yt_dlp/extractor/meta.py

   1 from .common import InfoExtractor
   2 from .pladform import PladformIE
   3 from ..utils import (
   4     unescapeHTML,
   5     int_or_none,
   6     ExtractorError,
   7 )
   8
   9
  10 class METAIE(InfoExtractor):
  11     _VALID_URL = r'https?://video\.meta\.ua/(?:iframe/)?(?P<id>[0-9]+)'
  12     _TESTS = [{
  13         'url': 'http://video.meta.ua/5502115.video',
  14         'md5': '71b6f3ee274bef16f1ab410f7f56b476',
  15         'info_dict': {
  16             'id': '5502115',
  17             'ext': 'mp4',
  18             'title': 'Sony Xperia Z camera test [HQ]',
  19             'description': 'Xperia Z shoots video in FullHD HDR.',
  20             'uploader_id': 'nomobile',
  21             'uploader': 'CHЁZA.TV',
  22             'upload_date': '20130211',
  23         },
  24         'add_ie': ['Youtube'],
  25     }, {
  26         'url': 'http://video.meta.ua/iframe/5502115',
  27         'only_matching': True,
  28     }, {
  29         # pladform embed
  30         'url': 'http://video.meta.ua/7121015.video',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         webpage = self._download_webpage(url, video_id)
  37
  38         st_html5 = self._search_regex(
  39             r"st_html5\s*=\s*'#([^']+)'", webpage, 'uppod html5 st', default=None)
  40
  41         if st_html5:
  42             # uppod st decryption algorithm is reverse engineered from function un(s) at uppod.js
  43             json_str = ''
  44             for i in range(0, len(st_html5), 3):
  45                 json_str += '&#x0%s;' % st_html5[i:i + 3]
  46             uppod_data = self._parse_json(unescapeHTML(json_str), video_id)
  47             error = uppod_data.get('customnotfound')
  48             if error:
  49                 raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
  50
  51             video_url = uppod_data['file']
  52             info = {
  53                 'id': video_id,
  54                 'url': video_url,
  55                 'title': uppod_data.get('comment') or self._og_search_title(webpage),
  56                 'description': self._og_search_description(webpage, default=None),
  57                 'thumbnail': uppod_data.get('poster') or self._og_search_thumbnail(webpage),
  58                 'duration': int_or_none(self._og_search_property(
  59                     'video:duration', webpage, default=None)),
  60             }
  61             if 'youtube.com/' in video_url:
  62                 info.update({
  63                     '_type': 'url_transparent',
  64                     'ie_key': 'Youtube',
  65                 })
  66             return info
  67
  68         pladform_url = PladformIE._extract_url(webpage)
  69         if pladform_url:
  70             return self.url_result(pladform_url)