Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/shahid.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_HTTPError
   9 from ..utils import (
  10     ExtractorError,
  11     int_or_none,
  12     parse_iso8601,
  13     str_or_none,
  14     urlencode_postdata,
  15     clean_html,
  16 )
  17
  18
  19 class ShahidIE(InfoExtractor):
  20     _NETRC_MACHINE = 'shahid'
  21     _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?P<type>episode|movie)/(?P<id>\d+)'
  22     _TESTS = [{
  23         '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',
  24         'info_dict': {
  25             'id': '90574',
  26             'ext': 'mp4',
  27             'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
  28             'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
  29             'duration': 2972,
  30             'timestamp': 1422057420,
  31             'upload_date': '20150123',
  32         },
  33         'params': {
  34             # m3u8 download
  35             'skip_download': True,
  36         }
  37     }, {
  38         'url': 'https://shahid.mbc.net/ar/movie/151746/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9.html',
  39         'only_matching': True
  40     }, {
  41         # shahid plus subscriber only
  42         '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',
  43         'only_matching': True
  44     }]
  45
  46     def _real_initialize(self):
  47         email, password = self._get_login_info()
  48         if email is None:
  49             return
  50
  51         try:
  52             user_data = self._download_json(
  53                 'https://shahid.mbc.net/wd/service/users/login',
  54                 None, 'Logging in', data=json.dumps({
  55                     'email': email,
  56                     'password': password,
  57                     'basic': 'false',
  58                 }).encode('utf-8'), headers={
  59                     'Content-Type': 'application/json; charset=UTF-8',
  60                 })['user']
  61         except ExtractorError as e:
  62             if isinstance(e.cause, compat_HTTPError):
  63                 fail_data = self._parse_json(
  64                     e.cause.read().decode('utf-8'), None, fatal=False)
  65                 if fail_data:
  66                     faults = fail_data.get('faults', [])
  67                     faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
  68                     if faults_message:
  69                         raise ExtractorError(faults_message, expected=True)
  70             raise
  71
  72         self._download_webpage(
  73             'https://shahid.mbc.net/populateContext',
  74             None, 'Populate Context', data=urlencode_postdata({
  75                 'firstName': user_data['firstName'],
  76                 'lastName': user_data['lastName'],
  77                 'userName': user_data['email'],
  78                 'csg_user_name': user_data['email'],
  79                 'subscriberId': user_data['id'],
  80                 'sessionId': user_data['sessionId'],
  81             }))
  82
  83     def _get_api_data(self, response):
  84         data = response.get('data', {})
  85
  86         error = data.get('error')
  87         if error:
  88             raise ExtractorError(
  89                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
  90                 expected=True)
  91
  92         return data
  93
  94     def _real_extract(self, url):
  95         page_type, video_id = re.match(self._VALID_URL, url).groups()
  96
  97         player = self._get_api_data(self._download_json(
  98             'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-player.html' % video_id,
  99             video_id, 'Downloading player JSON'))
 100
 101         if player.get('drm'):
 102             raise ExtractorError('This video is DRM protected.', expected=True)
 103
 104         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
 105         self._sort_formats(formats)
 106
 107         video = self._get_api_data(self._download_json(
 108             'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
 109             video_id, 'Downloading video JSON', query={
 110                 'apiKey': 'sh@hid0nlin3',
 111                 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
 112             }))[page_type]
 113
 114         title = video['title']
 115         categories = [
 116             category['name']
 117             for category in video.get('genres', []) if 'name' in category]
 118
 119         return {
 120             'id': video_id,
 121             'title': title,
 122             'description': video.get('description'),
 123             'thumbnail': video.get('thumbnailUrl'),
 124             'duration': int_or_none(video.get('duration')),
 125             'timestamp': parse_iso8601(video.get('referenceDate')),
 126             'categories': categories,
 127             'series': video.get('showTitle') or video.get('showName'),
 128             'season': video.get('seasonTitle'),
 129             'season_number': int_or_none(video.get('seasonNumber')),
 130             'season_id': str_or_none(video.get('seasonId')),
 131             'episode_number': int_or_none(video.get('number')),
 132             'episode_id': video_id,
 133             'formats': formats,
 134         }