]>
Commit | Line | Data |
---|---|---|
50451f2a JMF |
1 | # encoding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
01c10ca2 | 4 | from .common import InfoExtractor |
6e6bc8da | 5 | from ..compat import compat_urlparse |
1cc79574 | 6 | from ..utils import ( |
01c10ca2 | 7 | ExtractorError, |
5c2266df | 8 | sanitized_Request, |
6e6bc8da | 9 | urlencode_postdata, |
01c10ca2 PH |
10 | ) |
11 | ||
12 | ||
13 | class Vbox7IE(InfoExtractor): | |
5886b38d | 14 | _VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)' |
6f5ac90c | 15 | _TEST = { |
50451f2a JMF |
16 | 'url': 'http://vbox7.com/play:249bb972c2', |
17 | 'md5': '99f65c0c9ef9b682b97313e052734c3f', | |
18 | 'info_dict': { | |
19 | 'id': '249bb972c2', | |
8e6f8051 | 20 | 'ext': 'mp4', |
50451f2a JMF |
21 | 'title': 'Смях! Чудо - чист за секунди - Скрита камера', |
22 | }, | |
6f5ac90c | 23 | } |
01c10ca2 | 24 | |
50451f2a | 25 | def _real_extract(self, url): |
1cc79574 | 26 | video_id = self._match_id(url) |
01c10ca2 | 27 | |
4af98ecd YCH |
28 | # need to get the page 3 times for the correct jsSecretToken cookie |
29 | # which is necessary for the correct title | |
30 | def get_session_id(): | |
31 | redirect_page = self._download_webpage(url, video_id) | |
32 | session_id_url = self._search_regex( | |
33 | r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page, | |
34 | 'session id url') | |
35 | self._download_webpage( | |
36 | compat_urlparse.urljoin(url, session_id_url), video_id, | |
37 | 'Getting session id') | |
38 | ||
39 | get_session_id() | |
40 | get_session_id() | |
41 | ||
42 | webpage = self._download_webpage(url, video_id, | |
9e1a5b84 | 43 | 'Downloading redirect page') |
01c10ca2 PH |
44 | |
45 | title = self._html_search_regex(r'<title>(.*)</title>', | |
9e1a5b84 | 46 | webpage, 'title').split('/')[0].strip() |
01c10ca2 | 47 | |
611c1dd9 | 48 | info_url = 'http://vbox7.com/play/magare.do' |
6e6bc8da | 49 | data = urlencode_postdata({'as3': '1', 'vid': video_id}) |
5c2266df | 50 | info_request = sanitized_Request(info_url, data) |
01c10ca2 | 51 | info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
50451f2a | 52 | info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage') |
01c10ca2 | 53 | if info_response is None: |
50451f2a | 54 | raise ExtractorError('Unable to extract the media url') |
01c10ca2 PH |
55 | (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) |
56 | ||
50451f2a JMF |
57 | return { |
58 | 'id': video_id, | |
59 | 'url': final_url, | |
50451f2a | 60 | 'title': title, |
01c10ca2 | 61 | 'thumbnail': thumbnail_url, |
50451f2a | 62 | } |