Raphaël G. Git Repositories - youtubedl/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 (
   6     compat_urllib_parse,
   7     compat_urllib_request,
   8 )
   9 from ..utils import (
  10     int_or_none,
  11     parse_iso8601,
  12 )
  13
  14
  15 class DCNIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)'
  17     _TEST = {
  18         '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',
  19         'info_dict':
  20         {
  21             'id': '17375',
  22             'ext': 'mp4',
  23             'title': 'رحلة العمر : الحلقة 1',
  24             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26             'duration': 2041,
  27             'timestamp': 1227504126,
  28             'upload_date': '20081124',
  29         },
  30         'params': {
  31             # m3u8 download
  32             'skip_download': True,
  33         },
  34     }
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         request = compat_urllib_request.Request(
  40             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
  41             headers={'Origin': 'http://www.dcndigital.ae'})
  42
  43         video = self._download_json(request, video_id)
  44         title = video.get('title_en') or video['title_ar']
  45
  46         webpage = self._download_webpage(
  47             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
  48             compat_urllib_parse.urlencode({
  49                 'id': video['id'],
  50                 'user_id': video['user_id'],
  51                 'signature': video['signature'],
  52                 'countries': 'Q0M=',
  53                 'filter': 'DENY',
  54             }), video_id)
  55
  56         m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
  57         formats = self._extract_m3u8_formats(
  58             m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  59
  60         rtsp_url = self._search_regex(
  61             r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
  62         if rtsp_url:
  63             formats.append({
  64                 'url': rtsp_url,
  65                 'format_id': 'rtsp',
  66             })
  67
  68         self._sort_formats(formats)
  69
  70         img = video.get('img')
  71         thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
  72         duration = int_or_none(video.get('duration'))
  73         description = video.get('description_en') or video.get('description_ar')
  74         timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
  75
  76         return {
  77             'id': video_id,
  78             'title': title,
  79             'description': description,
  80             'thumbnail': thumbnail,
  81             'duration': duration,
  82             'timestamp': timestamp,
  83             'formats': formats,
  84         }