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     smuggle_url,
  15     unsmuggle_url,
  16 )
  17
  18
  19 class DCNGeneralIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
  21
  22     def _real_extract(self, url):
  23         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
  24         url = ''
  25         ie_key = ''
  26         if video_id and int(video_id) > 0:
  27             url = 'http://www.dcndigital.ae/#/media/%s' % video_id
  28             ie_key = 'DCNVideo'
  29         else:
  30             ie_key = 'DCNSeason'
  31             if season_id and int(season_id) > 0:
  32                 url = smuggle_url('http://www.dcndigital.ae/#/program/season/%s' % season_id, {'show_id': show_id})
  33             else:
  34                 url = 'http://www.dcndigital.ae/#/program/%s' % show_id
  35         return {
  36             'url': url,
  37             '_type': 'url',
  38             'ie_key': ie_key
  39         }
  40
  41
  42 class DCNVideoIE(InfoExtractor):
  43     IE_NAME = 'dcn:video'
  44     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media)/(?P<id>\d+)'
  45     _TEST = {
  46         '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',
  47         'info_dict':
  48         {
  49             'id': '17375',
  50             'ext': 'mp4',
  51             'title': 'رحلة العمر : الحلقة 1',
  52             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  53             'thumbnail': 're:^https?://.*\.jpg$',
  54             'duration': 2041,
  55             'timestamp': 1227504126,
  56             'upload_date': '20081124',
  57         },
  58         'params': {
  59             # m3u8 download
  60             'skip_download': True,
  61         },
  62     }
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66
  67         request = compat_urllib_request.Request(
  68             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
  69             headers={'Origin': 'http://www.dcndigital.ae'})
  70
  71         video = self._download_json(request, video_id)
  72         title = video.get('title_en') or video['title_ar']
  73
  74         webpage = self._download_webpage(
  75             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
  76             + compat_urllib_parse.urlencode({
  77                 'id': video['id'],
  78                 'user_id': video['user_id'],
  79                 'signature': video['signature'],
  80                 'countries': 'Q0M=',
  81                 'filter': 'DENY',
  82             }), video_id)
  83
  84         m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
  85         formats = self._extract_m3u8_formats(
  86             m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  87
  88         rtsp_url = self._search_regex(
  89             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  90         if rtsp_url:
  91             formats.append({
  92                 'url': rtsp_url,
  93                 'format_id': 'rtsp',
  94             })
  95
  96         self._sort_formats(formats)
  97
  98         img = video.get('img')
  99         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
 100         duration = int_or_none(video.get('duration'))
 101         description = video.get('description_en') or video.get('description_ar')
 102         timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'description': description,
 108             'thumbnail': thumbnail,
 109             'duration': duration,
 110             'timestamp': timestamp,
 111             'formats': formats,
 112         }
 113
 114
 115 class DCNSeasonIE(InfoExtractor):
 116     IE_NAME = 'dcn:season'
 117     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
 118     _TEST = {
 119         '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',
 120         'info_dict':
 121         {
 122             'id': '7910',
 123             'title': 'محاضرات الشيخ الشعراوي',
 124             'description': '',
 125         },
 126         'playlist_mincount': 27,
 127     }
 128
 129     def _real_extract(self, url):
 130         url, smuggled_data = unsmuggle_url(url, {})
 131         show_id, season_id = re.match(self._VALID_URL, url).groups()
 132         data = {}
 133         if season_id:
 134             data['season'] = season_id
 135             show_id = smuggled_data.get('show_id')
 136             if show_id is None:
 137                 request = compat_urllib_request.Request(
 138                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
 139                     headers={'Origin': 'http://www.dcndigital.ae'})
 140                 season = self._download_json(request, season_id)
 141                 show_id = season['id']
 142         data['show_id'] = show_id
 143         request = compat_urllib_request.Request(
 144             'http://admin.mangomolo.com/analytics/index.php/plus/show',
 145             compat_urllib_parse.urlencode(data),
 146             {
 147                 'Origin': 'http://www.dcndigital.ae',
 148                 'Content-Type': 'application/x-www-form-urlencoded'
 149             })
 150         show = self._download_json(request, show_id)
 151         season_id = season_id or show['default_season']
 152         title = show['cat'].get('title_en') or show['cat']['title_ar']
 153         description = show['cat'].get('description_en') or show['cat'].get('description_ar')
 154         entries = []
 155         for video in show['videos']:
 156             entries.append({
 157                 'url': 'http://www.dcndigital.ae/#/media/%s' % video['id'],
 158                 '_type': 'url',
 159                 'ie_key': 'DCNVideo',
 160             })
 161         return {
 162             'id': season_id,
 163             'title': title,
 164             'description': description,
 165             'entries': entries,
 166             '_type': 'playlist',
 167         }