yt_dlp/extractor/vzaar.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     int_or_none,
   5     float_or_none,
   6     unified_timestamp,
   7     url_or_none,
   8 )
   9
  10
  11 class VzaarIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)'
  13     _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//(?:view\.vzaar\.com)/[0-9]+)']
  14     _TESTS = [{
  15         # HTTP and HLS
  16         'url': 'https://vzaar.com/videos/1152805',
  17         'md5': 'bde5ddfeb104a6c56a93a06b04901dbf',
  18         'info_dict': {
  19             'id': '1152805',
  20             'ext': 'mp4',
  21             'title': 'sample video (public)',
  22         },
  23     }, {
  24         'url': 'https://view.vzaar.com/27272/player',
  25         'md5': '3b50012ac9bbce7f445550d54e0508f2',
  26         'info_dict': {
  27             'id': '27272',
  28             'ext': 'mp3',
  29             'title': 'MP3',
  30         },
  31     }, {
  32         # hlsAes = true
  33         'url': 'https://view.vzaar.com/11379930/player',
  34         'info_dict': {
  35             'id': '11379930',
  36             'ext': 'mp4',
  37             'title': 'Videoaula',
  38         },
  39         'params': {
  40             # m3u8 download
  41             'skip_download': True,
  42         },
  43     }, {
  44         # with null videoTitle
  45         'url': 'https://view.vzaar.com/20313539/download',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_extract(self, url):
  50         video_id = self._match_id(url)
  51         video_data = self._download_json(
  52             'http://view.vzaar.com/v2/%s/video' % video_id, video_id)
  53
  54         title = video_data.get('videoTitle') or video_id
  55
  56         formats = []
  57
  58         source_url = url_or_none(video_data.get('sourceUrl'))
  59         if source_url:
  60             f = {
  61                 'url': source_url,
  62                 'format_id': 'http',
  63                 'quality': 1,
  64             }
  65             if 'audio' in source_url:
  66                 f.update({
  67                     'vcodec': 'none',
  68                     'ext': 'mp3',
  69                 })
  70             else:
  71                 f.update({
  72                     'width': int_or_none(video_data.get('width')),
  73                     'height': int_or_none(video_data.get('height')),
  74                     'ext': 'mp4',
  75                     'fps': float_or_none(video_data.get('fps')),
  76                 })
  77             formats.append(f)
  78
  79         video_guid = video_data.get('guid')
  80         usp = video_data.get('usp')
  81         if video_data.get('uspEnabled') and isinstance(video_guid, compat_str) and isinstance(usp, dict):
  82             hls_aes = video_data.get('hlsAes')
  83             qs = '&'.join('%s=%s' % (k, v) for k, v in usp.items())
  84             url_templ = 'http://%%s.vzaar.com/v5/usp%s/%s/%s.ism%%s?' % ('aes' if hls_aes else '', video_guid, video_id)
  85             m3u8_formats = self._extract_m3u8_formats(
  86                 url_templ % ('fable', '/.m3u8') + qs, video_id, 'mp4', 'm3u8_native',
  87                 m3u8_id='hls', fatal=False)
  88             if hls_aes:
  89                 for f in m3u8_formats:
  90                     f['_decryption_key_url'] = url_templ % ('goose', '') + qs
  91             formats.extend(m3u8_formats)
  92
  93         self._sort_formats(formats)
  94
  95         return {
  96             'id': video_id,
  97             'title': title,
  98             'thumbnail': self._proto_relative_url(video_data.get('poster')),
  99             'duration': float_or_none(video_data.get('videoDuration')),
 100             'timestamp': unified_timestamp(video_data.get('ts')),
 101             'formats': formats,
 102         }