aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/golem.py
blob: 53714f47f1a0a8cd1abb8aab0ec09cdbd283d51b (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
64
65
66
67
68
69
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    compat_urlparse,
    determine_ext,
)


class GolemIE(InfoExtractor):
    _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
    _TEST = {
        'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
        'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
        'info_dict': {
            'id': '14095',
            'format_id': 'high',
            'ext': 'mp4',
            'title': 'iPhone 6 und 6 Plus - Test',
            'duration': 300.44,
            'filesize': 65309548,
        }
    }

    _PREFIX = 'http://video.golem.de'

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

        config = self._download_xml(
            'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)

        info = {
            'id': video_id,
            'title': config.findtext('./title', 'golem'),
            'duration': self._float(config.findtext('./playtime'), 'duration'),
        }

        formats = []
        for e in config:
            url = e.findtext('./url')
            if not url:
                continue

            formats.append({
                'format_id': e.tag,
                'url': compat_urlparse.urljoin(self._PREFIX, url),
                'height': self._int(e.get('height'), 'height'),
                'width': self._int(e.get('width'), 'width'),
                'filesize': self._int(e.findtext('filesize'), 'filesize'),
                'ext': determine_ext(e.findtext('./filename')),
            })
        self._sort_formats(formats)
        info['formats'] = formats

        thumbnails = []
        for e in config.findall('.//teaser'):
            url = e.findtext('./url')
            if not url:
                continue
            thumbnails.append({
                'url': compat_urlparse.urljoin(self._PREFIX, url),
                'width': self._int(e.get('width'), 'thumbnail width'),
                'height': self._int(e.get('height'), 'thumbnail height'),
            })
        info['thumbnails'] = thumbnails

        return info