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 compat_urllib_parse
   9 from ..utils import (
  10     int_or_none,
  11     parse_iso8601,
  12     sanitized_Request,
  13     smuggle_url,
  14     unsmuggle_url,
  15 )
  16
  17
  18 class DCNIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
  20
  21     def _real_extract(self, url):
  22         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
  23         if video_id and int(video_id) > 0:
  24             return self.url_result(
  25                 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
  26         elif season_id and int(season_id) > 0:
  27             return self.url_result(smuggle_url(
  28                 'http://www.dcndigital.ae/program/season/%s' % season_id,
  29                 {'show_id': show_id}), 'DCNSeason')
  30         else:
  31             return self.url_result(
  32                 'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
  33
  34
  35 class DCNBaseIE(InfoExtractor):
  36     def _extract_video_info(self, video_data, video_id, is_live):
  37         title = video_data.get('title_en') or video_data['title_ar']
  38         img = video_data.get('img')
  39         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
  40         duration = int_or_none(video_data.get('duration'))
  41         description = video_data.get('description_en') or video_data.get('description_ar')
  42         timestamp = parse_iso8601(video_data.get('create_time'), ' ')
  43
  44         return {
  45             'id': video_id,
  46             'title': self._live_title(title) if is_live else title,
  47             'description': description,
  48             'thumbnail': thumbnail,
  49             'duration': duration,
  50             'timestamp': timestamp,
  51             'is_live': is_live,
  52         }
  53
  54     def _extract_video_formats(self, webpage, video_id, entry_protocol):
  55         formats = []
  56         m3u8_url = self._html_search_regex(
  57             r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False)
  58         if m3u8_url:
  59             m3u8_formats = self._extract_m3u8_formats(
  60                 m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None)
  61             if m3u8_formats:
  62                 formats.extend(m3u8_formats)
  63
  64         rtsp_url = self._search_regex(
  65             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  66         if rtsp_url:
  67             formats.append({
  68                 'url': rtsp_url,
  69                 'format_id': 'rtsp',
  70             })
  71
  72         self._sort_formats(formats)
  73         return formats
  74
  75
  76 class DCNVideoIE(DCNBaseIE):
  77     IE_NAME = 'dcn:video'
  78     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
  79     _TEST = {
  80         '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',
  81         'info_dict':
  82         {
  83             'id': '17375',
  84             'ext': 'mp4',
  85             'title': 'رحلة العمر : الحلقة 1',
  86             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  87             'duration': 2041,
  88             'timestamp': 1227504126,
  89             'upload_date': '20081124',
  90         },
  91         'params': {
  92             # m3u8 download
  93             'skip_download': True,
  94         },
  95     }
  96
  97     def _real_extract(self, url):
  98         video_id = self._match_id(url)
  99
 100         request = sanitized_Request(
 101             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
 102             headers={'Origin': 'http://www.dcndigital.ae'})
 103         video_data = self._download_json(request, video_id)
 104         info = self._extract_video_info(video_data, video_id, False)
 105
 106         webpage = self._download_webpage(
 107             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
 108             compat_urllib_parse.urlencode({
 109                 'id': video_data['id'],
 110                 'user_id': video_data['user_id'],
 111                 'signature': video_data['signature'],
 112                 'countries': 'Q0M=',
 113                 'filter': 'DENY',
 114             }), video_id)
 115         info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
 116         return info
 117
 118
 119 class DCNLiveIE(DCNBaseIE):
 120     IE_NAME = 'dcn:live'
 121     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
 122
 123     def _real_extract(self, url):
 124         channel_id = self._match_id(url)
 125
 126         request = sanitized_Request(
 127             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
 128             headers={'Origin': 'http://www.dcndigital.ae'})
 129
 130         channel_data = self._download_json(request, channel_id)
 131         info = self._extract_video_info(channel_data, channel_id, True)
 132
 133         webpage = self._download_webpage(
 134             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
 135             compat_urllib_parse.urlencode({
 136                 'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
 137                 'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
 138                 'signature': channel_data['signature'],
 139                 'countries': 'Q0M=',
 140                 'filter': 'DENY',
 141             }), channel_id)
 142         info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
 143         return info
 144
 145
 146 class DCNSeasonIE(InfoExtractor):
 147     IE_NAME = 'dcn:season'
 148     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 149     _TEST = {
 150         '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',
 151         'info_dict':
 152         {
 153             'id': '7910',
 154             'title': 'محاضرات الشيخ الشعراوي',
 155         },
 156         'playlist_mincount': 27,
 157     }
 158
 159     def _real_extract(self, url):
 160         url, smuggled_data = unsmuggle_url(url, {})
 161         show_id, season_id = re.match(self._VALID_URL, url).groups()
 162
 163         data = {}
 164         if season_id:
 165             data['season'] = season_id
 166             show_id = smuggled_data.get('show_id')
 167             if show_id is None:
 168                 request = sanitized_Request(
 169                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 170                     headers={'Origin': 'http://www.dcndigital.ae'})
 171                 season = self._download_json(request, season_id)
 172                 show_id = season['id']
 173         data['show_id'] = show_id
 174         request = sanitized_Request(
 175             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 176             compat_urllib_parse.urlencode(data),
 177             {
 178                 'Origin': 'http://www.dcndigital.ae',
 179                 'Content-Type': 'application/x-www-form-urlencoded'
 180             })
 181
 182         show = self._download_json(request, show_id)
 183         if not season_id:
 184             season_id = show['default_season']
 185         for season in show['seasons']:
 186             if season['id'] == season_id:
 187                 title = season.get('title_en') or season['title_ar']
 188
 189                 entries = []
 190                 for video in show['videos']:
 191                     entries.append(self.url_result(
 192                         'http://www.dcndigital.ae/media/%s' % video['id'], 'DCNVideo'))
 193
 194                 return self.playlist_result(entries, season_id, title)