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         # TODO: Current DASH formats are broken - $Time$ pattern in
  66         # <SegmentTemplate> not implemented yet
  67         # formats.extend(self._extract_mpd_formats(
  68         #     format_url_base + '/manifest.mpd',
  69         #     video_id, mpd_id='dash', fatal=False))
  70         formats.extend(self._extract_m3u8_formats(
  71             format_url_base + '/playlist.m3u8', video_id, 'mp4',
  72             m3u8_entry_protocol, m3u8_id='hls', fatal=False))
  73         formats.extend(self._extract_f4m_formats(
  74             format_url_base + '/manifest.f4m',
  75             video_id, f4m_id='hds', fatal=False))
  76         self._sort_formats(formats)
  77         return formats
  78
  79
  80 class DCNVideoIE(DCNBaseIE):
  81     IE_NAME = 'dcn:video'
  82     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
  83     _TESTS = [{
  84         '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',
  85         'info_dict':
  86         {
  87             'id': '17375',
  88             'ext': 'mp4',
  89             'title': 'رحلة العمر : الحلقة 1',
  90             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  91             'duration': 2041,
  92             'timestamp': 1227504126,
  93             'upload_date': '20081124',
  94         },
  95         'params': {
  96             # m3u8 download
  97             'skip_download': True,
  98         },
  99     }, {
 100         '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',
 101         'only_matching': True,
 102     }]
 103
 104     def _real_extract(self, url):
 105         video_id = self._match_id(url)
 106
 107         request = sanitized_Request(
 108             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
 109             headers={'Origin': 'http://www.dcndigital.ae'})
 110         video_data = self._download_json(request, video_id)
 111         info = self._extract_video_info(video_data, video_id, False)
 112
 113         webpage = self._download_webpage(
 114             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
 115             compat_urllib_parse_urlencode({
 116                 'id': video_data['id'],
 117                 'user_id': video_data['user_id'],
 118                 'signature': video_data['signature'],
 119                 'countries': 'Q0M=',
 120                 'filter': 'DENY',
 121             }), video_id)
 122         info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
 123         return info
 124
 125
 126 class DCNLiveIE(DCNBaseIE):
 127     IE_NAME = 'dcn:live'
 128     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
 129
 130     def _real_extract(self, url):
 131         channel_id = self._match_id(url)
 132
 133         request = sanitized_Request(
 134             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
 135             headers={'Origin': 'http://www.dcndigital.ae'})
 136
 137         channel_data = self._download_json(request, channel_id)
 138         info = self._extract_video_info(channel_data, channel_id, True)
 139
 140         webpage = self._download_webpage(
 141             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
 142             compat_urllib_parse_urlencode({
 143                 'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
 144                 'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
 145                 'signature': channel_data['signature'],
 146                 'countries': 'Q0M=',
 147                 'filter': 'DENY',
 148             }), channel_id)
 149         info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
 150         return info
 151
 152
 153 class DCNSeasonIE(InfoExtractor):
 154     IE_NAME = 'dcn:season'
 155     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 156     _TEST = {
 157         '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',
 158         'info_dict':
 159         {
 160             'id': '7910',
 161             'title': 'محاضرات الشيخ الشعراوي',
 162         },
 163         'playlist_mincount': 27,
 164     }
 165
 166     def _real_extract(self, url):
 167         url, smuggled_data = unsmuggle_url(url, {})
 168         show_id, season_id = re.match(self._VALID_URL, url).groups()
 169
 170         data = {}
 171         if season_id:
 172             data['season'] = season_id
 173             show_id = smuggled_data.get('show_id')
 174             if show_id is None:
 175                 request = sanitized_Request(
 176                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 177                     headers={'Origin': 'http://www.dcndigital.ae'})
 178                 season = self._download_json(request, season_id)
 179                 show_id = season['id']
 180         data['show_id'] = show_id
 181         request = sanitized_Request(
 182             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 183             urlencode_postdata(data),
 184             {
 185                 'Origin': 'http://www.dcndigital.ae',
 186                 'Content-Type': 'application/x-www-form-urlencoded'
 187             })
 188
 189         show = self._download_json(request, show_id)
 190         if not season_id:
 191             season_id = show['default_season']
 192         for season in show['seasons']:
 193             if season['id'] == season_id:
 194                 title = season.get('title_en') or season['title_ar']
 195
 196                 entries = []
 197                 for video in show['videos']:
 198                     video_id = compat_str(video['id'])
 199                     entries.append(self.url_result(
 200                         'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
 201
 202                 return self.playlist_result(entries, season_id, title)