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

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     get_element_by_id,
   4     ExtractorError,
   5 }
   6
   7 class ShahidIE(InfoExtractor):
   8     _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
   9     _TESTS = [
  10         {
  11             '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',
  12             'info_dict': {
  13                 'id': '108084',
  14                 'ext': 'm3u8',
  15                 'title': 'بسم الله',
  16                 'description': 'بسم الله'
  17             },
  18             'params': {
  19                 # m3u8 download
  20                 'skip_download': True,
  21             }
  22         },
  23         {
  24             #shahid plus subscriber only
  25             'url': 'https://shahid.mbc.net/ar/series/90497/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011.html',
  26             'only_matching': True
  27         }
  28     ]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33         json_data = self._parse_json(
  34             get_element_by_id('jsonld', webpage),
  35             video_id
  36         )
  37         title = json_data['name']
  38         thumbnail = json_data['image']
  39         categories = json_data['genre']
  40         description = json_data['description']
  41         player_json_data = self._download_json(
  42             'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-'+video_id+'.type-player.html',
  43             video_id
  44         )['data']
  45         if 'url' in player_json_data:
  46             m3u8_url = player_json_data['url']
  47         else:
  48             for error in json_data['error'].values():
  49                 raise ExtractorError(error)
  50             return
  51         formats = self._extract_m3u8_formats(m3u8_url, video_id)
  52         return {
  53             'id': video_id,
  54             'title': title,
  55             'thumbnail': thumbnail,
  56             'categories': categories,
  57             'description': description,
  58             'formats': formats,
  59         }