aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/dcn.py
blob: b98a6c0321d145bd703ab2f694b25ef03166a6b2 (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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_urllib_request,
)
from ..utils import (
    int_or_none,
    parse_iso8601,
)


class DCNIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)/?'
    _TEST = {
        'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887',
        'info_dict':
        {
            'id': '17375',
            'ext': 'mp4',
            'title': 'رحلة العمر : الحلقة 1',
            'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 2041,
            'timestamp': 1227504126,
            'upload_date': '20081124',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }

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

        request = compat_urllib_request.Request(
            'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
            headers={'Origin': 'http://www.dcndigital.ae'})

        video = self._download_json(request, video_id)
        title = video.get('title_en') or video['title_ar']

        webpage = self._download_webpage(
            'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
            + compat_urllib_parse.urlencode({
                'id': video['id'],
                'user_id': video['user_id'],
                'signature': video['signature'],
                'countries': 'Q0M=',
                'filter': 'DENY',
            }), video_id)

        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
        formats = self._extract_m3u8_formats(
            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')

        rtsp_url = self._search_regex(
            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
        if rtsp_url:
            formats.append({
                'url': rtsp_url,
                'format_id': 'rtsp',
            })

        self._sort_formats(formats)

        img = video.get('img')
        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
        duration = int_or_none(video.get('duration'))
        description = video.get('description_en') or video.get('description_ar')
        timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')

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