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 compat_str
  10 from ..utils import (
  11     ExtractorError,
  12     float_or_none,
  13     int_or_none,
  14     sanitized_Request,
  15     urlencode_postdata,
  16     xpath_text,
  17 )
  18
  19
  20 class AtresPlayerIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
  22     _NETRC_MACHINE = 'atresplayer'
  23     _TESTS = [
  24         {
  25             'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
  26             'md5': 'efd56753cda1bb64df52a3074f62e38a',
  27             'info_dict': {
  28                 'id': 'capitulo-10-especial-solidario-nochebuena',
  29                 'ext': 'mp4',
  30                 'title': 'Especial Solidario de Nochebuena',
  31                 'description': 'md5:e2d52ff12214fa937107d21064075bf1',
  32                 'duration': 5527.6,
  33                 'thumbnail': r're:^https?://.*\.jpg$',
  34             },
  35             'skip': 'This video is only available for registered users'
  36         },
  37         {
  38             'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
  39             'md5': '0d0e918533bbd4b263f2de4d197d4aac',
  40             'info_dict': {
  41                 'id': 'capitulo-112-david-bustamante',
  42                 'ext': 'flv',
  43                 'title': 'David Bustamante',
  44                 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
  45                 'duration': 1439.0,
  46                 'thumbnail': r're:^https?://.*\.jpg$',
  47             },
  48         },
  49         {
  50             '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',
  51             'only_matching': True,
  52         },
  53     ]
  54
  55     _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
  56     _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
  57     _TIMESTAMP_SHIFT = 30000
  58
  59     _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
  60     _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
  61     _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
  62     _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
  63
  64     _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
  65
  66     _ERRORS = {
  67         'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
  68         'DELETED': 'This video has expired and is no longer available for online streaming.',
  69         'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
  70         # 'PREMIUM': 'PREMIUM',
  71     }
  72
  73     def _real_initialize(self):
  74         self._login()
  75
  76     def _login(self):
  77         (username, password) = self._get_login_info()
  78         if username is None:
  79             return
  80
  81         login_form = {
  82             'j_username': username,
  83             'j_password': password,
  84         }
  85
  86         request = sanitized_Request(
  87             self._LOGIN_URL, urlencode_postdata(login_form))
  88         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  89         response = self._download_webpage(
  90             request, None, 'Logging in as %s' % username)
  91
  92         error = self._html_search_regex(
  93             r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>',
  94             response, 'error', default=None)
  95         if error:
  96             raise ExtractorError(
  97                 'Unable to login: %s' % error, expected=True)
  98
  99     def _real_extract(self, url):
 100         video_id = self._match_id(url)
 101
 102         webpage = self._download_webpage(url, video_id)
 103
 104         episode_id = self._search_regex(
 105             r'episode="([^"]+)"', webpage, 'episode id')
 106
 107         request = sanitized_Request(
 108             self._PLAYER_URL_TEMPLATE % episode_id,
 109             headers={'User-Agent': self._USER_AGENT})
 110         player = self._download_json(request, episode_id, 'Downloading player JSON')
 111
 112         episode_type = player.get('typeOfEpisode')
 113         error_message = self._ERRORS.get(episode_type)
 114         if error_message:
 115             raise ExtractorError(
 116                 '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
 117
 118         formats = []
 119         video_url = player.get('urlVideo')
 120         if video_url:
 121             format_info = {
 122                 'url': video_url,
 123                 'format_id': 'http',
 124             }
 125             mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
 126             if mobj:
 127                 format_info.update({
 128                     'width': int_or_none(mobj.group('width')),
 129                     'height': int_or_none(mobj.group('height')),
 130                     'tbr': int_or_none(mobj.group('bitrate')),
 131                 })
 132             formats.append(format_info)
 133
 134         timestamp = int_or_none(self._download_webpage(
 135             self._TIME_API_URL,
 136             video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
 137         timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
 138         token = hmac.new(
 139             self._MAGIC.encode('ascii'),
 140             (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
 141         ).hexdigest()
 142
 143         request = sanitized_Request(
 144             self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
 145             headers={'User-Agent': self._USER_AGENT})
 146
 147         fmt_json = self._download_json(
 148             request, video_id, 'Downloading windows video JSON')
 149
 150         result = fmt_json.get('resultDes')
 151         if result.lower() != 'ok':
 152             raise ExtractorError(
 153                 '%s returned error: %s' % (self.IE_NAME, result), expected=True)
 154
 155         for format_id, video_url in fmt_json['resultObject'].items():
 156             if format_id == 'token' or not video_url.startswith('http'):
 157                 continue
 158             if 'geodeswowsmpra3player' in video_url:
 159                 # f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
 160                 # f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
 161                 # this videos are protected by DRM, the f4m downloader doesn't support them
 162                 continue
 163             video_url_hd = video_url.replace('free_es', 'es')
 164             formats.extend(self._extract_f4m_formats(
 165                 video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds',
 166                 fatal=False))
 167             formats.extend(self._extract_mpd_formats(
 168                 video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash',
 169                 fatal=False))
 170         self._sort_formats(formats)
 171
 172         path_data = player.get('pathData')
 173
 174         episode = self._download_xml(
 175             self._EPISODE_URL_TEMPLATE % path_data, video_id,
 176             'Downloading episode XML')
 177
 178         duration = float_or_none(xpath_text(
 179             episode, './media/asset/info/technical/contentDuration', 'duration'))
 180
 181         art = episode.find('./media/asset/info/art')
 182         title = xpath_text(art, './name', 'title')
 183         description = xpath_text(art, './description', 'description')
 184         thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
 185
 186         subtitles = {}
 187         subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
 188         if subtitle_url:
 189             subtitles['es'] = [{
 190                 'ext': 'srt',
 191                 'url': subtitle_url,
 192             }]
 193
 194         return {
 195             'id': video_id,
 196             'title': title,
 197             'description': description,
 198             'thumbnail': thumbnail,
 199             'duration': duration,
 200             'formats': formats,
 201             'subtitles': subtitles,
 202         }