Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pornotube.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..utils import int_or_none
   7
   8
   9 class PornotubeIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com/(?:[^?#]*?)/video/(?P<id>[0-9]+)'
  11     _TEST = {
  12         'url': 'http://www.pornotube.com/orientation/straight/video/4964/title/weird-hot-and-wet-science',
  13         'md5': '60fc5a4f0d93a97968fc7999d98260c9',
  14         'info_dict': {
  15             'id': '4964',
  16             'ext': 'mp4',
  17             'upload_date': '20141203',
  18             'title': 'Weird Hot and Wet Science',
  19             'description': 'md5:a8304bef7ef06cb4ab476ca6029b01b0',
  20             'categories': ['Adult Humor', 'Blondes'],
  21             'uploader': 'Alpha Blue Archives',
  22             'thumbnail': 're:^https?://.*\\.jpg$',
  23             'timestamp': 1417582800,
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         token = self._download_json(
  32             'https://api.aebn.net/auth/v2/origins/authenticate',
  33             video_id, note='Downloading token',
  34             data=json.dumps({'credentials': 'Clip Application'}).encode('utf-8'),
  35             headers={
  36                 'Content-Type': 'application/json',
  37                 'Origin': 'http://www.pornotube.com',
  38             })['tokenKey']
  39
  40         video_url = self._download_json(
  41             'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id,
  42             video_id, note='Downloading delivery information',
  43             headers={'Authorization': token})['mediaUrl']
  44
  45         FIELDS = (
  46             'title', 'description', 'startSecond', 'endSecond', 'publishDate',
  47             'studios{name}', 'categories{name}', 'movieId', 'primaryImageNumber'
  48         )
  49
  50         info = self._download_json(
  51             'https://api.aebn.net/content/v2/clips/%s?fields=%s'
  52             % (video_id, ','.join(FIELDS)), video_id,
  53             note='Downloading metadata',
  54             headers={'Authorization': token})
  55
  56         if isinstance(info, list):
  57             info = info[0]
  58
  59         title = info['title']
  60
  61         timestamp = int_or_none(info.get('publishDate'), scale=1000)
  62         uploader = info.get('studios', [{}])[0].get('name')
  63         movie_id = info.get('movieId')
  64         primary_image_number = info.get('primaryImageNumber')
  65         thumbnail = None
  66         if movie_id and primary_image_number:
  67             thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % (
  68                 movie_id, movie_id, primary_image_number)
  69         start = int_or_none(info.get('startSecond'))
  70         end = int_or_none(info.get('endSecond'))
  71         duration = end - start if start and end else None
  72         categories = [c['name'] for c in info.get('categories', []) if c.get('name')]
  73
  74         return {
  75             'id': video_id,
  76             'url': video_url,
  77             'title': title,
  78             'description': info.get('description'),
  79             'duration': duration,
  80             'timestamp': timestamp,
  81             'uploader': uploader,
  82             'thumbnail': thumbnail,
  83             'categories': categories,
  84             'age_limit': 18,
  85         }