_ 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 DCNIE(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         if video_id and int(video_id) > 0:
  26             return self.url_result(
  27                 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
  28         elif season_id and int(season_id) > 0:
  29             return self.url_result(smuggle_url(
  30                 'http://www.dcndigital.ae/program/season/%s' % season_id,
  31                 {'show_id': show_id}), 'DCNSeason')
  32         else:
  33             return self.url_result(
  34                 'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
  35
  36
  37 class DCNBaseIE(InfoExtractor):
  38     def _extract_video_info(self, video_data, video_id, is_live):
  39         title = video_data.get('title_en') or video_data['title_ar']
  40         img = video_data.get('img')
  41         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
  42         duration = int_or_none(video_data.get('duration'))
  43         description = video_data.get('description_en') or video_data.get('description_ar')
  44         timestamp = parse_iso8601(video_data.get('create_time'), ' ')
  45
  46         return {
  47             'id': video_id,
  48             'title': self._live_title(title) if is_live else title,
  49             'description': description,
  50             'thumbnail': thumbnail,
  51             'duration': duration,
  52             'timestamp': timestamp,
  53             'is_live': is_live,
  54         }
  55
  56     def _extract_video_formats(self, webpage, video_id, entry_protocol):
  57         formats = []
  58         m3u8_url = self._html_search_regex(
  59             r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False)
  60         if m3u8_url:
  61             m3u8_formats = self._extract_m3u8_formats(
  62                 m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None)
  63             if m3u8_formats:
  64                 formats.extend(m3u8_formats)
  65
  66         rtsp_url = self._search_regex(
  67             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  68         if rtsp_url:
  69             formats.append({
  70                 'url': rtsp_url,
  71                 'format_id': 'rtsp',
  72             })
  73
  74         self._sort_formats(formats)
  75         return formats
  76
  77
  78 class DCNVideoIE(DCNBaseIE):
  79     IE_NAME = 'dcn:video'
  80     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
  81     _TEST = {
  82         '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',
  83         'info_dict':
  84         {
  85             'id': '17375',
  86             'ext': 'mp4',
  87             'title': 'رحلة العمر : الحلقة 1',
  88             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  89             'duration': 2041,
  90             'timestamp': 1227504126,
  91             'upload_date': '20081124',
  92         },
  93         'params': {
  94             # m3u8 download
  95             'skip_download': True,
  96         },
  97     }
  98
  99     def _real_extract(self, url):
 100         video_id = self._match_id(url)
 101
 102         request = compat_urllib_request.Request(
 103             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
 104             headers={'Origin': 'http://www.dcndigital.ae'})
 105         video_data = self._download_json(request, video_id)
 106         info = self._extract_video_info(video_data, video_id, False)
 107
 108         webpage = self._download_webpage(
 109             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
 110             compat_urllib_parse.urlencode({
 111                 'id': video_data['id'],
 112                 'user_id': video_data['user_id'],
 113                 'signature': video_data['signature'],
 114                 'countries': 'Q0M=',
 115                 'filter': 'DENY',
 116             }), video_id)
 117         info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
 118         return info
 119
 120
 121 class DCNLiveIE(DCNBaseIE):
 122     IE_NAME = 'dcn:live'
 123     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
 124
 125     def _real_extract(self, url):
 126         channel_id = self._match_id(url)
 127
 128         request = compat_urllib_request.Request(
 129             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
 130             headers={'Origin': 'http://www.dcndigital.ae'})
 131
 132         channel_data = self._download_json(request, channel_id)
 133         info = self._extract_video_info(channel_data, channel_id, True)
 134
 135         webpage = self._download_webpage(
 136             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
 137             compat_urllib_parse.urlencode({
 138                 'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
 139                 'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
 140                 'signature': channel_data['signature'],
 141                 'countries': 'Q0M=',
 142                 'filter': 'DENY',
 143             }), channel_id)
 144         info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
 145         return info
 146
 147
 148 class DCNSeasonIE(InfoExtractor):
 149     IE_NAME = 'dcn:season'
 150     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 151     _TEST = {
 152         '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',
 153         'info_dict':
 154         {
 155             'id': '7910',
 156             'title': 'محاضرات الشيخ الشعراوي',
 157         },
 158         'playlist_mincount': 27,
 159     }
 160
 161     def _real_extract(self, url):
 162         url, smuggled_data = unsmuggle_url(url, {})
 163         show_id, season_id = re.match(self._VALID_URL, url).groups()
 164
 165         data = {}
 166         if season_id:
 167             data['season'] = season_id
 168             show_id = smuggled_data.get('show_id')
 169             if show_id is None:
 170                 request = compat_urllib_request.Request(
 171                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 172                     headers={'Origin': 'http://www.dcndigital.ae'})
 173                 season = self._download_json(request, season_id)
 174                 show_id = season['id']
 175         data['show_id'] = show_id
 176         request = compat_urllib_request.Request(
 177             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 178             compat_urllib_parse.urlencode(data),
 179             {
 180                 'Origin': 'http://www.dcndigital.ae',
 181                 'Content-Type': 'application/x-www-form-urlencoded'
 182             })
 183
 184         show = self._download_json(request, show_id)
 185         if not season_id:
 186             season_id = show['default_season']
 187         for season in show['seasons']:
 188             if season['id'] == season_id:
 189                 title = season.get('title_en') or season['title_ar']
 190
 191                 entries = []
 192                 for video in show['videos']:
 193                     entries.append(self.url_result(
 194                         'http://www.dcndigital.ae/media/%s' % video['id'], 'DCNVideo'))
 195
 196                 return self.playlist_result(entries, season_id, title)