yt_dlp/extractor/parlview.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     try_get,
   5     unified_timestamp,
   6 )
   7
   8
   9 class ParlviewIE(InfoExtractor):
  10     _WORKING = False
  11     _VALID_URL = r'https?://(?:www\.)?parlview\.aph\.gov\.au/(?:[^/]+)?\bvideoID=(?P<id>\d{6})'
  12     _TESTS = [{
  13         'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=542661',
  14         'info_dict': {
  15             'id': '542661',
  16             'ext': 'mp4',
  17             'title': "Australia's Family Law System [Part 2]",
  18             'duration': 5799,
  19             'description': 'md5:7099883b391619dbae435891ca871a62',
  20             'timestamp': 1621430700,
  21             'upload_date': '20210519',
  22             'uploader': 'Joint Committee',
  23         },
  24         'params': {
  25             'skip_download': True,
  26         },
  27     }, {
  28         'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=539936',
  29         'only_matching': True,
  30     }]
  31     _API_URL = 'https://parlview.aph.gov.au/api_v3/1/playback/getUniversalPlayerConfig?videoID=%s&format=json'
  32     _MEDIA_INFO_URL = 'https://parlview.aph.gov.au/ajaxPlayer.php?videoID=%s&tabNum=4&action=loadTab'
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         webpage = self._download_webpage(url, video_id)
  37         media = self._download_json(self._API_URL % video_id, video_id).get('media')
  38         timestamp = try_get(media, lambda x: x['timeMap']['source']['timecode_offsets'][0], str) or '/'
  39
  40         stream = try_get(media, lambda x: x['renditions'][0], dict)
  41         if not stream:
  42             self.raise_no_formats('No streams were detected')
  43         elif stream.get('streamType') != 'VOD':
  44             self.raise_no_formats('Unknown type of stream was detected: "{}"'.format(str(stream.get('streamType'))))
  45         formats = self._extract_m3u8_formats(stream['url'], video_id, 'mp4', 'm3u8_native')
  46
  47         media_info = self._download_webpage(
  48             self._MEDIA_INFO_URL % video_id, video_id, note='Downloading media info', fatal=False)
  49
  50         return {
  51             'id': video_id,
  52             'url': url,
  53             'title': self._html_search_regex(r'<h2>([^<]+)<', webpage, 'title', fatal=False),
  54             'formats': formats,
  55             'duration': int_or_none(media.get('duration')),
  56             'timestamp': unified_timestamp(timestamp.split('/', 1)[1].replace('_', ' ')),
  57             'description': self._html_search_regex(
  58                 r'<div[^>]+class="descripti?on"[^>]*>[^>]+<strong>[^>]+>[^>]+>([^<]+)',
  59                 webpage, 'description', fatal=False),
  60             'uploader': self._html_search_regex(
  61                 r'<td>[^>]+>Channel:[^>]+>([^<]+)', media_info, 'channel', fatal=False),
  62             'thumbnail': media.get('staticImage'),
  63         }