]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/tube8.py
Merge pull request #2340 from Fnordlab/master
[youtube-dl.git] / youtube_dl / extractor / tube8.py
1 import os
2 import re
3
4 from .common import InfoExtractor
5 from ..utils import (
6     compat_urllib_parse_urlparse,
7     compat_urllib_request,
8 )
9 from ..aes import (
10     aes_decrypt_text
11 )
12
13 class Tube8IE(InfoExtractor):
14     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)'
15     _TEST = {
16         u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/',
17         u'file': u'229795.mp4',
18         u'md5': u'e9e0b0c86734e5e3766e653509475db0',
19         u'info_dict': {
20             u"description": u"hot teen Kasia grinding", 
21             u"uploader": u"unknown", 
22             u"title": u"Kasia music video",
23             u"age_limit": 18,
24         }
25     }
26
27     def _real_extract(self, url):
28         mobj = re.match(self._VALID_URL, url)
29         video_id = mobj.group('videoid')
30         url = 'http://www.' + mobj.group('url')
31
32         req = compat_urllib_request.Request(url)
33         req.add_header('Cookie', 'age_verified=1')
34         webpage = self._download_webpage(req, video_id)
35
36         video_title = self._html_search_regex(r'videotitle      ="([^"]+)', webpage, u'title')
37         video_description = self._html_search_regex(r'>Description:</strong>(.+?)<', webpage, u'description', fatal=False)
38         video_uploader = self._html_search_regex(r'>Submitted by:</strong>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
39         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
40         if thumbnail:
41             thumbnail = thumbnail.replace('\\/', '/')
42
43         video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url')
44         if webpage.find('"encrypted":true')!=-1:
45             password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password')
46             video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
47         path = compat_urllib_parse_urlparse(video_url).path
48         extension = os.path.splitext(path)[1][1:]
49         format = path.split('/')[4].split('_')[:2]
50         format = "-".join(format)
51
52         return {
53             'id': video_id,
54             'uploader': video_uploader,
55             'title': video_title,
56             'thumbnail': thumbnail,
57             'description': video_description,
58             'url': video_url,
59             'ext': extension,
60             'format': format,
61             'format_id': format,
62             'age_limit': 18,
63         }