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             'https://api.beeg.com/api/v5/video/%s' % video_id, video_id)
  38
  39         def split(o, e):
  40             def cut(s, x):
  41                 n.append(s[:x])
  42                 return s[x:]
  43             n = []
  44             r = len(o) % e
  45             if r > 0:
  46                 o = cut(o, r)
  47             while len(o) > e:
  48                 o = cut(o, e)
  49             n.append(o)
  50             return n
  51
  52         def decrypt_key(key):
  53             # Reverse engineered from http://static.beeg.com/cpl/1105.js
  54             a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB'
  55             e = compat_urllib_parse_unquote(key)
  56             o = ''.join([
  57                 compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
  58                 for n in range(len(e))])
  59             return ''.join(split(o, 3)[::-1])
  60
  61         def decrypt_url(encrypted_url):
  62             encrypted_url = self._proto_relative_url(
  63                 encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
  64             key = self._search_regex(
  65                 r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
  66             if not key:
  67                 return encrypted_url
  68             return encrypted_url.replace(key, decrypt_key(key))
  69
  70         formats = []
  71         for format_id, video_url in video.items():
  72             if not video_url:
  73                 continue
  74             height = self._search_regex(
  75                 r'^(\d+)[pP]$', format_id, 'height', default=None)
  76             if not height:
  77                 continue
  78             formats.append({
  79                 'url': decrypt_url(video_url),
  80                 'format_id': format_id,
  81                 'height': int(height),
  82             })
  83         self._sort_formats(formats)
  84
  85         title = video['title']
  86         video_id = video.get('id') or video_id
  87         display_id = video.get('code')
  88         description = video.get('desc')
  89
  90         timestamp = parse_iso8601(video.get('date'), ' ')
  91         duration = int_or_none(video.get('duration'))
  92
  93         tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
  94
  95         return {
  96             'id': video_id,
  97             'display_id': display_id,
  98             'title': title,
  99             'description': description,
 100             'timestamp': timestamp,
 101             'duration': duration,
 102             'tags': tags,
 103             'formats': formats,
 104             'age_limit': 18,
 105         }