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/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
  22     _TESTS = [{
  23         'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AC%D9%84%D8%B3-%D8%A7%D9%84%D8%B4%D8%A8%D8%A7%D8%A8-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-275286',
  24         'info_dict': {
  25             'id': '275286',
  26             'ext': 'mp4',
  27             'title': 'مجلس الشباب الموسم 1 كليب 1',
  28             'timestamp': 1506988800,
  29             'upload_date': '20171003',
  30         },
  31         'params': {
  32             # m3u8 download
  33             'skip_download': True,
  34         }
  35     }, {
  36         'url': 'https://shahid.mbc.net/ar/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746',
  37         'only_matching': True
  38     }, {
  39         # shahid plus subscriber only
  40         'url': 'https://shahid.mbc.net/ar/series/%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/episode-90511',
  41         'only_matching': True
  42     }]
  43
  44     def _api2_request(self, *args, **kwargs):
  45         try:
  46             return self._download_json(*args, **kwargs)
  47         except ExtractorError as e:
  48             if isinstance(e.cause, compat_HTTPError):
  49                 fail_data = self._parse_json(
  50                     e.cause.read().decode('utf-8'), None, fatal=False)
  51                 if fail_data:
  52                     faults = fail_data.get('faults', [])
  53                     faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
  54                     if faults_message:
  55                         raise ExtractorError(faults_message, expected=True)
  56             raise
  57
  58     def _real_initialize(self):
  59         email, password = self._get_login_info()
  60         if email is None:
  61             return
  62
  63         user_data = self._api2_request(
  64             'https://shahid.mbc.net/wd/service/users/login',
  65             None, 'Logging in', data=json.dumps({
  66                 'email': email,
  67                 'password': password,
  68                 'basic': 'false',
  69             }).encode('utf-8'), headers={
  70                 'Content-Type': 'application/json; charset=UTF-8',
  71             })['user']
  72
  73         self._download_webpage(
  74             'https://shahid.mbc.net/populateContext',
  75             None, 'Populate Context', data=urlencode_postdata({
  76                 'firstName': user_data['firstName'],
  77                 'lastName': user_data['lastName'],
  78                 'userName': user_data['email'],
  79                 'csg_user_name': user_data['email'],
  80                 'subscriberId': user_data['id'],
  81                 'sessionId': user_data['sessionId'],
  82             }))
  83
  84     def _get_api_data(self, response):
  85         data = response.get('data', {})
  86
  87         error = data.get('error')
  88         if error:
  89             raise ExtractorError(
  90                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
  91                 expected=True)
  92
  93         return data
  94
  95     def _real_extract(self, url):
  96         page_type, video_id = re.match(self._VALID_URL, url).groups()
  97         if page_type == 'clip':
  98             page_type = 'episode'
  99
 100         playout = self._api2_request(
 101             'https://api2.shahid.net/proxy/v2/playout/url/' + video_id,
 102             video_id, 'Downloading player JSON')['playout']
 103
 104         if playout.get('drm'):
 105             raise ExtractorError('This video is DRM protected.', expected=True)
 106
 107         formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')
 108         self._sort_formats(formats)
 109
 110         video = self._get_api_data(self._download_json(
 111             'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
 112             video_id, 'Downloading video JSON', query={
 113                 'apiKey': 'sh@hid0nlin3',
 114                 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
 115             }))[page_type]
 116
 117         title = video['title']
 118         categories = [
 119             category['name']
 120             for category in video.get('genres', []) if 'name' in category]
 121
 122         return {
 123             'id': video_id,
 124             'title': title,
 125             'description': video.get('description'),
 126             'thumbnail': video.get('thumbnailUrl'),
 127             'duration': int_or_none(video.get('duration')),
 128             'timestamp': parse_iso8601(video.get('referenceDate')),
 129             'categories': categories,
 130             'series': video.get('showTitle') or video.get('showName'),
 131             'season': video.get('seasonTitle'),
 132             'season_number': int_or_none(video.get('seasonNumber')),
 133             'season_id': str_or_none(video.get('seasonId')),
 134             'episode_number': int_or_none(video.get('number')),
 135             'episode_id': video_id,
 136             'formats': formats,
 137         }