summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/awaan.py
blob: 4066a5a83f2af7ee2c6c35d03440928b4750604b (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
import base64
import urllib.parse

from .common import InfoExtractor
from ..utils import (
    format_field,
    int_or_none,
    parse_iso8601,
    smuggle_url,
    unsmuggle_url,
    urlencode_postdata,
)


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

    def _real_extract(self, url):
        show_id, video_id, season_id = self._match_valid_url(url).groups()
        if video_id and int(video_id) > 0:
            return self.url_result(
                f'http://awaan.ae/media/{video_id}', 'AWAANVideo')
        elif season_id and int(season_id) > 0:
            return self.url_result(smuggle_url(
                f'http://awaan.ae/program/season/{season_id}',
                {'show_id': show_id}), 'AWAANSeason')
        else:
            return self.url_result(
                f'http://awaan.ae/program/{show_id}', 'AWAANSeason')


class AWAANBaseIE(InfoExtractor):
    def _parse_video_data(self, video_data, video_id, is_live):
        title = video_data.get('title_en') or video_data['title_ar']
        img = video_data.get('img')

        return {
            'id': video_id,
            'title': title,
            'description': video_data.get('description_en') or video_data.get('description_ar'),
            'thumbnail': format_field(img, None, 'http://admin.mangomolo.com/analytics/%s'),
            'duration': int_or_none(video_data.get('duration')),
            'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
            'is_live': is_live,
            'uploader_id': video_data.get('user_id'),
        }


class AWAANVideoIE(AWAANBaseIE):
    IE_NAME = 'awaan:video'
    _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
    _TESTS = [{
        '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',
        'md5': '5f61c33bfc7794315c671a62d43116aa',
        'info_dict':
        {
            'id': '17375',
            'ext': 'mp4',
            'title': 'رحلة العمر : الحلقة 1',
            'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
            'duration': 2041,
            'timestamp': 1227504126,
            'upload_date': '20081124',
            'uploader_id': '71',
        },
    }, {
        'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
        'only_matching': True,
    }]

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

        video_data = self._download_json(
            f'http://admin.mangomolo.com/analytics/index.php/plus/video?id={video_id}',
            video_id, headers={'Origin': 'http://awaan.ae'})
        info = self._parse_video_data(video_data, video_id, False)

        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + urllib.parse.urlencode({
            'id': video_data['id'],
            'user_id': video_data['user_id'],
            'signature': video_data['signature'],
            'countries': 'Q0M=',
            'filter': 'DENY',
        })
        info.update({
            '_type': 'url_transparent',
            'url': embed_url,
            'ie_key': 'MangomoloVideo',
        })
        return info


class AWAANLiveIE(AWAANBaseIE):
    IE_NAME = 'awaan:live'
    _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
    _TEST = {
        'url': 'http://awaan.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}$',
            'upload_date': '20150107',
            'timestamp': 1420588800,
            'uploader_id': '71',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }

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

        channel_data = self._download_json(
            f'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id={channel_id}',
            channel_id, headers={'Origin': 'http://awaan.ae'})
        info = self._parse_video_data(channel_data, channel_id, True)

        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + urllib.parse.urlencode({
            'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
            'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
            'signature': channel_data['signature'],
            'countries': 'Q0M=',
            'filter': 'DENY',
        })
        info.update({
            '_type': 'url_transparent',
            'url': embed_url,
            'ie_key': 'MangomoloLive',
        })
        return info


class AWAANSeasonIE(InfoExtractor):
    IE_NAME = 'awaan:season'
    _VALID_URL = r'https?://(?:www\.)?(?:awaan|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 = self._match_valid_url(url).groups()

        data = {}
        if season_id:
            data['season'] = season_id
            show_id = smuggled_data.get('show_id')
            if show_id is None:
                season = self._download_json(
                    f'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id={season_id}',
                    season_id, headers={'Origin': 'http://awaan.ae'})
                show_id = season['id']
        data['show_id'] = show_id
        show = self._download_json(
            'http://admin.mangomolo.com/analytics/index.php/plus/show',
            show_id, data=urlencode_postdata(data), headers={
                'Origin': 'http://awaan.ae',
                'Content-Type': 'application/x-www-form-urlencoded',
            })
        if not season_id:
            season_id = show['default_season']
        for season in show['seasons']:
            if season['id'] == season_id:
                title = season.get('title_en') or season['title_ar']

                entries = []
                for video in show['videos']:
                    video_id = str(video['id'])
                    entries.append(self.url_result(
                        f'http://awaan.ae/media/{video_id}', 'AWAANVideo', video_id))

                return self.playlist_result(entries, season_id, title)