_ 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 from ..utils import int_or_none
   7
   8
   9 class DcnIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)/?'
  11     _TEST = {
  12         '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',
  13         'info_dict':
  14         {
  15             'id': '17375',
  16             'ext': 'm3u8',
  17             'title': 'رحلة العمر : الحلقة 1',
  18             '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',
  19             'thumbnail': 'http://admin.mangomolo.com/analytics/uploads/71/images/media/2/2cefc09d7bec80afa754682f40e49503.jpg',
  20             'duration': 2041
  21         },
  22         'params': {
  23             # m3u8 download
  24             'skip_download': True,
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         request = compat_urllib_request.Request(
  31             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=' + video_id,
  32             headers={'Origin': 'http://www.dcndigital.ae'}
  33         )
  34         json_data = self._download_json(request, video_id)
  35         title = json_data['title_ar']
  36         thumbnail = 'http://admin.mangomolo.com/analytics/' + json_data.get('img')
  37         duration = int_or_none(json_data.get('duration'))
  38         description = json_data.get('description_ar')
  39         webpage = self._download_webpage(
  40             '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'],
  41             video_id
  42         )
  43         m3u8_url = self._html_search_regex(
  44             r'file:\s*"([^"]+)',
  45             webpage,
  46             'm3u8_url'
  47         )
  48         formats = self._extract_m3u8_formats(m3u8_url, video_id)
  49         return {
  50             'id': video_id,
  51             'title': title,
  52             'thumbnail': thumbnail,
  53             'duration': duration,
  54             'description': description,
  55             'formats': formats,
  56         }