yt_dlp/extractor/pornotube.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class PornotubeIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com/(?:[^?#]*?)/video/(?P<id>[0-9]+)'
   9     _TEST = {
  10         'url': 'http://www.pornotube.com/orientation/straight/video/4964/title/weird-hot-and-wet-science',
  11         'md5': '60fc5a4f0d93a97968fc7999d98260c9',
  12         'info_dict': {
  13             'id': '4964',
  14             'ext': 'mp4',
  15             'upload_date': '20141203',
  16             'title': 'Weird Hot and Wet Science',
  17             'description': 'md5:a8304bef7ef06cb4ab476ca6029b01b0',
  18             'categories': ['Adult Humor', 'Blondes'],
  19             'uploader': 'Alpha Blue Archives',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21             'timestamp': 1417582800,
  22             'age_limit': 18,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         token = self._download_json(
  30             'https://api.aebn.net/auth/v2/origins/authenticate',
  31             video_id, note='Downloading token',
  32             data=json.dumps({'credentials': 'Clip Application'}).encode('utf-8'),
  33             headers={
  34                 'Content-Type': 'application/json',
  35                 'Origin': 'http://www.pornotube.com',
  36             })['tokenKey']
  37
  38         video_url = self._download_json(
  39             'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id,
  40             video_id, note='Downloading delivery information',
  41             headers={'Authorization': token})['mediaUrl']
  42
  43         FIELDS = (
  44             'title', 'description', 'startSecond', 'endSecond', 'publishDate',
  45             'studios{name}', 'categories{name}', 'movieId', 'primaryImageNumber'
  46         )
  47
  48         info = self._download_json(
  49             'https://api.aebn.net/content/v2/clips/%s?fields=%s'
  50             % (video_id, ','.join(FIELDS)), video_id,
  51             note='Downloading metadata',
  52             headers={'Authorization': token})
  53
  54         if isinstance(info, list):
  55             info = info[0]
  56
  57         title = info['title']
  58
  59         timestamp = int_or_none(info.get('publishDate'), scale=1000)
  60         uploader = info.get('studios', [{}])[0].get('name')
  61         movie_id = info.get('movieId')
  62         primary_image_number = info.get('primaryImageNumber')
  63         thumbnail = None
  64         if movie_id and primary_image_number:
  65             thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % (
  66                 movie_id, movie_id, primary_image_number)
  67         start = int_or_none(info.get('startSecond'))
  68         end = int_or_none(info.get('endSecond'))
  69         duration = end - start if start and end else None
  70         categories = [c['name'] for c in info.get('categories', []) if c.get('name')]
  71
  72         return {
  73             'id': video_id,
  74             'url': video_url,
  75             'title': title,
  76             'description': info.get('description'),
  77             'duration': duration,
  78             'timestamp': timestamp,
  79             'uploader': uploader,
  80             'thumbnail': thumbnail,
  81             'categories': categories,
  82             'age_limit': 18,
  83         }