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

   1 from __future__ import unicode_literals
   2
   3 import time
   4 import hmac
   5 import hashlib
   6 import re
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_str,
  11     compat_urllib_parse,
  12 )
  13 from ..utils import (
  14     int_or_none,
  15     float_or_none,
  16     sanitized_Request,
  17     xpath_text,
  18     ExtractorError,
  19 )
  20
  21
  22 class AtresPlayerIE(InfoExtractor):
  23     _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
  24     _NETRC_MACHINE = 'atresplayer'
  25     _TESTS = [
  26         {
  27             'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
  28             'md5': 'efd56753cda1bb64df52a3074f62e38a',
  29             'info_dict': {
  30                 'id': 'capitulo-10-especial-solidario-nochebuena',
  31                 'ext': 'mp4',
  32                 'title': 'Especial Solidario de Nochebuena',
  33                 'description': 'md5:e2d52ff12214fa937107d21064075bf1',
  34                 'duration': 5527.6,
  35                 'thumbnail': 're:^https?://.*\.jpg$',
  36             },
  37             'skip': 'This video is only available for registered users'
  38         },
  39         {
  40             'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
  41             'md5': '0d0e918533bbd4b263f2de4d197d4aac',
  42             'info_dict': {
  43                 'id': 'capitulo-112-david-bustamante',
  44                 'ext': 'flv',
  45                 'title': 'David Bustamante',
  46                 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
  47                 'duration': 1439.0,
  48                 'thumbnail': 're:^https?://.*\.jpg$',
  49             },
  50         },
  51         {
  52             'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
  53             'only_matching': True,
  54         },
  55     ]
  56
  57     _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
  58     _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
  59     _TIMESTAMP_SHIFT = 30000
  60
  61     _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
  62     _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
  63     _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
  64     _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
  65
  66     _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
  67
  68     _ERRORS = {
  69         'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
  70         'DELETED': 'This video has expired and is no longer available for online streaming.',
  71         'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
  72         # 'PREMIUM': 'PREMIUM',
  73     }
  74
  75     def _real_initialize(self):
  76         self._login()
  77
  78     def _login(self):
  79         (username, password) = self._get_login_info()
  80         if username is None:
  81             return
  82
  83         login_form = {
  84             'j_username': username,
  85             'j_password': password,
  86         }
  87
  88         request = sanitized_Request(
  89             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
  90         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  91         response = self._download_webpage(
  92             request, None, 'Logging in as %s' % username)
  93
  94         error = self._html_search_regex(
  95             r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
  96         if error:
  97             raise ExtractorError(
  98                 'Unable to login: %s' % error, expected=True)
  99
 100     def _real_extract(self, url):
 101         video_id = self._match_id(url)
 102
 103         webpage = self._download_webpage(url, video_id)
 104
 105         episode_id = self._search_regex(
 106             r'episode="([^"]+)"', webpage, 'episode id')
 107
 108         request = sanitized_Request(
 109             self._PLAYER_URL_TEMPLATE % episode_id,
 110             headers={'User-Agent': self._USER_AGENT})
 111         player = self._download_json(request, episode_id, 'Downloading player JSON')
 112
 113         episode_type = player.get('typeOfEpisode')
 114         error_message = self._ERRORS.get(episode_type)
 115         if error_message:
 116             raise ExtractorError(
 117                 '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
 118
 119         formats = []
 120         video_url = player.get('urlVideo')
 121         if video_url:
 122             format_info = {
 123                 'url': video_url,
 124                 'format_id': 'http',
 125             }
 126             mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
 127             if mobj:
 128                 format_info.update({
 129                     'width': int_or_none(mobj.group('width')),
 130                     'height': int_or_none(mobj.group('height')),
 131                     'tbr': int_or_none(mobj.group('bitrate')),
 132                 })
 133             formats.append(format_info)
 134
 135         timestamp = int_or_none(self._download_webpage(
 136             self._TIME_API_URL,
 137             video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
 138         timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
 139         token = hmac.new(
 140             self._MAGIC.encode('ascii'),
 141             (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
 142         ).hexdigest()
 143
 144         request = sanitized_Request(
 145             self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
 146             headers={'User-Agent': self._USER_AGENT})
 147
 148         fmt_json = self._download_json(
 149             request, video_id, 'Downloading windows video JSON')
 150
 151         result = fmt_json.get('resultDes')
 152         if result.lower() != 'ok':
 153             raise ExtractorError(
 154                 '%s returned error: %s' % (self.IE_NAME, result), expected=True)
 155
 156         for format_id, video_url in fmt_json['resultObject'].items():
 157             if format_id == 'token' or not video_url.startswith('http'):
 158                 continue
 159             if 'geodeswowsmpra3player' in video_url:
 160                 f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
 161                 f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
 162                 # this videos are protected by DRM, the f4m downloader doesn't support them
 163                 continue
 164             else:
 165                 f4m_url = video_url[:-9] + '/manifest.f4m'
 166             formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
 167         self._sort_formats(formats)
 168
 169         path_data = player.get('pathData')
 170
 171         episode = self._download_xml(
 172             self._EPISODE_URL_TEMPLATE % path_data, video_id,
 173             'Downloading episode XML')
 174
 175         duration = float_or_none(xpath_text(
 176             episode, './media/asset/info/technical/contentDuration', 'duration'))
 177
 178         art = episode.find('./media/asset/info/art')
 179         title = xpath_text(art, './name', 'title')
 180         description = xpath_text(art, './description', 'description')
 181         thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
 182
 183         subtitles = {}
 184         subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
 185         if subtitle_url:
 186             subtitles['es'] = [{
 187                 'ext': 'srt',
 188                 'url': subtitle_url,
 189             }]
 190
 191         return {
 192             'id': video_id,
 193             'title': title,
 194             'description': description,
 195             'thumbnail': thumbnail,
 196             'duration': duration,
 197             'formats': formats,
 198             'subtitles': subtitles,
 199         }