aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/dcn.py
blob: 8b360a9d7ed381437ac47b7b6357983c9669bd3c (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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
# coding: utf-8
from __future__ import unicode_literals

import re
import base64

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


class DCNGeneralIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'

    def _real_extract(self, url):
        show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
        url = ''
        ie_key = ''
        if video_id and int(video_id) > 0:
            return self.url_result('http://www.dcndigital.ae/#/media/%s' % video_id, 'DCNVideo')
        else:
            if season_id and int(season_id) > 0:
                url = smuggle_url('http://www.dcndigital.ae/#/program/season/%s' % season_id, {'show_id': show_id})
            else:
                url = 'http://www.dcndigital.ae/#/program/%s' % show_id
            return self.url_result(url, 'DCNSeason')


class DCNVideoIE(InfoExtractor):
    IE_NAME = 'dcn:video'
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.dcndigital.ae/#/video/%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',
        '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']
        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'), ' ')

        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)

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


class DCNLiveIE(InfoExtractor):
    IE_NAME = 'dcn:live'
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.dcndigital.ae/#/live/6/dubai-tv',
        'info_dict':
        {
            'id': '6',
            'ext': 'mp4',
            'title': 're:^Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'thumbnail': 're:^https?://.*\.png$',
            'is_live': True,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }

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

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

        channel = self._download_json(request, channel_id)
        title = channel.get('title_en') or channel['title_ar']
        img = channel.get('thumbnail')
        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
        description = channel.get('description_en') or channel.get('description_ar')
        timestamp = parse_iso8601(channel.get('create_time') or channel.get('update_time'), ' ')

        webpage = self._download_webpage(
            'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
            compat_urllib_parse.urlencode({
                'id': base64.b64encode(channel['user_id'].encode()).decode(),
                'channelid': base64.b64encode(channel['id'].encode()).decode(),
                'signature': channel['signature'],
                'countries': 'Q0M=',
                'filter': 'DENY',
            }), channel_id)

        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
        formats = self._extract_m3u8_formats(
            m3u8_url, channel_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)

        return {
            'id': channel_id,
            'title': self._live_title(title),
            'description': description,
            'thumbnail': thumbnail,
            'formats': formats,
            'is_live': True,
        }


class DCNSeasonIE(InfoExtractor):
    IE_NAME = 'dcn:season'
    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
    _TEST = {
        'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
        'info_dict':
        {
            'id': '7910',
            'title': 'محاضرات الشيخ الشعراوي',
        },
        'playlist_mincount': 27,
    }

    def _real_extract(self, url):
        url, smuggled_data = unsmuggle_url(url, {})
        show_id, season_id = re.match(self._VALID_URL, url).groups()

        data = {}
        if season_id:
            data['season'] = season_id
            show_id = smuggled_data.get('show_id')
            if show_id is None:
                request = compat_urllib_request.Request(
                    'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
                    headers={'Origin': 'http://www.dcndigital.ae'})
                season = self._download_json(request, season_id)
                show_id = season['id']
        data['show_id'] = show_id
        request = compat_urllib_request.Request(
            'http://admin.mangomolo.com/analytics/index.php/plus/show',
            compat_urllib_parse.urlencode(data),
            {
                'Origin': 'http://www.dcndigital.ae',
                'Content-Type': 'application/x-www-form-urlencoded'
            })

        show = self._download_json(request, show_id)
        season_id = season_id or show['default_season']
        season = {}
        for _ in show['seasons']:
            if _['id'] == season_id:
                season = _
                break
        title = season.get('title_en') or season['title_ar']

        entries = []
        for video in show['videos']:
            entries.append(self.url_result('http://www.dcndigital.ae/#/media/%s' % video['id'], 'DCNVideo'))

        return self.playlist_result(entries, season_id, title)