Raphaël G. Git Repositories - youtubedl/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_urlencode,
  10     compat_str,
  11 )
  12 from ..utils import (
  13     int_or_none,
  14     parse_iso8601,
  15     sanitized_Request,
  16     smuggle_url,
  17     unsmuggle_url,
  18     urlencode_postdata,
  19 )
  20
  21
  22 class DCNIE(InfoExtractor):
  23     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
  24
  25     def _real_extract(self, url):
  26         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
  27         if video_id and int(video_id) > 0:
  28             return self.url_result(
  29                 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
  30         elif season_id and int(season_id) > 0:
  31             return self.url_result(smuggle_url(
  32                 'http://www.dcndigital.ae/program/season/%s' % season_id,
  33                 {'show_id': show_id}), 'DCNSeason')
  34         else:
  35             return self.url_result(
  36                 'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
  37
  38
  39 class DCNBaseIE(InfoExtractor):
  40     def _extract_video_info(self, video_data, video_id, is_live):
  41         title = video_data.get('title_en') or video_data['title_ar']
  42         img = video_data.get('img')
  43         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
  44         duration = int_or_none(video_data.get('duration'))
  45         description = video_data.get('description_en') or video_data.get('description_ar')
  46         timestamp = parse_iso8601(video_data.get('create_time'), ' ')
  47
  48         return {
  49             'id': video_id,
  50             'title': self._live_title(title) if is_live else title,
  51             'description': description,
  52             'thumbnail': thumbnail,
  53             'duration': duration,
  54             'timestamp': timestamp,
  55             'is_live': is_live,
  56         }
  57
  58     def _extract_video_formats(self, webpage, video_id, m3u8_entry_protocol):
  59         formats = []
  60         format_url_base = 'http' + self._html_search_regex(
  61             [
  62                 r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8',
  63                 r'<a[^>]+href="rtsp(://[^"]+)"'
  64             ], webpage, 'format url')
  65         formats.extend(self._extract_mpd_formats(
  66             format_url_base + '/manifest.mpd',
  67             video_id, mpd_id='dash', fatal=False))
  68         formats.extend(self._extract_m3u8_formats(
  69             format_url_base + '/playlist.m3u8', video_id, 'mp4',
  70             m3u8_entry_protocol, m3u8_id='hls', fatal=False))
  71         formats.extend(self._extract_f4m_formats(
  72             format_url_base + '/manifest.f4m',
  73             video_id, f4m_id='hds', fatal=False))
  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\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
  81     _TESTS = [{
  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         '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',
  99         'only_matching': True,
 100     }]
 101
 102     def _real_extract(self, url):
 103         video_id = self._match_id(url)
 104
 105         request = sanitized_Request(
 106             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
 107             headers={'Origin': 'http://www.dcndigital.ae'})
 108         video_data = self._download_json(request, video_id)
 109         info = self._extract_video_info(video_data, video_id, False)
 110
 111         webpage = self._download_webpage(
 112             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
 113             compat_urllib_parse_urlencode({
 114                 'id': video_data['id'],
 115                 'user_id': video_data['user_id'],
 116                 'signature': video_data['signature'],
 117                 'countries': 'Q0M=',
 118                 'filter': 'DENY',
 119             }), video_id)
 120         info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
 121         return info
 122
 123
 124 class DCNLiveIE(DCNBaseIE):
 125     IE_NAME = 'dcn:live'
 126     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
 127
 128     def _real_extract(self, url):
 129         channel_id = self._match_id(url)
 130
 131         request = sanitized_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_data = self._download_json(request, channel_id)
 136         info = self._extract_video_info(channel_data, channel_id, True)
 137
 138         webpage = self._download_webpage(
 139             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
 140             compat_urllib_parse_urlencode({
 141                 'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
 142                 'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
 143                 'signature': channel_data['signature'],
 144                 'countries': 'Q0M=',
 145                 'filter': 'DENY',
 146             }), channel_id)
 147         info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
 148         return info
 149
 150
 151 class DCNSeasonIE(InfoExtractor):
 152     IE_NAME = 'dcn:season'
 153     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 154     _TEST = {
 155         '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',
 156         'info_dict':
 157         {
 158             'id': '7910',
 159             'title': 'محاضرات الشيخ الشعراوي',
 160         },
 161         'playlist_mincount': 27,
 162     }
 163
 164     def _real_extract(self, url):
 165         url, smuggled_data = unsmuggle_url(url, {})
 166         show_id, season_id = re.match(self._VALID_URL, url).groups()
 167
 168         data = {}
 169         if season_id:
 170             data['season'] = season_id
 171             show_id = smuggled_data.get('show_id')
 172             if show_id is None:
 173                 request = sanitized_Request(
 174                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 175                     headers={'Origin': 'http://www.dcndigital.ae'})
 176                 season = self._download_json(request, season_id)
 177                 show_id = season['id']
 178         data['show_id'] = show_id
 179         request = sanitized_Request(
 180             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 181             urlencode_postdata(data),
 182             {
 183                 'Origin': 'http://www.dcndigital.ae',
 184                 'Content-Type': 'application/x-www-form-urlencoded'
 185             })
 186
 187         show = self._download_json(request, show_id)
 188         if not season_id:
 189             season_id = show['default_season']
 190         for season in show['seasons']:
 191             if season['id'] == season_id:
 192                 title = season.get('title_en') or season['title_ar']
 193
 194                 entries = []
 195                 for video in show['videos']:
 196                     video_id = compat_str(video['id'])
 197                     entries.append(self.url_result(
 198                         'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
 199
 200                 return self.playlist_result(entries, season_id, title)