yt_dlp/extractor/daftsex.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_b64decode
   6 from ..utils import (
   7     get_elements_by_class,
   8     int_or_none,
   9     js_to_json,
  10     parse_count,
  11     parse_duration,
  12     try_get,
  13 )
  14
  15
  16 class DaftsexIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?daftsex\.com/watch/(?P<id>-?\d+_\d+)'
  18     _TESTS = [{
  19         'url': 'https://daftsex.com/watch/-156601359_456242791',
  20         'info_dict': {
  21             'id': '-156601359_456242791',
  22             'ext': 'mp4',
  23             'title': 'Skye Blue - Dinner And A Show',
  24         },
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30         title = get_elements_by_class('heading', webpage)[-1]
  31         duration = parse_duration(self._search_regex(
  32             r'Duration: ((?:[0-9]{2}:){0,2}[0-9]{2})',
  33             webpage, 'duration', fatal=False))
  34         views = parse_count(self._search_regex(
  35             r'Views: ([0-9 ]+)',
  36             webpage, 'views', fatal=False))
  37
  38         player_hash = self._search_regex(
  39             r'DaxabPlayer\.Init\({[\s\S]*hash:\s*"([0-9a-zA-Z_\-]+)"[\s\S]*}',
  40             webpage, 'player hash')
  41         player_color = self._search_regex(
  42             r'DaxabPlayer\.Init\({[\s\S]*color:\s*"([0-9a-z]+)"[\s\S]*}',
  43             webpage, 'player color', fatal=False) or ''
  44
  45         embed_page = self._download_webpage(
  46             'https://daxab.com/player/%s?color=%s' % (player_hash, player_color),
  47             video_id, headers={'Referer': url})
  48         video_params = self._parse_json(
  49             self._search_regex(
  50                 r'window\.globParams\s*=\s*({[\S\s]+})\s*;\s*<\/script>',
  51                 embed_page, 'video parameters'),
  52             video_id, transform_source=js_to_json)
  53
  54         server_domain = 'https://%s' % compat_b64decode(video_params['server'][::-1]).decode('utf-8')
  55         formats = []
  56         for format_id, format_data in video_params['video']['cdn_files'].items():
  57             ext, height = format_id.split('_')
  58             extra_quality_data = format_data.split('.')[-1]
  59             url = f'{server_domain}/videos/{video_id.replace("_", "/")}/{height}.mp4?extra={extra_quality_data}'
  60             formats.append({
  61                 'format_id': format_id,
  62                 'url': url,
  63                 'height': int_or_none(height),
  64                 'ext': ext,
  65             })
  66         self._sort_formats(formats)
  67
  68         thumbnail = try_get(video_params,
  69                             lambda vi: 'https:' + compat_b64decode(vi['video']['thumb']).decode('utf-8'))
  70
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'formats': formats,
  75             'duration': duration,
  76             'thumbnail': thumbnail,
  77             'view_count': views,
  78             'age_limit': 18,
  79         }