aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/meta.py
blob: 2ca7092e5199211a944e2b2f87b0c07f47364003 (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    unescapeHTML,
    int_or_none,
    ExtractorError,
)


class METAIE(InfoExtractor):
    _VALID_URL = r'https?://video\.meta\.ua/(?:iframe/)?(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://video.meta.ua/5502115.video',
        'md5': '71b6f3ee274bef16f1ab410f7f56b476',
        'info_dict': {
            'id': '5502115',
            'ext': 'mp4',
            'title': 'Sony Xperia Z camera test [HQ]',
            'description': 'Xperia Z shoots video in FullHD HDR.',
            'uploader_id': 'nomobile',
            'uploader': 'CHЁZA.TV',
            'upload_date': '20130211',
        },
        'add_ie': ['Youtube'],
    }, {
        'url': 'http://video.meta.ua/iframe/5502115',
        'only_matching': True,
    }]

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

        st_html5 = self._search_regex(r"st_html5\s*=\s*'#([^']+)'", webpage, 'uppod html5 st')
        json_str = ''
        for i in range(0, len(st_html5), 3):
            json_str += '&#x0%s;' % st_html5[i:i + 3]
        uppod_data = self._parse_json(unescapeHTML(json_str), video_id)
        error = uppod_data.get('customnotfound')
        if error:
            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)

        video_url = uppod_data['file']
        info = {
            'id': video_id,
            'url': video_url,
            'title': uppod_data.get('comment') or self._og_search_title(webpage),
            'description': self._og_search_description(webpage),
            'thumbnail': uppod_data.get('poster') or self._og_search_thumbnail(webpage),
            'duration': int_or_none(self._og_search_property('video:duration', webpage)),
        }
        if 'youtube.com/' in video_url:
            info.update({
                '_type': 'url_transparent',
                'ie_key': 'Youtube',
            })
        return info