yt_dlp/extractor/parlview.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     int_or_none,
   5     try_get,
   6     unified_timestamp,
   7 )
   8
   9
  10 class ParlviewIE(InfoExtractor):
  11
  12     _VALID_URL = r'https?://(?:www\.)?parlview\.aph\.gov\.au/(?:[^/]+)?\bvideoID=(?P<id>\d{6})'
  13     _TESTS = [{
  14         'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=542661',
  15         'info_dict': {
  16             'id': '542661',
  17             'ext': 'mp4',
  18             'title': "Australia's Family Law System [Part 2]",
  19             'duration': 5799,
  20             'description': 'md5:7099883b391619dbae435891ca871a62',
  21             'timestamp': 1621430700,
  22             'upload_date': '20210519',
  23             'uploader': 'Joint Committee',
  24         },
  25         'params': {
  26             'skip_download': True,
  27         }
  28     }, {
  29         'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=539936',
  30         'only_matching': True,
  31     }]
  32     _API_URL = 'https://parlview.aph.gov.au/api_v3/1/playback/getUniversalPlayerConfig?videoID=%s&format=json'
  33     _MEDIA_INFO_URL = 'https://parlview.aph.gov.au/ajaxPlayer.php?videoID=%s&tabNum=4&action=loadTab'
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37         webpage = self._download_webpage(url, video_id)
  38         media = self._download_json(self._API_URL % video_id, video_id).get('media')
  39         timestamp = try_get(media, lambda x: x['timeMap']['source']['timecode_offsets'][0], compat_str) or '/'
  40
  41         stream = try_get(media, lambda x: x['renditions'][0], dict)
  42         if not stream:
  43             self.raise_no_formats('No streams were detected')
  44         elif stream.get('streamType') != 'VOD':
  45             self.raise_no_formats('Unknown type of stream was detected: "%s"' % str(stream.get('streamType')))
  46         formats = self._extract_m3u8_formats(stream['url'], video_id, 'mp4', 'm3u8_native')
  47         self._sort_formats(formats)
  48
  49         media_info = self._download_webpage(
  50             self._MEDIA_INFO_URL % video_id, video_id, note='Downloading media info', fatal=False)
  51
  52         return {
  53             'id': video_id,
  54             'url': url,
  55             'title': self._html_search_regex(r'<h2>([^<]+)<', webpage, 'title', fatal=False),
  56             'formats': formats,
  57             'duration': int_or_none(media.get('duration')),
  58             'timestamp': unified_timestamp(timestamp.split('/', 1)[1].replace('_', ' ')),
  59             'description': self._html_search_regex(
  60                 r'<div[^>]+class="descripti?on"[^>]*>[^>]+<strong>[^>]+>[^>]+>([^<]+)',
  61                 webpage, 'description', fatal=False),
  62             'uploader': self._html_search_regex(
  63                 r'<td>[^>]+>Channel:[^>]+>([^<]+)', media_info, 'channel', fatal=False),
  64             'thumbnail': media.get('staticImage'),
  65         }