]>
Commit | Line | Data |
---|---|---|
50451f2a JMF |
1 | # encoding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
01c10ca2 | 4 | from .common import InfoExtractor |
1cc79574 | 5 | from ..compat import ( |
01c10ca2 PH |
6 | compat_urllib_parse, |
7 | compat_urllib_request, | |
1cc79574 PH |
8 | ) |
9 | from ..utils import ( | |
01c10ca2 PH |
10 | ExtractorError, |
11 | ) | |
12 | ||
13 | ||
14 | class Vbox7IE(InfoExtractor): | |
1cc79574 | 15 | _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)' |
6f5ac90c | 16 | _TEST = { |
50451f2a JMF |
17 | 'url': 'http://vbox7.com/play:249bb972c2', |
18 | 'md5': '99f65c0c9ef9b682b97313e052734c3f', | |
19 | 'info_dict': { | |
20 | 'id': '249bb972c2', | |
8e6f8051 | 21 | 'ext': 'mp4', |
50451f2a JMF |
22 | 'title': 'Смях! Чудо - чист за секунди - Скрита камера', |
23 | }, | |
6f5ac90c | 24 | } |
01c10ca2 | 25 | |
50451f2a | 26 | def _real_extract(self, url): |
1cc79574 | 27 | video_id = self._match_id(url) |
01c10ca2 PH |
28 | |
29 | redirect_page, urlh = self._download_webpage_handle(url, video_id) | |
50451f2a | 30 | new_location = self._search_regex(r'window\.location = \'(.*)\';', |
9e1a5b84 | 31 | redirect_page, 'redirect location') |
01c10ca2 | 32 | redirect_url = urlh.geturl() + new_location |
50451f2a | 33 | webpage = self._download_webpage(redirect_url, video_id, |
9e1a5b84 | 34 | 'Downloading redirect page') |
01c10ca2 PH |
35 | |
36 | title = self._html_search_regex(r'<title>(.*)</title>', | |
9e1a5b84 | 37 | webpage, 'title').split('/')[0].strip() |
01c10ca2 | 38 | |
01c10ca2 | 39 | info_url = "http://vbox7.com/play/magare.do" |
50451f2a | 40 | data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id}) |
01c10ca2 PH |
41 | info_request = compat_urllib_request.Request(info_url, data) |
42 | info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
50451f2a | 43 | info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage') |
01c10ca2 | 44 | if info_response is None: |
50451f2a | 45 | raise ExtractorError('Unable to extract the media url') |
01c10ca2 PH |
46 | (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) |
47 | ||
50451f2a JMF |
48 | return { |
49 | 'id': video_id, | |
50 | 'url': final_url, | |
50451f2a | 51 | 'title': title, |
01c10ca2 | 52 | 'thumbnail': thumbnail_url, |
50451f2a | 53 | } |