Raphaël G. Git Repositories - youtubedl/blob - 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/(?P<id>\d+)'
  13     _TEST = {
  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
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         beeg_version = self._search_regex(
  35             r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
  36             default='1546225636701')
  37
  38         for api_path in ('', 'api.'):
  39             video = self._download_json(
  40                 'https://%sbeeg.com/api/v6/%s/video/%s'
  41                 % (api_path, beeg_version, video_id), video_id,
  42                 fatal=api_path == 'api.')
  43             if video:
  44                 break
  45
  46         formats = []
  47         for format_id, video_url in video.items():
  48             if not video_url:
  49                 continue
  50             height = self._search_regex(
  51                 r'^(\d+)[pP]$', format_id, 'height', default=None)
  52             if not height:
  53                 continue
  54             formats.append({
  55                 'url': self._proto_relative_url(
  56                     video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
  57                 'format_id': format_id,
  58                 'height': int(height),
  59             })
  60         self._sort_formats(formats)
  61
  62         title = video['title']
  63         video_id = compat_str(video.get('id') or video_id)
  64         display_id = video.get('code')
  65         description = video.get('desc')
  66         series = video.get('ps_name')
  67
  68         timestamp = unified_timestamp(video.get('date'))
  69         duration = int_or_none(video.get('duration'))
  70
  71         tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
  72
  73         return {
  74             'id': video_id,
  75             'display_id': display_id,
  76             'title': title,
  77             'description': description,
  78             'series': series,
  79             'timestamp': timestamp,
  80             'duration': duration,
  81             'tags': tags,
  82             'formats': formats,
  83             'age_limit': self._rta_search(webpage),
  84         }