logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

gbnews.py (5138B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. from .common import InfoExtractor
  5. from ..utils import (
  6.     extract_attributes,
  7.     ExtractorError,
  8.     T,
  9.     traverse_obj,
  10.     txt_or_none,
  11.     url_or_none,
  12. )
  15. class GBNewsIE(InfoExtractor):
  16.     IE_DESC = 'GB News clips, features and live stream'
  18.     # \w+ is normally shows or news, but apparently any word redirects to the correct URL
  19.     _VALID_URL = r'https?://(?:www\.)?gbnews\.(?:uk|com)/(?:\w+/)?(?P<id>[^#?]+)'
  21.     _PLATFORM = 'safari'
  22.     _SSMP_URL = 'https://mm-v2.simplestream.com/ssmp/api.php'
  23.     _TESTS = [{
  24.         'url': 'https://www.gbnews.uk/shows/andrew-neils-message-to-companies-choosing-to-boycott-gb-news/106889',
  25.         'info_dict': {
  26.             'id': '106889',
  27.             'ext': 'mp4',
  28.             'title': "Andrew Neil's message to companies choosing to boycott GB News",
  29.             'description': 'md5:b281f5d22fd6d5eda64a4e3ba771b351',
  30.         },
  31.         'skip': '404 not found',
  32.     }, {
  33.         'url': 'https://www.gbnews.com/news/bbc-claudine-gay-harvard-university-antisemitism-row',
  34.         'info_dict': {
  35.             'id': '52264136',
  36.             'display_id': 'bbc-claudine-gay-harvard-university-antisemitism-row',
  37.             'ext': 'mp4',
  38.             'title': 'BBC deletes post after furious backlash over headline downplaying antisemitism',
  39.             'description': 'The post was criticised by former employers of the broadcaster',
  40.         },
  41.     }, {
  42.         'url': 'https://www.gbnews.uk/watchlive',
  43.         'info_dict': {
  44.             'id': '1069',
  45.             'display_id': 'watchlive',
  46.             'ext': 'mp4',
  47.             'title': 'GB News Live',
  48.             'is_live': True,
  49.         },
  50.         'params': {
  51.             'skip_download': 'm3u8',
  52.         },
  53.     }]
  55.     def _real_extract(self, url):
  56.         display_id = self._match_id(url).split('/')[-1]
  58.         webpage = self._download_webpage(url, display_id)
  59.         # extraction based on https://github.com/ytdl-org/youtube-dl/issues/29341
  60.         '''
  61.         <div id="video-106908"
  62.             class="simplestream"
  63.             data-id="GB001"
  64.             data-type="vod"
  65.             data-key="3Li3Nt2Qs8Ct3Xq9Fi5Uy0Mb2Bj0Qs"
  66.             data-token="f9c317c727dc07f515b20036c8ef14a6"
  67.             data-expiry="1624300052"
  68.             data-uvid="37900558"
  69.             data-poster="https://thumbnails.simplestreamcdn.com/gbnews/ondemand/37900558.jpg?width=700&"
  70.             data-npaw="false"
  71.             data-env="production">
  72.         '''
  73.         # exception if no match
  74.         video_data = self._search_regex(
  75.             r'(<div\s[^>]*\bclass\s*=\s*(\'|")(?!.*sidebar\b)simplestream(?:\s[\s\w$-]*)?\2[^>]*>)',
  76.             webpage, 'video data')
  78.         video_data = extract_attributes(video_data)
  79.         ss_id = video_data.get('data-id')
  80.         if not ss_id:
  81.             raise ExtractorError('Simplestream ID not found')
  83.         json_data = self._download_json(
  84.             self._SSMP_URL, display_id,
  85.             note='Downloading Simplestream JSON metadata',
  86.             errnote='Unable to download Simplestream JSON metadata',
  87.             query={
  88.                 'id': ss_id,
  89.                 'env': video_data.get('data-env', 'production'),
  90.             }, fatal=False)
  92.         meta_url = traverse_obj(json_data, ('response', 'api_hostname'))
  93.         if not meta_url:
  94.             raise ExtractorError('No API host found')
  96.         uvid = video_data['data-uvid']
  97.         dtype = video_data.get('data-type')
  98.         stream_data = self._download_json(
  99.             '%s/api/%s/stream/%s' % (meta_url, 'show' if dtype == 'vod' else dtype, uvid),
  100.             uvid,
  101.             query={
  102.                 'key': video_data.get('data-key'),
  103.                 'platform': self._PLATFORM,
  104.             },
  105.             headers={
  106.                 'Token': video_data.get('data-token'),
  107.                 'Token-Expiry': video_data.get('data-expiry'),
  108.                 'Uvid': uvid,
  109.             }, fatal=False)
  111.         stream_url = traverse_obj(stream_data, (
  112.             'response', 'stream', T(url_or_none)))
  113.         if not stream_url:
  114.             raise ExtractorError('No stream data/URL')
  116.         # now known to be a dict
  117.         stream_data = stream_data['response']
  118.         drm = stream_data.get('drm')
  119.         if drm:
  120.             self.report_drm(uvid)
  122.         formats = self._extract_m3u8_formats(
  123.             stream_url, uvid, ext='mp4', entry_protocol='m3u8_native',
  124.             fatal=False)
  125.         # exception if no formats
  126.         self._sort_formats(formats)
  128.         return {
  129.             'id': uvid,
  130.             'display_id': display_id,
  131.             'title': (traverse_obj(stream_data, ('title', T(txt_or_none)))
  132.                       or self._og_search_title(webpage, default=None)
  133.                       or display_id.replace('-', ' ').capitalize()),
  134.             'description': self._og_search_description(webpage, default=None),
  135.             'thumbnail': (traverse_obj(video_data, ('data-poster', T(url_or_none)))
  136.                           or self._og_search_thumbnail(webpage)),
  137.             'formats': formats,
  138.             'is_live': (dtype == 'live') or None,
  139.         }