_ 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         m3u8_url = self._html_search_regex(
  58             r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url')
  59         formats = self._extract_m3u8_formats(
  60             m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls')
  61
  62         rtsp_url = self._search_regex(
  63             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  64         if rtsp_url:
  65             formats.append({
  66                 'url': rtsp_url,
  67                 'format_id': 'rtsp',
  68             })
  69
  70         self._sort_formats(formats)
  71         return formats
  72
  73
  74 class DCNVideoIE(DCNBaseIE):
  75     IE_NAME = 'dcn:video'
  76     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
  77     _TEST = {
  78         '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',
  79         'info_dict':
  80         {
  81             'id': '17375',
  82             'ext': 'mp4',
  83             'title': 'رحلة العمر : الحلقة 1',
  84             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  85             'duration': 2041,
  86             'timestamp': 1227504126,
  87             'upload_date': '20081124',
  88         },
  89         'params': {
  90             # m3u8 download
  91             'skip_download': True,
  92         },
  93     }
  94
  95     def _real_extract(self, url):
  96         video_id = self._match_id(url)
  97
  98         request = compat_urllib_request.Request(
  99             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
 100             headers={'Origin': 'http://www.dcndigital.ae'})
 101         video_data = self._download_json(request, video_id)
 102         info = self._extract_video_info(video_data, video_id, False)
 103
 104         webpage = self._download_webpage(
 105             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
 106             compat_urllib_parse.urlencode({
 107                 'id': video_data['id'],
 108                 'user_id': video_data['user_id'],
 109                 'signature': video_data['signature'],
 110                 'countries': 'Q0M=',
 111                 'filter': 'DENY',
 112             }), video_id)
 113         info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
 114         return info
 115
 116
 117 class DCNLiveIE(DCNBaseIE):
 118     IE_NAME = 'dcn:live'
 119     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
 120     _TEST = {
 121         'url': 'http://www.dcndigital.ae/#/live/6/dubai-tv',
 122         'info_dict':
 123         {
 124             'id': '6',
 125             'ext': 'mp4',
 126             'title': 're:^Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 127             'thumbnail': 're:^https?://.*\.png$',
 128             'is_live': True,
 129         },
 130         'params': {
 131             # m3u8 download
 132             'skip_download': True,
 133         },
 134     }
 135
 136     def _real_extract(self, url):
 137         channel_id = self._match_id(url)
 138
 139         request = compat_urllib_request.Request(
 140             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
 141             headers={'Origin': 'http://www.dcndigital.ae'})
 142
 143         channel_data = self._download_json(request, channel_id)
 144         info = self._extract_video_info(channel_data, channel_id, True)
 145
 146         webpage = self._download_webpage(
 147             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
 148             compat_urllib_parse.urlencode({
 149                 'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
 150                 'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
 151                 'signature': channel_data['signature'],
 152                 'countries': 'Q0M=',
 153                 'filter': 'DENY',
 154             }), channel_id)
 155         info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
 156         return info
 157
 158
 159 class DCNSeasonIE(InfoExtractor):
 160     IE_NAME = 'dcn:season'
 161     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 162     _TEST = {
 163         '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',
 164         'info_dict':
 165         {
 166             'id': '7910',
 167             'title': 'محاضرات الشيخ الشعراوي',
 168         },
 169         'playlist_mincount': 27,
 170     }
 171
 172     def _real_extract(self, url):
 173         url, smuggled_data = unsmuggle_url(url, {})
 174         show_id, season_id = re.match(self._VALID_URL, url).groups()
 175
 176         data = {}
 177         if season_id:
 178             data['season'] = season_id
 179             show_id = smuggled_data.get('show_id')
 180             if show_id is None:
 181                 request = compat_urllib_request.Request(
 182                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 183                     headers={'Origin': 'http://www.dcndigital.ae'})
 184                 season = self._download_json(request, season_id)
 185                 show_id = season['id']
 186         data['show_id'] = show_id
 187         request = compat_urllib_request.Request(
 188             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 189             compat_urllib_parse.urlencode(data),
 190             {
 191                 'Origin': 'http://www.dcndigital.ae',
 192                 'Content-Type': 'application/x-www-form-urlencoded'
 193             })
 194
 195         show = self._download_json(request, show_id)
 196         if not season_id:
 197             season_id = show['default_season']
 198         for season in show['seasons']:
 199             if season['id'] == season_id:
 200                 title = season.get('title_en') or season['title_ar']
 201
 202                 entries = []
 203                 for video in show['videos']:
 204                     entries.append(self.url_result(
 205                         'http://www.dcndigital.ae/media/%s' % video['id'], 'DCNVideo'))
 206
 207                 return self.playlist_result(entries, season_id, title)