youtube_dl/extractor/beeg.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     int_or_none,
   7     unified_timestamp,
   8 )
   9
  10
  11 class BeegIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
  13     _TESTS = [{
  14         'url': 'http://beeg.com/5416503',
  15         'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
  16         'info_dict': {
  17             'id': '5416503',
  18             'ext': 'mp4',
  19             'title': 'Sultry Striptease',
  20             'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
  21             'timestamp': 1391813355,
  22             'upload_date': '20140207',
  23             'duration': 383,
  24             'tags': list,
  25             'age_limit': 18,
  26         }
  27     }, {
  28         'url': 'https://beeg.porn/video/5416503',
  29         'only_matching': True,
  30     }, {
  31         'url': 'https://beeg.porn/5416503',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(url, video_id)
  39
  40         beeg_version = self._search_regex(
  41             r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
  42             default='1546225636701')
  43
  44         for api_path in ('', 'api.'):
  45             video = self._download_json(
  46                 'https://%sbeeg.com/api/v6/%s/video/%s'
  47                 % (api_path, beeg_version, video_id), video_id,
  48                 fatal=api_path == 'api.')
  49             if video:
  50                 break
  51
  52         formats = []
  53         for format_id, video_url in video.items():
  54             if not video_url:
  55                 continue
  56             height = self._search_regex(
  57                 r'^(\d+)[pP]$', format_id, 'height', default=None)
  58             if not height:
  59                 continue
  60             formats.append({
  61                 'url': self._proto_relative_url(
  62                     video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
  63                 'format_id': format_id,
  64                 'height': int(height),
  65             })
  66         self._sort_formats(formats)
  67
  68         title = video['title']
  69         video_id = compat_str(video.get('id') or video_id)
  70         display_id = video.get('code')
  71         description = video.get('desc')
  72         series = video.get('ps_name')
  73
  74         timestamp = unified_timestamp(video.get('date'))
  75         duration = int_or_none(video.get('duration'))
  76
  77         tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
  78
  79         return {
  80             'id': video_id,
  81             'display_id': display_id,
  82             'title': title,
  83             'description': description,
  84             'series': series,
  85             'timestamp': timestamp,
  86             'duration': duration,
  87             'tags': tags,
  88             'formats': formats,
  89             'age_limit': self._rta_search(webpage),
  90         }