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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_request
   6
   7
   8 class DcnIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)/?'
  10     _TEST = {
  11         'url': 'http://www.dcndigital.ae/#/show/199074/%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%A9-1/17375/6887',
  12         'info_dict':
  13         {
  14             'id': '17375',
  15             'ext': 'm3u8',
  16             'title': 'رحلة العمر : الحلقة 1',
  17             'description': 'في هذه الحلقة من برنامج رحلة العمر يقدّم الدكتور عمر عبد الكافي تبسيطاً لمناسك الحج والعمرة ويجيب مباشرة على استفسارات حجاج بيت الله الحرام بخصوص مناسك الحج والعمرة\n1',
  18             'thumbnail': 'http://admin.mangomolo.com/analytics/uploads/71/images/media/2/2cefc09d7bec80afa754682f40e49503.jpg',
  19             'duration': '2041'
  20         },
  21         'params': {
  22             # m3u8 download
  23             'skip_download': True,
  24         },
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         request = compat_urllib_request.Request(
  30             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=' + video_id,
  31             headers={'Origin': 'http://www.dcndigital.ae'}
  32         )
  33         json_data = self._download_json(request, video_id)
  34         title = json_data['title_ar']
  35         thumbnail = 'http://admin.mangomolo.com/analytics/' + json_data['img']
  36         duration = json_data['duration']
  37         description = json_data['description_ar']
  38         webpage = self._download_webpage(
  39             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?id=' + json_data['id'] + '&user_id=' + json_data['user_id'] + '&countries=Q0M=&w=100%&h=100%&filter=DENY&signature=' + json_data['signature'],
  40             video_id
  41         )
  42         m3u8_url = self._html_search_regex(
  43             r'file:\s*"([^"]+)',
  44             webpage,
  45             'm3u8_url'
  46         )
  47         formats = self._extract_m3u8_formats(m3u8_url, video_id)
  48         return {
  49             'id': video_id,
  50             'title': title,
  51             'thumbnail': thumbnail,
  52             'duration': duration,
  53             'description': description,
  54             'formats': formats,
  55         }