Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/shahid.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     ExtractorError,
   8     int_or_none,
   9     parse_iso8601,
  10 )
  11
  12
  13 class ShahidIE(InfoExtractor):
  14     _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
  15     _TESTS = [{
  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': 'mp4',
  20             'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
  21             'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
  22             'duration': 2972,
  23             'timestamp': 1422057420,
  24             'upload_date': '20150123',
  25         },
  26         'params': {
  27             # m3u8 download
  28             'skip_download': True,
  29         }
  30     }, {
  31         # shahid plus subscriber only
  32         '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',
  33         'only_matching': True
  34     }]
  35
  36     def _handle_error(self, response):
  37         if not isinstance(response, dict):
  38             return
  39         error = response.get('error')
  40         if error:
  41             raise ExtractorError(
  42                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
  43                 expected=True)
  44
  45     def _download_json(self, url, video_id, note='Downloading JSON metadata'):
  46         response = super(ShahidIE, self)._download_json(url, video_id, note)['data']
  47         self._handle_error(response)
  48         return response
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52
  53         webpage = self._download_webpage(url, video_id)
  54
  55         api_vars = {
  56             'id': video_id,
  57             'type': 'player',
  58             'url': 'http://api.shahid.net/api/v1_1',
  59             'playerType': 'episode',
  60         }
  61
  62         flashvars = self._search_regex(
  63             r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None)
  64         if flashvars:
  65             for key in api_vars.keys():
  66                 value = self._search_regex(
  67                     r'\b%s\s*:\s*(?P<q>["\'])(?P<value>.+?)(?P=q)' % key,
  68                     flashvars, 'type', default=None, group='value')
  69                 if value:
  70                     api_vars[key] = value
  71
  72         player = self._download_json(
  73             'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html'
  74             % (video_id, api_vars['type']), video_id, 'Downloading player JSON')
  75
  76         if player.get('drm'):
  77             raise ExtractorError('This video is DRM protected.', expected=True)
  78
  79         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
  80
  81         video = self._download_json(
  82             '%s/%s/%s?%s' % (
  83                 api_vars['url'], api_vars['playerType'], api_vars['id'],
  84                 compat_urllib_parse.urlencode({
  85                     'apiKey': 'sh@hid0nlin3',
  86                     'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
  87                 })),
  88             video_id, 'Downloading video JSON')
  89
  90         video = video[api_vars['playerType']]
  91
  92         title = video['title']
  93         description = video.get('description')
  94         thumbnail = video.get('thumbnailUrl')
  95         duration = int_or_none(video.get('duration'))
  96         timestamp = parse_iso8601(video.get('referenceDate'))
  97         categories = [
  98             category['name']
  99             for category in video.get('genres', []) if 'name' in category]
 100
 101         return {
 102             'id': video_id,
 103             'title': title,
 104             'description': description,
 105             'thumbnail': thumbnail,
 106             'duration': duration,
 107             'timestamp': timestamp,
 108             'categories': categories,
 109             'formats': formats,
 110         }