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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_HTTPError
   9 )
  10 from ..utils import (
  11     sanitized_Request,
  12     ExtractorError
  13 )
  14
  15
  16 class HRTiIE(InfoExtractor):
  17     '''
  18     Information Extractor for Croatian Radiotelevision video on demand site
  19     https://hrti.hrt.hr
  20     Reverse engineered from the JavaScript app in app.min.js
  21     '''
  22     _NETRC_MACHINE = 'hrti'
  23
  24     APP_LANGUAGE = 'hr'
  25     APP_VERSION = '1.1'
  26     APP_PUBLICATION_ID = 'all_in_one'
  27
  28     _VALID_URL = r'https?://hrti.hrt.hr/#/video/show/(?P<id>[0-9]+)/(?P<name>(\w|-)+)?'
  29     _TEST = {
  30         'url': 'https://hrti.hrt.hr/#/video/show/2181385/republika-dokumentarna-serija-16-hd',
  31         'info_dict': {
  32             'id': '2181385',
  33             'ext': 'mp4',
  34             'name': 'REPUBLIKA, dokumentarna serija (4_6)-2251938',
  35         },
  36         'skip': 'Requires login'
  37     }
  38
  39     def _initialize_api(self):
  40         '''Initializes the API and obtains the required urls'''
  41         api_url = 'http://clientapi.hrt.hr/client_api.php/config/identify/format/json'
  42         app_data = json.dumps({
  43             'application_publication_id': HRTiIE.APP_PUBLICATION_ID
  44         })
  45         self.uuid = self._download_json(api_url, None, note='Getting UUID',
  46                                         errnote='Unable to obtain an UUID',
  47                                         data=app_data)['uuid']
  48
  49         app_data = json.dumps({
  50             'uuid': self.uuid,
  51             'application_publication_id': HRTiIE.APP_PUBLICATION_ID,
  52             'screen_height': 1080,
  53             'screen_width': 1920,
  54             'os': 'Windows',
  55             'os_version': 'NT 4.0',
  56             'device_model_string_id': 'chrome 42.0.2311.135',
  57             'application_version': HRTiIE.APP_VERSION
  58         })
  59
  60         req = sanitized_Request(api_url, data=app_data)
  61         req.get_method = lambda: 'PUT'
  62
  63         resources = self._download_json(
  64             req, None, note='Getting API endpoint and session information',
  65             errnote='Unable to get endpoint and session information',
  66             headers={'Content-type': 'application/json'})
  67
  68         self.session_id = resources['session_id']
  69         modules = resources['modules']
  70
  71         self.search_url = modules['vod_catalog']['resources']['search']['uri']
  72         self.search_url = self.search_url.format(
  73             language=HRTiIE.APP_LANGUAGE,
  74             application_id=HRTiIE.APP_PUBLICATION_ID)
  75
  76         self.login_url = modules['user']['resources']['login']['uri']
  77         self.login_url = self.login_url.format(session_id=self.session_id)
  78         self.login_url += '/format/json'
  79
  80         self.logout_url = modules['user']['resources']['logout']['uri']
  81
  82     def _login(self):
  83         '''Performs a login to the webservice'''
  84         (username, password) = self._get_login_info()
  85
  86         if username is None or password is None:
  87             self.raise_login_required()
  88
  89         auth_data = json.dumps({
  90             'username': username,
  91             'password': password,
  92         })
  93         try:
  94             auth_info = self._download_json(
  95                 self.login_url, None, note='Authenticating',
  96                 errnote='Unable to log in', data=auth_data)
  97         except ExtractorError as ee:
  98             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 406:
  99                 raise ExtractorError('Unable to login, ' +
 100                                      'incorrect username and/or password')
 101             raise
 102
 103         self.token = auth_info['secure_streaming_token']
 104         self.access_token = auth_info['session_token']
 105
 106         self.logout_url = self.logout_url.format(session_id=self.session_id,
 107                                                  access_token=self.access_token)
 108         self.logout_url += '/format/json'
 109
 110     def _real_initialize(self):
 111         '''Performs necessary operations so that the information extractor is
 112         ready for operation'''
 113         self._initialize_api()
 114         self._login()
 115
 116     def _logout(self):
 117         '''Performs logout from the webservice'''
 118         self._download_json(self.logout_url, None, note='Logout',
 119                             errnote='Unable to log out', fatal=False)
 120
 121     def _real_extract(self, url):
 122         '''Extract the data necessary to download the video'''
 123         video_id = self._match_id(url)
 124
 125         metadata_url = self.search_url + \
 126             '/video_id/{video_id}/format/json'.format(video_id=video_id)
 127
 128         metadata = self._download_json(metadata_url, video_id,
 129                                        note='Getting video metadata')
 130         video = metadata['video'][0]
 131         title_info = video.get('title', {})
 132         title = title_info.get('title_long')
 133         description = title_info.get('summary_long')
 134
 135         movie = video['video_assets']['movie'][0]
 136         url = movie['url'].format(TOKEN=self.token)
 137
 138         formats = self._extract_m3u8_formats(url, video_id, 'mp4')
 139
 140         self._sort_formats(formats)
 141
 142         self._logout()
 143
 144         return {
 145             'id': video_id,
 146             'title': title,
 147             'description': description,
 148             'formats': formats,
 149         }