]>
Commit | Line | Data |
---|---|---|
1d45a23b | 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 | compat_urllib_parse, | |
9 | unescapeHTML, | |
10 | ) | |
11 | from ..aes import ( | |
12 | aes_decrypt_text | |
13 | ) | |
14 | ||
15 | class Tube8IE(InfoExtractor): | |
16 | _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)' | |
17 | _TEST = { | |
18 | u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/', | |
19 | u'file': u'229795.mp4', | |
20 | u'md5': u'e9e0b0c86734e5e3766e653509475db0', | |
21 | u'info_dict': { | |
22 | u"description": u"hot teen Kasia grinding", | |
23 | u"uploader": u"unknown", | |
24 | u"title": u"Kasia music video", | |
25 | } | |
26 | } | |
27 | ||
28 | def _real_extract(self, url): | |
29 | mobj = re.match(self._VALID_URL, url) | |
30 | video_id = mobj.group('videoid') | |
31 | url = 'http://www.' + mobj.group('url') | |
32 | ||
33 | req = compat_urllib_request.Request(url) | |
34 | req.add_header('Cookie', 'age_verified=1') | |
35 | webpage = self._download_webpage(req, video_id) | |
36 | ||
37 | video_title = self._html_search_regex(r'videotitle ="([^"]+)', webpage, u'title') | |
38 | video_description = self._html_search_regex(r'>Description:</strong>(.+?)<', webpage, u'description', fatal=False) | |
39 | video_uploader = self._html_search_regex(r'>Submitted by:</strong>(?:\w|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False) | |
40 | thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False) | |
41 | if thumbnail: | |
42 | thumbnail = thumbnail.replace('\\/', '/') | |
43 | ||
44 | video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url') | |
45 | if webpage.find('"encrypted":true')!=-1: | |
46 | password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password') | |
47 | video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8') | |
48 | path = compat_urllib_parse_urlparse( video_url ).path | |
49 | extension = os.path.splitext( path )[1][1:] | |
50 | format = path.split('/')[4].split('_')[:2] | |
51 | format = "-".join( format ) | |
52 | ||
53 | return { | |
54 | 'id': video_id, | |
55 | 'uploader': video_uploader, | |
56 | 'title': video_title, | |
57 | 'thumbnail': thumbnail, | |
58 | 'description': video_description, | |
59 | 'url': video_url, | |
60 | 'ext': extension, | |
61 | 'format': format, | |
62 | 'format_id': format, | |
63 | } |