yt_dlp/extractor/vzaar.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     int_or_none,
   7     float_or_none,
   8     unified_timestamp,
   9     url_or_none,
  10 )
  11
  12
  13 class VzaarIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)'
  15     _TESTS = [{
  16         # HTTP and HLS
  17         'url': 'https://vzaar.com/videos/1152805',
  18         'md5': 'bde5ddfeb104a6c56a93a06b04901dbf',
  19         'info_dict': {
  20             'id': '1152805',
  21             'ext': 'mp4',
  22             'title': 'sample video (public)',
  23         },
  24     }, {
  25         'url': 'https://view.vzaar.com/27272/player',
  26         'md5': '3b50012ac9bbce7f445550d54e0508f2',
  27         'info_dict': {
  28             'id': '27272',
  29             'ext': 'mp3',
  30             'title': 'MP3',
  31         },
  32     }, {
  33         # hlsAes = true
  34         'url': 'https://view.vzaar.com/11379930/player',
  35         'info_dict': {
  36             'id': '11379930',
  37             'ext': 'mp4',
  38             'title': 'Videoaula',
  39         },
  40         'params': {
  41             # m3u8 download
  42             'skip_download': True,
  43         },
  44     }, {
  45         # with null videoTitle
  46         'url': 'https://view.vzaar.com/20313539/download',
  47         'only_matching': True,
  48     }]
  49
  50     @staticmethod
  51     def _extract_urls(webpage):
  52         return re.findall(
  53             r'<iframe[^>]+src=["\']((?:https?:)?//(?:view\.vzaar\.com)/[0-9]+)',
  54             webpage)
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58         video_data = self._download_json(
  59             'http://view.vzaar.com/v2/%s/video' % video_id, video_id)
  60
  61         title = video_data.get('videoTitle') or video_id
  62
  63         formats = []
  64
  65         source_url = url_or_none(video_data.get('sourceUrl'))
  66         if source_url:
  67             f = {
  68                 'url': source_url,
  69                 'format_id': 'http',
  70                 'quality': 1,
  71             }
  72             if 'audio' in source_url:
  73                 f.update({
  74                     'vcodec': 'none',
  75                     'ext': 'mp3',
  76                 })
  77             else:
  78                 f.update({
  79                     'width': int_or_none(video_data.get('width')),
  80                     'height': int_or_none(video_data.get('height')),
  81                     'ext': 'mp4',
  82                     'fps': float_or_none(video_data.get('fps')),
  83                 })
  84             formats.append(f)
  85
  86         video_guid = video_data.get('guid')
  87         usp = video_data.get('usp')
  88         if video_data.get('uspEnabled') and isinstance(video_guid, compat_str) and isinstance(usp, dict):
  89             hls_aes = video_data.get('hlsAes')
  90             qs = '&'.join('%s=%s' % (k, v) for k, v in usp.items())
  91             url_templ = 'http://%%s.vzaar.com/v5/usp%s/%s/%s.ism%%s?' % ('aes' if hls_aes else '', video_guid, video_id)
  92             m3u8_formats = self._extract_m3u8_formats(
  93                 url_templ % ('fable', '/.m3u8') + qs, video_id, 'mp4', 'm3u8_native',
  94                 m3u8_id='hls', fatal=False)
  95             if hls_aes:
  96                 for f in m3u8_formats:
  97                     f['_decryption_key_url'] = url_templ % ('goose', '') + qs
  98             formats.extend(m3u8_formats)
  99
 100         self._sort_formats(formats)
 101
 102         return {
 103             'id': video_id,
 104             'title': title,
 105             'thumbnail': self._proto_relative_url(video_data.get('poster')),
 106             'duration': float_or_none(video_data.get('videoDuration')),
 107             'timestamp': unified_timestamp(video_data.get('ts')),
 108             'formats': formats,
 109         }