_ Git - youtube-dl/blob - youtube_dl/extractor/dcn.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import base64
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12 from ..utils import (
  13     int_or_none,
  14     parse_iso8601,
  15     smuggle_url,
  16     unsmuggle_url,
  17 )
  18
  19
  20 class DCNGeneralIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
  22
  23     def _real_extract(self, url):
  24         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
  25         url = ''
  26         ie_key = ''
  27         if video_id and int(video_id) > 0:
  28             return self.url_result('http://www.dcndigital.ae/#/media/%s' % video_id, 'DCNVideo')
  29         else:
  30             if season_id and int(season_id) > 0:
  31                 url = smuggle_url('http://www.dcndigital.ae/#/program/season/%s' % season_id, {'show_id': show_id})
  32             else:
  33                 url = 'http://www.dcndigital.ae/#/program/%s' % show_id
  34             return self.url_result(url, 'DCNSeason')
  35
  36
  37 class DCNVideoIE(InfoExtractor):
  38     IE_NAME = 'dcn:video'
  39     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
  40     _TEST = {
  41         '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',
  42         'info_dict':
  43         {
  44             'id': '17375',
  45             'ext': 'mp4',
  46             'title': 'رحلة العمر : الحلقة 1',
  47             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  48             'thumbnail': 're:^https?://.*\.jpg$',
  49             'duration': 2041,
  50             'timestamp': 1227504126,
  51             'upload_date': '20081124',
  52         },
  53         'params': {
  54             # m3u8 download
  55             'skip_download': True,
  56         },
  57     }
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61
  62         request = compat_urllib_request.Request(
  63             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
  64             headers={'Origin': 'http://www.dcndigital.ae'})
  65
  66         video = self._download_json(request, video_id)
  67         title = video.get('title_en') or video['title_ar']
  68         img = video.get('img')
  69         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
  70         duration = int_or_none(video.get('duration'))
  71         description = video.get('description_en') or video.get('description_ar')
  72         timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
  73
  74         webpage = self._download_webpage(
  75             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
  76             + compat_urllib_parse.urlencode({
  77                 'id': video['id'],
  78                 'user_id': video['user_id'],
  79                 'signature': video['signature'],
  80                 'countries': 'Q0M=',
  81                 'filter': 'DENY',
  82             }), video_id)
  83
  84         m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
  85         formats = self._extract_m3u8_formats(
  86             m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  87
  88         rtsp_url = self._search_regex(
  89             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  90         if rtsp_url:
  91             formats.append({
  92                 'url': rtsp_url,
  93                 'format_id': 'rtsp',
  94             })
  95
  96         self._sort_formats(formats)
  97
  98         return {
  99             'id': video_id,
 100             'title': title,
 101             'description': description,
 102             'thumbnail': thumbnail,
 103             'duration': duration,
 104             'timestamp': timestamp,
 105             'formats': formats,
 106         }
 107
 108
 109 class DCNLiveIE(InfoExtractor):
 110     IE_NAME = 'dcn:live'
 111     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
 112     _TEST = {
 113         'url': 'http://www.dcndigital.ae/#/live/6/dubai-tv',
 114         'info_dict':
 115         {
 116             'id': '6',
 117             'ext': 'mp4',
 118             'title': 're:^Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 119             'thumbnail': 're:^https?://.*\.png$',
 120             'is_live': True,
 121         },
 122         'params': {
 123             # m3u8 download
 124             'skip_download': True,
 125         },
 126     }
 127
 128     def _real_extract(self, url):
 129         channel_id = self._match_id(url)
 130
 131         request = compat_urllib_request.Request(
 132             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
 133             headers={'Origin': 'http://www.dcndigital.ae'})
 134
 135         channel = self._download_json(request, channel_id)
 136         title = channel.get('title_en') or channel['title_ar']
 137         img = channel.get('thumbnail')
 138         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
 139         description = channel.get('description_en') or channel.get('description_ar')
 140         timestamp = parse_iso8601(channel.get('create_time') or channel.get('update_time'), ' ')
 141
 142         webpage = self._download_webpage(
 143             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
 144             compat_urllib_parse.urlencode({
 145                 'id': base64.b64encode(channel['user_id'].encode()).decode(),
 146                 'channelid': base64.b64encode(channel['id'].encode()).decode(),
 147                 'signature': channel['signature'],
 148                 'countries': 'Q0M=',
 149                 'filter': 'DENY',
 150             }), channel_id)
 151
 152         m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
 153         formats = self._extract_m3u8_formats(
 154             m3u8_url, channel_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
 155
 156         rtsp_url = self._search_regex(
 157             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
 158         if rtsp_url:
 159             formats.append({
 160                 'url': rtsp_url,
 161                 'format_id': 'rtsp',
 162             })
 163
 164         self._sort_formats(formats)
 165
 166         return {
 167             'id': channel_id,
 168             'title': self._live_title(title),
 169             'description': description,
 170             'thumbnail': thumbnail,
 171             'formats': formats,
 172             'is_live': True,
 173         }
 174
 175
 176 class DCNSeasonIE(InfoExtractor):
 177     IE_NAME = 'dcn:season'
 178     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 179     _TEST = {
 180         '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',
 181         'info_dict':
 182         {
 183             'id': '7910',
 184             'title': 'محاضرات الشيخ الشعراوي',
 185         },
 186         'playlist_mincount': 27,
 187     }
 188
 189     def _real_extract(self, url):
 190         url, smuggled_data = unsmuggle_url(url, {})
 191         show_id, season_id = re.match(self._VALID_URL, url).groups()
 192
 193         data = {}
 194         if season_id:
 195             data['season'] = season_id
 196             show_id = smuggled_data.get('show_id')
 197             if show_id is None:
 198                 request = compat_urllib_request.Request(
 199                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 200                     headers={'Origin': 'http://www.dcndigital.ae'})
 201                 season = self._download_json(request, season_id)
 202                 show_id = season['id']
 203         data['show_id'] = show_id
 204         request = compat_urllib_request.Request(
 205             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 206             compat_urllib_parse.urlencode(data),
 207             {
 208                 'Origin': 'http://www.dcndigital.ae',
 209                 'Content-Type': 'application/x-www-form-urlencoded'
 210             })
 211
 212         show = self._download_json(request, show_id)
 213         if not season_id:
 214             season_id = show['default_season']
 215         for season in show['seasons']:
 216             if season['id'] == season_id:
 217                 title = season.get('title_en') or season['title_ar']
 218
 219                 entries = []
 220                 for video in show['videos']:
 221                     entries.append(self.url_result('http://www.dcndigital.ae/#/media/%s' % video['id'], 'DCNVideo'))
 222
 223                 return self.playlist_result(entries, season_id, title)