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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     js_to_json,
   7     ExtractorError,
   8     int_or_none
   9 )
  10
  11
  12 class ShahidIE(InfoExtractor):
  13     _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
  14     _TESTS = [
  15         {
  16             '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',
  17             'info_dict': {
  18                 'id': '108084',
  19                 'ext': 'm3u8',
  20                 'title': 'خواطر الموسم 11 الحلقة 1',
  21                 'description': 'بسم الله',
  22                 'duration': 1166,
  23             },
  24             'params': {
  25                 # m3u8 download
  26                 'skip_download': True,
  27             }
  28         },
  29         {
  30             # shahid plus subscriber only
  31             'url': 'https://shahid.mbc.net/ar/series/90497/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011.html',
  32             'only_matching': True
  33         }
  34     ]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         webpage = self._download_webpage(url, video_id)
  39
  40         player_info = ''
  41         for line in self._search_regex('var flashvars = ({[^}]+})', webpage, 'flashvars').splitlines():
  42             if '+' not in line and '(' not in line and ')' not in line:
  43                 player_info += line
  44         player_info = self._parse_json(js_to_json(player_info), video_id)
  45         video_id = player_info['id']
  46         player_type = player_info['playerType']
  47
  48         player_json_data = self._download_json(
  49             'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + player_info['type'] + '.html',
  50             video_id
  51         )['data']
  52         if 'url' in player_json_data:
  53             m3u8_url = player_json_data['url']
  54         else:
  55             for error in player_json_data['error'].values():
  56                 raise ExtractorError(error)
  57         formats = self._extract_m3u8_formats(m3u8_url, video_id)
  58
  59         video_info = self._download_json(
  60             player_info['url'] + '/' + player_type + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D',
  61             video_id
  62         )['data']
  63         if video_info.get('error'):
  64             for error in video_info['error']:
  65                 raise ExtractorError(error)
  66         video_info = video_info[player_type]
  67         title = video_info['title']
  68         thumbnail = video_info.get('thumbnailUrl')
  69         categories = [category['name'] for category in video_info.get('genres')]
  70         description = video_info.get('description')
  71         duration = int_or_none(video_info.get('duration'))
  72
  73         return {
  74             'id': video_id,
  75             'title': title,
  76             'thumbnail': thumbnail,
  77             'categories': categories,
  78             'description': description,
  79             'duration': duration,
  80             'formats': formats,
  81         }