34735c51e19c7dbbb1c07f2fc4a203df4dda70a9
[youtube-dl] / youtube_dl / extractor / pornotube.py
1 from __future__ import unicode_literals
2
3 import json
4
5 from .common import InfoExtractor
6 from ..compat import (
7     compat_urllib_request,
8 )
9 from ..utils import (
10     int_or_none,
11 )
12
13
14 class PornotubeIE(InfoExtractor):
15     _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com/(?:[^?#]*?)/video/(?P<id>[0-9]+)'
16     _TEST = {
17         'url': 'http://www.pornotube.com/orientation/straight/video/4964/title/weird-hot-and-wet-science',
18         'md5': '60fc5a4f0d93a97968fc7999d98260c9',
19         'info_dict': {
20             'id': '4964',
21             'ext': 'mp4',
22             'upload_date': '20141203',
23             'title': 'Weird Hot and Wet Science',
24             'description': 'md5:a8304bef7ef06cb4ab476ca6029b01b0',
25             'categories': ['Adult Humor', 'Blondes'],
26             'uploader': 'Alpha Blue Archives',
27             'thumbnail': 're:^https?://.*\\.jpg$',
28             'timestamp': 1417582800,
29             'age_limit': 18,
30         }
31     }
32
33     def _real_extract(self, url):
34         video_id = self._match_id(url)
35
36         # Fetch origin token
37         js_config = self._download_webpage(
38             'http://www.pornotube.com/assets/src/app/config.js', video_id,
39             note='Download JS config')
40         originAuthenticationSpaceKey = self._search_regex(
41             r"constant\('originAuthenticationSpaceKey',\s*'([^']+)'",
42             js_config, 'originAuthenticationSpaceKey')
43
44         # Fetch actual token
45         token_req_data = {
46             'authenticationSpaceKey': originAuthenticationSpaceKey,
47             'credentials': 'Clip Application',
48         }
49         token_req = compat_urllib_request.Request(
50             'https://api.aebn.net/auth/v1/token/primal',
51             data=json.dumps(token_req_data).encode('utf-8'))
52         token_req.add_header('Content-Type', 'application/json')
53         token_req.add_header('Origin', 'http://www.pornotube.com')
54         token_answer = self._download_json(
55             token_req, video_id, note='Requesting primal token')
56         token = token_answer['tokenKey']
57
58         # Get video URL
59         delivery_req = compat_urllib_request.Request(
60             'https://api.aebn.net/delivery/v1/clips/%s/MP4' % video_id)
61         delivery_req.add_header('Authorization', token)
62         delivery_info = self._download_json(
63             delivery_req, video_id, note='Downloading delivery information')
64         video_url = delivery_info['mediaUrl']
65
66         # Get additional info (title etc.)
67         info_req = compat_urllib_request.Request(
68             'https://api.aebn.net/content/v1/clips/%s?expand='
69             'title,description,primaryImageNumber,startSecond,endSecond,'
70             'movie.title,movie.MovieId,movie.boxCoverFront,movie.stars,'
71             'movie.studios,stars.name,studios.name,categories.name,'
72             'clipActive,movieActive,publishDate,orientations' % video_id)
73         info_req.add_header('Authorization', token)
74         info = self._download_json(
75             info_req, video_id, note='Downloading metadata')
76
77         timestamp = int_or_none(info.get('publishDate'), scale=1000)
78         uploader = info.get('studios', [{}])[0].get('name')
79         movie_id = info['movie']['movieId']
80         thumbnail = 'http://pic.aebn.net/dis/t/%s/%s_%08d.jpg' % (
81             movie_id, movie_id, info['primaryImageNumber'])
82         categories = [c['name'] for c in info.get('categories')]
83
84         return {
85             'id': video_id,
86             'url': video_url,
87             'title': info['title'],
88             'description': info.get('description'),
89             'timestamp': timestamp,
90             'uploader': uploader,
91             'thumbnail': thumbnail,
92             'categories': categories,
93             'age_limit': 18,
94         }