youtube_dl/extractor/beeg.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_chr,
   6     compat_ord,
   7     compat_urllib_parse_unquote,
   8 )
   9 from ..utils import (
  10     int_or_none,
  11     parse_iso8601,
  12 )
  13
  14
  15 class BeegIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
  17     _TEST = {
  18         'url': 'http://beeg.com/5416503',
  19         'md5': '46c384def73b33dbc581262e5ee67cef',
  20         'info_dict': {
  21             'id': '5416503',
  22             'ext': 'mp4',
  23             'title': 'Sultry Striptease',
  24             'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
  25             'timestamp': 1391813355,
  26             'upload_date': '20140207',
  27             'duration': 383,
  28             'tags': list,
  29             'age_limit': 18,
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         video = self._download_json(
  37             'http://beeg.com/api/v4/video/%s' % video_id, video_id)
  38
  39         def decrypt_key(key):
  40             # Reverse engineered from http://static.beeg.com/cpl/1067.js
  41             a = '8RPUUCS35ZWp3ADnKcSmpH71ZusrROo'
  42             e = compat_urllib_parse_unquote(key)
  43             return ''.join([
  44                 compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 25)
  45                 for n in range(len(e))])
  46
  47         def decrypt_url(encrypted_url):
  48             encrypted_url = self._proto_relative_url(
  49                 encrypted_url.replace('{DATA_MARKERS}', ''), 'http:')
  50             key = self._search_regex(
  51                 r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
  52             if not key:
  53                 return encrypted_url
  54             return encrypted_url.replace(key, decrypt_key(key))
  55
  56         formats = []
  57         for format_id, video_url in video.items():
  58             if not video_url:
  59                 continue
  60             height = self._search_regex(
  61                 r'^(\d+)[pP]$', format_id, 'height', default=None)
  62             if not height:
  63                 continue
  64             formats.append({
  65                 'url': decrypt_url(video_url),
  66                 'format_id': format_id,
  67                 'height': int(height),
  68             })
  69         self._sort_formats(formats)
  70
  71         title = video['title']
  72         video_id = video.get('id') or video_id
  73         display_id = video.get('code')
  74         description = video.get('desc')
  75
  76         timestamp = parse_iso8601(video.get('date'), ' ')
  77         duration = int_or_none(video.get('duration'))
  78
  79         tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
  80
  81         return {
  82             'id': video_id,
  83             'display_id': display_id,
  84             'title': title,
  85             'description': description,
  86             'timestamp': timestamp,
  87             'duration': duration,
  88             'tags': tags,
  89             'formats': formats,
  90             'age_limit': 18,
  91         }