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

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     js_to_json,
   4     ExtractorError,
   5     int_or_none
   6 )
   7
   8 class ShahidIE(InfoExtractor):
   9     _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
  10     _TESTS = [
  11         {
  12             'url': 'https://shahid.mbc.net/ar/episode/108084/%D8%AE%D9%88%D8%A7%D8%B7%D8%B1-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-11-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
  13             'info_dict': {
  14                 'id': '108084',
  15                 'ext': 'm3u8',
  16                 'title': 'خواطر الموسم 11 الحلقة 1',
  17                 'description': 'بسم الله',
  18                 'duration': 1166,
  19             },
  20             'params': {
  21                 # m3u8 download
  22                 'skip_download': True,
  23             }
  24         },
  25         {
  26             #shahid plus subscriber only
  27             'url': 'https://shahid.mbc.net/ar/series/90497/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011.html',
  28             'only_matching': True
  29         }
  30     ]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         webpage = self._download_webpage(url, video_id)
  35         player_info = ''
  36         for line in self._search_regex( 'var flashvars = ({[^}]+})', webpage, 'flashvars').splitlines():
  37             if '+' not in line and '(' not in line and ')' not in line:
  38                 player_info += line
  39         player_info = self._parse_json(js_to_json(player_info), video_id)
  40         video_id = player_info['id']
  41         player_type = player_info['playerType']
  42
  43         video_info = self._download_json(
  44             player_info['url'] + '/' + player_type + '/' + video_id +
  45                 '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D',
  46             video_id
  47         )['data']
  48         if video_info['error']:
  49             for error in video_info['error']:
  50                 raise ExtractorError(error)
  51         video_info = video_info[player_type]
  52         if video_info.get('availabilities').get('plus'):
  53             raise ExtractorError('plus members only')
  54         title = video_info['title']
  55         thumbnail = video_info.get('thumbnailUrl')
  56         categories = [category['name'] for category in video_info.get('genres')]
  57         description = video_info.get('description')
  58         duration = int_or_none(video_info.get('duration'))
  59
  60         player_json_data = self._download_json(
  61             'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + player_info['type'] + '.html',
  62             video_id
  63         )['data']
  64         if 'url' in player_json_data:
  65             m3u8_url = player_json_data['url']
  66         else:
  67             for error in json_data['error'].values():
  68                 raise ExtractorError(error)
  69             return
  70         formats = self._extract_m3u8_formats(m3u8_url, video_id)
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'thumbnail': thumbnail,
  75             'categories': categories,
  76             'description': description,
  77             'duration': duration,
  78             'formats': formats,
  79         }