_ Git - youtube-dl/blob - youtube_dl/extractor/dcn.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13     parse_iso8601,
  14 )
  15
  16
  17 class DCNGeneralIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
  19
  20     def _real_extract(self, url):
  21         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
  22         url = ''
  23         ie_key = ''
  24         if video_id and int(video_id) > 0:
  25             url = 'http://www.dcndigital.ae/#/media/%s' % video_id
  26             ie_key = 'DCNVideo'
  27         else:
  28             ie_key = 'DCNShow'
  29             if season_id and int(season_id) > 0:
  30                 url = 'http://www.dcndigital.ae/#/program/season/%s' % season_id
  31             else:
  32                 url = 'http://www.dcndigital.ae/#/program/%s' % show_id
  33         return {
  34             'url': url,
  35             '_type': 'url',
  36             'ie_key': ie_key
  37         }
  38
  39
  40 class DCNVideoIE(InfoExtractor):
  41     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media)/(?P<id>\d+)'
  42     _TEST = {
  43         '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',
  44         'info_dict':
  45         {
  46             'id': '17375',
  47             'ext': 'mp4',
  48             'title': 'رحلة العمر : الحلقة 1',
  49             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  50             'thumbnail': 're:^https?://.*\.jpg$',
  51             'duration': 2041,
  52             'timestamp': 1227504126,
  53             'upload_date': '20081124',
  54         },
  55         'params': {
  56             # m3u8 download
  57             'skip_download': True,
  58         },
  59     }
  60
  61     def _real_extract(self, url):
  62         video_id = self._match_id(url)
  63
  64         request = compat_urllib_request.Request(
  65             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
  66             headers={'Origin': 'http://www.dcndigital.ae'})
  67
  68         video = self._download_json(request, video_id)
  69         title = video.get('title_en') or video['title_ar']
  70
  71         webpage = self._download_webpage(
  72             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
  73             + compat_urllib_parse.urlencode({
  74                 'id': video['id'],
  75                 'user_id': video['user_id'],
  76                 'signature': video['signature'],
  77                 'countries': 'Q0M=',
  78                 'filter': 'DENY',
  79             }), video_id)
  80
  81         m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
  82         formats = self._extract_m3u8_formats(
  83             m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  84
  85         rtsp_url = self._search_regex(
  86             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  87         if rtsp_url:
  88             formats.append({
  89                 'url': rtsp_url,
  90                 'format_id': 'rtsp',
  91             })
  92
  93         self._sort_formats(formats)
  94
  95         img = video.get('img')
  96         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
  97         duration = int_or_none(video.get('duration'))
  98         description = video.get('description_en') or video.get('description_ar')
  99         timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
 100
 101         return {
 102             'id': video_id,
 103             'title': title,
 104             'description': description,
 105             'thumbnail': thumbnail,
 106             'duration': duration,
 107             'timestamp': timestamp,
 108             'formats': formats,
 109         }
 110
 111
 112 class DCNShowIE(InfoExtractor):
 113     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 114     _TEST = {
 115         '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',
 116         'info_dict':
 117         {
 118             'id': '205024',
 119             'title': 'محاضرات الشيخ الشعراوي',
 120             'description': '',
 121         },
 122         'playlist_mincount': 27,
 123     }
 124
 125     def _real_extract(self, url):
 126         show_id, season_id = re.match(self._VALID_URL, url).groups()
 127         data = {}
 128         if season_id:
 129             request = compat_urllib_request.Request(
 130                 'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 131                 headers={'Origin': 'http://www.dcndigital.ae'})
 132             season = self._download_json(request, season_id)
 133             show_id = season['id']
 134             data['season'] = season_id
 135         data['show_id'] = show_id
 136         request = compat_urllib_request.Request(
 137             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 138             compat_urllib_parse.urlencode(data),
 139             {
 140                 'Origin': 'http://www.dcndigital.ae',
 141                 'Content-Type': 'application/x-www-form-urlencoded'
 142             })
 143         show = self._download_json(request, show_id)
 144         title = show['cat'].get('title_en') or show['cat']['title_ar']
 145         description = show['cat'].get('description_en') or show['cat'].get('description_ar')
 146         entries = []
 147         for video in show['videos']:
 148             entries.append({
 149                 'url': 'http://www.dcndigital.ae/#/media/%s' % video['id'],
 150                 '_type': 'url',
 151                 'ie_key': 'DCNVideo',
 152             })
 153         return {
 154             'id': show_id,
 155             'title': title,
 156             'description': description,
 157             'entries': entries,
 158             '_type': 'playlist',
 159         }