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,
  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 )
  19
  20
  21 class DCNIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
  23
  24     def _real_extract(self, url):
  25         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
  26         if video_id and int(video_id) > 0:
  27             return self.url_result(
  28                 'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
  29         elif season_id and int(season_id) > 0:
  30             return self.url_result(smuggle_url(
  31                 'http://www.dcndigital.ae/program/season/%s' % season_id,
  32                 {'show_id': show_id}), 'DCNSeason')
  33         else:
  34             return self.url_result(
  35                 'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
  36
  37
  38 class DCNBaseIE(InfoExtractor):
  39     def _extract_video_info(self, video_data, video_id, is_live):
  40         title = video_data.get('title_en') or video_data['title_ar']
  41         img = video_data.get('img')
  42         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
  43         duration = int_or_none(video_data.get('duration'))
  44         description = video_data.get('description_en') or video_data.get('description_ar')
  45         timestamp = parse_iso8601(video_data.get('create_time'), ' ')
  46
  47         return {
  48             'id': video_id,
  49             'title': self._live_title(title) if is_live else title,
  50             'description': description,
  51             'thumbnail': thumbnail,
  52             'duration': duration,
  53             'timestamp': timestamp,
  54             'is_live': is_live,
  55         }
  56
  57     def _extract_video_formats(self, webpage, video_id, entry_protocol):
  58         formats = []
  59         m3u8_url = self._html_search_regex(
  60             r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False)
  61         if m3u8_url:
  62             formats.extend(self._extract_m3u8_formats(
  63                 m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None))
  64
  65         rtsp_url = self._search_regex(
  66             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  67         if rtsp_url:
  68             formats.append({
  69                 'url': rtsp_url,
  70                 'format_id': 'rtsp',
  71             })
  72
  73         self._sort_formats(formats)
  74         return formats
  75
  76
  77 class DCNVideoIE(DCNBaseIE):
  78     IE_NAME = 'dcn:video'
  79     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
  80     _TEST = {
  81         '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',
  82         'info_dict':
  83         {
  84             'id': '17375',
  85             'ext': 'mp4',
  86             'title': 'رحلة العمر : الحلقة 1',
  87             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  88             'duration': 2041,
  89             'timestamp': 1227504126,
  90             'upload_date': '20081124',
  91         },
  92         'params': {
  93             # m3u8 download
  94             'skip_download': True,
  95         },
  96     }
  97
  98     def _real_extract(self, url):
  99         video_id = self._match_id(url)
 100
 101         request = sanitized_Request(
 102             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
 103             headers={'Origin': 'http://www.dcndigital.ae'})
 104         video_data = self._download_json(request, video_id)
 105         info = self._extract_video_info(video_data, video_id, False)
 106
 107         webpage = self._download_webpage(
 108             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
 109             compat_urllib_parse.urlencode({
 110                 'id': video_data['id'],
 111                 'user_id': video_data['user_id'],
 112                 'signature': video_data['signature'],
 113                 'countries': 'Q0M=',
 114                 'filter': 'DENY',
 115             }), video_id)
 116         info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
 117         return info
 118
 119
 120 class DCNLiveIE(DCNBaseIE):
 121     IE_NAME = 'dcn:live'
 122     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
 123
 124     def _real_extract(self, url):
 125         channel_id = self._match_id(url)
 126
 127         request = sanitized_Request(
 128             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
 129             headers={'Origin': 'http://www.dcndigital.ae'})
 130
 131         channel_data = self._download_json(request, channel_id)
 132         info = self._extract_video_info(channel_data, channel_id, True)
 133
 134         webpage = self._download_webpage(
 135             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
 136             compat_urllib_parse.urlencode({
 137                 'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
 138                 'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
 139                 'signature': channel_data['signature'],
 140                 'countries': 'Q0M=',
 141                 'filter': 'DENY',
 142             }), channel_id)
 143         info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
 144         return info
 145
 146
 147 class DCNSeasonIE(InfoExtractor):
 148     IE_NAME = 'dcn:season'
 149     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 150     _TEST = {
 151         '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',
 152         'info_dict':
 153         {
 154             'id': '7910',
 155             'title': 'محاضرات الشيخ الشعراوي',
 156         },
 157         'playlist_mincount': 27,
 158     }
 159
 160     def _real_extract(self, url):
 161         url, smuggled_data = unsmuggle_url(url, {})
 162         show_id, season_id = re.match(self._VALID_URL, url).groups()
 163
 164         data = {}
 165         if season_id:
 166             data['season'] = season_id
 167             show_id = smuggled_data.get('show_id')
 168             if show_id is None:
 169                 request = sanitized_Request(
 170                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 171                     headers={'Origin': 'http://www.dcndigital.ae'})
 172                 season = self._download_json(request, season_id)
 173                 show_id = season['id']
 174         data['show_id'] = show_id
 175         request = sanitized_Request(
 176             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 177             compat_urllib_parse.urlencode(data),
 178             {
 179                 'Origin': 'http://www.dcndigital.ae',
 180                 'Content-Type': 'application/x-www-form-urlencoded'
 181             })
 182
 183         show = self._download_json(request, show_id)
 184         if not season_id:
 185             season_id = show['default_season']
 186         for season in show['seasons']:
 187             if season['id'] == season_id:
 188                 title = season.get('title_en') or season['title_ar']
 189
 190                 entries = []
 191                 for video in show['videos']:
 192                     video_id = compat_str(video['id'])
 193                     entries.append(self.url_result(
 194                         'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
 195
 196                 return self.playlist_result(entries, season_id, title)