals
   2
   3 from ..utils import (
   4     unescapeHTML,
   5     urljoin,
   6     ExtractorError,
   7 )
   8 from .common import InfoExtractor
   9 from .vimeo import VimeoIE
  10 from .youtube import YoutubeIE
  11
  12
  13 class UkColumnIE(InfoExtractor):
  14     IE_NAME = 'ukcolumn'
  15     _VALID_URL = r'(?i)https?://(?:www\.)?ukcolumn\.org(/index\.php)?/(?:video|ukcolumn-news)/(?P<id>[-a-z0-9]+)'
  16
  17     _TESTS = [{
  18         'url': 'https://www.ukcolumn.org/ukcolumn-news/uk-column-news-28th-april-2021',
  19         'info_dict': {
  20             'id': '541632443',
  21             'ext': 'mp4',
  22             'title': 'UK Column News - 28th April 2021',
  23             'uploader_id': 'ukcolumn',
  24             'uploader': 'UK Column',
  25         },
  26         'add_ie': [VimeoIE.ie_key()],
  27         'expected_warnings': ['Unable to download JSON metadata'],
  28         'params': {
  29             'skip_download': 'Handled by Vimeo',
  30         },
  31     }, {
  32         'url': 'https://www.ukcolumn.org/video/insight-eu-military-unification',
  33         'info_dict': {
  34             'id': 'Fzbnb9t7XAw',
  35             'ext': 'mp4',
  36             'title': 'Insight: EU Military Unification',
  37             'uploader_id': 'ukcolumn',
  38             'description': 'md5:29a207965271af89baa0bc191f5de576',
  39             'uploader': 'UK Column',
  40             'upload_date': '20170514',
  41         },
  42         'add_ie': [YoutubeIE.ie_key()],
  43         'params': {
  44             'skip_download': 'Handled by Youtube',
  45         },
  46     }, {
  47         'url': 'https://www.ukcolumn.org/index.php/ukcolumn-news/uk-column-news-30th-april-2021',
  48         'only_matching': True,
  49     }]
  50
  51     def _real_extract(self, url):
  52         display_id = self._match_id(url)
  53         webpage = self._download_webpage(url, display_id)
  54
  55         oembed_url = urljoin(url, unescapeHTML(self._search_regex(
  56             r'<iframe[^>]+src=(["\'])(?P<url>/media/oembed\?url=.+?)\1',
  57             webpage, 'OEmbed URL', group='url')))
  58         oembed_webpage = self._download_webpage(
  59             oembed_url, display_id, note='Downloading OEmbed page')
  60
  61         ie, video_url = YoutubeIE, YoutubeIE._extract_url(oembed_webpage)
  62         if not video_url:
  63             ie, video_url = VimeoIE, VimeoIE._extract_url(url, oembed_webpage)
  64         if not video_url:
  65             raise ExtractorError('No embedded video found')
  66
  67         return {
  68             '_type': 'url_transparent',
  69             'title': self._og_search_title(webpage),
  70             'url': video_url,
  71             'ie_key': ie.ie_key(),
  72         }