ccf1928b5d323f277b4e8a47bd4d008e821b147c
[youtube-dl] / youtube_dl / extractor / vodlocker.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import (
6     compat_urllib_parse,
7     compat_urllib_request,
8 )
9
10
11 class VodlockerIE(InfoExtractor):
12     _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
13
14     _TESTS = [{
15         'url': 'http://vodlocker.com/e8wvyzz4sl42',
16         'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
17         'info_dict': {
18             'id': 'e8wvyzz4sl42',
19             'ext': 'mp4',
20             'title': 'Germany vs Brazil',
21             'thumbnail': 're:http://.*\.jpg',
22         },
23     }]
24
25     def _real_extract(self, url):
26         video_id = self._match_id(url)
27         webpage = self._download_webpage(url, video_id)
28
29         fields = self._hidden_inputs(webpage)
30
31         if fields['op'] == 'download1':
32             self._sleep(3, video_id)  # they do detect when requests happen too fast!
33             post = compat_urllib_parse.urlencode(fields)
34             req = compat_urllib_request.Request(url, post)
35             req.add_header('Content-type', 'application/x-www-form-urlencoded')
36             webpage = self._download_webpage(
37                 req, video_id, 'Downloading video page')
38
39         title = self._search_regex(
40             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
41         thumbnail = self._search_regex(
42             r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
43         url = self._search_regex(
44             r'file:\s*"(http[^\"]+)",', webpage, 'file url')
45
46         formats = [{
47             'format_id': 'sd',
48             'url': url,
49         }]
50
51         return {
52             'id': video_id,
53             'title': title,
54             'thumbnail': thumbnail,
55             'formats': formats,
56         }