aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/anitube.py
blob: 23f942ae2d039cf92c9a67934a07d3062f744b0d (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor


class AnitubeIE(InfoExtractor):
    IE_NAME = 'anitube.se'
    _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'

    _TEST = {
        'url': 'http://www.anitube.se/video/36621',
        'md5': '59d0eeae28ea0bc8c05e7af429998d43',
        'info_dict': {
            'id': '36621',
            'ext': 'mp4',
            'title': 'Recorder to Randoseru 01',
            'duration': 180.19,
        },
        'skip': 'Blocked in the US',
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')

        webpage = self._download_webpage(url, video_id)
        key = self._search_regex(
            r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')

        config_xml = self._download_xml(
            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)

        video_title = config_xml.find('title').text
        thumbnail = config_xml.find('image').text
        duration = float(config_xml.find('duration').text)

        formats = []
        video_url = config_xml.find('file')
        if video_url is not None:
            formats.append({
                'format_id': 'sd',
                'url': video_url.text,
            })
        video_url = config_xml.find('filehd')
        if video_url is not None:
            formats.append({
                'format_id': 'hd',
                'url': video_url.text,
            })

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