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