_ 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/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html',
  17             'info_dict': {
  18                 'id': '90574',
  19                 'ext': 'm3u8',
  20                 'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
  21                 'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
  22                 'duration': 2972,
  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/episode/90511/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
  32             'only_matching': True
  33         }
  34     ]
  35
  36     _api_vars = {
  37         'type': 'player',
  38         'url': 'http://api.shahid.net/api/v1_1',
  39         'playerType': 'episode',
  40     }
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44         webpage = self._download_webpage(url, video_id)
  45
  46         player_info = ''
  47         flash_vars = self._search_regex('var flashvars = ({[^}]+})', webpage, 'flashvars', None)
  48         if flash_vars is not None:
  49             for line in flash_vars.splitlines():
  50                 if '+' not in line and '(' not in line and ')' not in line:
  51                     player_info += line
  52             player_info = self._parse_json(player_info, video_id, js_to_json, False)
  53             if player_info is not None:
  54                 for key in self._api_vars:
  55                     if key in player_info:
  56                         self._api_vars[key] = player_info[key]
  57
  58         player_json_data = self._download_json(
  59             'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + self._api_vars['type'] + '.html',
  60             video_id
  61         )['data']
  62         if 'url' in player_json_data:
  63             m3u8_url = player_json_data['url']
  64         else:
  65             for error in player_json_data['error'].values():
  66                 raise ExtractorError(error)
  67         formats = self._extract_m3u8_formats(m3u8_url, video_id)
  68
  69         video_info = self._download_json(
  70             self._api_vars['url'] + '/' + self._api_vars['playerType'] + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D',
  71             video_id
  72         )['data']
  73         if video_info.get('error'):
  74             for error in video_info['error']:
  75                 raise ExtractorError(error)
  76         video_info = video_info[self._api_vars['playerType']]
  77         title = video_info['title']
  78         thumbnail = video_info.get('thumbnailUrl')
  79         categories = [category['name'] for category in video_info.get('genres')]
  80         description = video_info.get('description')
  81         duration = int_or_none(video_info.get('duration'))
  82
  83         return {
  84             'id': video_id,
  85             'title': title,
  86             'thumbnail': thumbnail,
  87             'categories': categories,
  88             'description': description,
  89             'duration': duration,
  90             'formats': formats,
  91         }