yt_dlp/extractor/beeg.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     str_or_none,
   5     traverse_obj,
   6     try_get,
   7     unified_timestamp,
   8 )
   9
  10
  11 class BeegIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com(?:/video)?)/-?(?P<id>\d+)'
  13     _TESTS = [{
  14         'url': 'https://beeg.com/-0983946056129650',
  15         'md5': '51d235147c4627cfce884f844293ff88',
  16         'info_dict': {
  17             'id': '0983946056129650',
  18             'ext': 'mp4',
  19             'title': 'sucked cock and fucked in a private plane',
  20             'duration': 927,
  21             'tags': list,
  22             'age_limit': 18,
  23             'upload_date': '20220131',
  24             'timestamp': 1643656455,
  25             'display_id': '2540839',
  26         }
  27     }, {
  28         'url': 'https://beeg.com/-0599050563103750?t=4-861',
  29         'md5': 'bd8b5ea75134f7f07fad63008db2060e',
  30         'info_dict': {
  31             'id': '0599050563103750',
  32             'ext': 'mp4',
  33             'title': 'Bad Relatives',
  34             'duration': 2060,
  35             'tags': list,
  36             'age_limit': 18,
  37             'description': 'md5:b4fc879a58ae6c604f8f259155b7e3b9',
  38             'timestamp': 1643623200,
  39             'display_id': '2569965',
  40             'upload_date': '20220131',
  41         }
  42     }, {
  43         # api/v6 v2
  44         'url': 'https://beeg.com/1941093077?t=911-1391',
  45         'only_matching': True,
  46     }, {
  47         # api/v6 v2 w/o t
  48         'url': 'https://beeg.com/1277207756',
  49         'only_matching': True,
  50     }]
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54
  55         webpage = self._download_webpage(url, video_id)
  56
  57         video = self._download_json(
  58             'https://store.externulls.com/facts/file/%s' % video_id,
  59             video_id, 'Downloading JSON for %s' % video_id)
  60
  61         fc_facts = video.get('fc_facts')
  62         first_fact = {}
  63         for fact in fc_facts:
  64             if not first_fact or try_get(fact, lambda x: x['id'] < first_fact['id']):
  65                 first_fact = fact
  66
  67         resources = traverse_obj(video, ('file', 'hls_resources')) or first_fact.get('hls_resources')
  68
  69         formats = []
  70         for format_id, video_uri in resources.items():
  71             if not video_uri:
  72                 continue
  73             height = int_or_none(self._search_regex(r'fl_cdn_(\d+)', format_id, 'height', default=None))
  74             current_formats = self._extract_m3u8_formats(f'https://video.beeg.com/{video_uri}', video_id, ext='mp4', m3u8_id=str(height))
  75             for f in current_formats:
  76                 f['height'] = height
  77             formats.extend(current_formats)
  78
  79         return {
  80             'id': video_id,
  81             'display_id': str_or_none(first_fact.get('id')),
  82             'title': traverse_obj(video, ('file', 'stuff', 'sf_name')),
  83             'description': traverse_obj(video, ('file', 'stuff', 'sf_story')),
  84             'timestamp': unified_timestamp(first_fact.get('fc_created')),
  85             'duration': int_or_none(traverse_obj(video, ('file', 'fl_duration'))),
  86             'tags': traverse_obj(video, ('tags', ..., 'tg_name')),
  87             'formats': formats,
  88             'age_limit': self._rta_search(webpage),
  89         }