]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/vodlocker.py
[SpankBang] Use python2.6 compatible string formatting spec
[youtube-dl] / youtube_dl / extractor / vodlocker.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import (
8     compat_urllib_parse,
9     compat_urllib_request,
10 )
11
12
13 class VodlockerIE(InfoExtractor):
14     _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
15
16     _TESTS = [{
17         'url': 'http://vodlocker.com/e8wvyzz4sl42',
18         'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
19         'info_dict': {
20             'id': 'e8wvyzz4sl42',
21             'ext': 'mp4',
22             'title': 'Germany vs Brazil',
23             'thumbnail': 're:http://.*\.jpg',
24         },
25     }]
26
27     def _real_extract(self, url):
28         video_id = self._match_id(url)
29         webpage = self._download_webpage(url, video_id)
30
31         fields = dict(re.findall(r'''(?x)<input\s+
32             type="hidden"\s+
33             name="([^"]+)"\s+
34             (?:id="[^"]+"\s+)?
35             value="([^"]*)"
36             ''', webpage))
37
38         if fields['op'] == 'download1':
39             self._sleep(3, video_id)  # they do detect when requests happen too fast!
40             post = compat_urllib_parse.urlencode(fields)
41             req = compat_urllib_request.Request(url, post)
42             req.add_header('Content-type', 'application/x-www-form-urlencoded')
43             webpage = self._download_webpage(
44                 req, video_id, 'Downloading video page')
45
46         title = self._search_regex(
47             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
48         thumbnail = self._search_regex(
49             r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
50         url = self._search_regex(
51             r'file:\s*"(http[^\"]+)",', webpage, 'file url')
52
53         formats = [{
54             'format_id': 'sd',
55             'url': url,
56         }]
57
58         return {
59             'id': video_id,
60             'title': title,
61             'thumbnail': thumbnail,
62             'formats': formats,
63         }