aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vodlocker.py
blob: 1c0966a793511a2ec3a9d147bd75ff22e8fb7209 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
# -*- coding: utf-8 -*-
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_urllib_request,
)


class VodlockerIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'

    _TESTS = [{
        'url': 'http://vodlocker.com/e8wvyzz4sl42',
        'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
        'info_dict': {
            'id': 'e8wvyzz4sl42',
            'ext': 'mp4',
            'title': 'Germany vs Brazil',
            'thumbnail': 're:http://.*\.jpg',
        },
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        fields = dict(re.findall(r'''(?x)<input\s+
            type="hidden"\s+
            name="([^"]+)"\s+
            (?:id="[^"]+"\s+)?
            value="([^"]*)"
            ''', webpage))

        if fields['op'] == 'download1':
            self._sleep(3, video_id)  # they do detect when requests happen too fast!
            post = compat_urllib_parse.urlencode(fields)
            req = compat_urllib_request.Request(url, post)
            req.add_header('Content-type', 'application/x-www-form-urlencoded')
            webpage = self._download_webpage(
                req, video_id, 'Downloading video page')

        title = self._search_regex(
            r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
        thumbnail = self._search_regex(
            r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
        url = self._search_regex(
            r'file:\s*"(http[^\"]+)",', webpage, 'file url')

        formats = [{
            'format_id': 'sd',
            'url': url,
        }]

        return {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'formats': formats,
        }