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
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urllib_parse,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13     float_or_none,
  14     sanitized_Request,
  15     xpath_text,
  16     ExtractorError,
  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': 're:^https?://.*\.jpg$',
  34             },
  35         },
  36         {
  37             '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',
  38             'only_matching': True,
  39         },
  40     ]
  41
  42     _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
  43     _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
  44     _TIMESTAMP_SHIFT = 30000
  45
  46     _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
  47     _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
  48     _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
  49     _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
  50
  51     _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
  52
  53     def _real_initialize(self):
  54         self._login()
  55
  56     def _login(self):
  57         (username, password) = self._get_login_info()
  58         if username is None:
  59             return
  60
  61         login_form = {
  62             'j_username': username,
  63             'j_password': password,
  64         }
  65
  66         request = sanitized_Request(
  67             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
  68         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  69         response = self._download_webpage(
  70             request, None, 'Logging in as %s' % username)
  71
  72         error = self._html_search_regex(
  73             r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
  74         if error:
  75             raise ExtractorError(
  76                 'Unable to login: %s' % error, expected=True)
  77
  78     def _real_extract(self, url):
  79         video_id = self._match_id(url)
  80
  81         webpage = self._download_webpage(url, video_id)
  82
  83         episode_id = self._search_regex(
  84             r'episode="([^"]+)"', webpage, 'episode id')
  85
  86         timestamp = int_or_none(self._download_webpage(
  87             self._TIME_API_URL,
  88             video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
  89         timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
  90         token = hmac.new(
  91             self._MAGIC.encode('ascii'),
  92             (episode_id + timestamp_shifted).encode('utf-8')
  93         ).hexdigest()
  94
  95         formats = []
  96         for fmt in ['windows', 'android_tablet']:
  97             request = sanitized_Request(
  98                 self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
  99             request.add_header('User-Agent', self._USER_AGENT)
 100
 101             fmt_json = self._download_json(
 102                 request, video_id, 'Downloading %s video JSON' % fmt)
 103
 104             result = fmt_json.get('resultDes')
 105             if result.lower() != 'ok':
 106                 raise ExtractorError(
 107                     '%s returned error: %s' % (self.IE_NAME, result), expected=True)
 108
 109             for format_id, video_url in fmt_json['resultObject'].items():
 110                 if format_id == 'token' or not video_url.startswith('http'):
 111                     continue
 112                 if video_url.endswith('/Manifest'):
 113                     if 'geodeswowsmpra3player' in video_url:
 114                         f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
 115                         f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
 116                         # this videos are protected by DRM, the f4m downloader doesn't support them
 117                         continue
 118                     else:
 119                         f4m_url = video_url[:-9] + '/manifest.f4m'
 120                     formats.extend(self._extract_f4m_formats(f4m_url, video_id))
 121                 else:
 122                     formats.append({
 123                         'url': video_url,
 124                         'format_id': 'android-%s' % format_id,
 125                         'preference': 1,
 126                     })
 127         self._sort_formats(formats)
 128
 129         player = self._download_json(
 130             self._PLAYER_URL_TEMPLATE % episode_id,
 131             episode_id)
 132
 133         path_data = player.get('pathData')
 134
 135         episode = self._download_xml(
 136             self._EPISODE_URL_TEMPLATE % path_data,
 137             video_id, 'Downloading episode XML')
 138
 139         duration = float_or_none(xpath_text(
 140             episode, './media/asset/info/technical/contentDuration', 'duration'))
 141
 142         art = episode.find('./media/asset/info/art')
 143         title = xpath_text(art, './name', 'title')
 144         description = xpath_text(art, './description', 'description')
 145         thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
 146
 147         subtitles = {}
 148         subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
 149         if subtitle_url:
 150             subtitles['es'] = [{
 151                 'ext': 'srt',
 152                 'url': subtitle_url,
 153             }]
 154
 155         return {
 156             'id': video_id,
 157             'title': title,
 158             'description': description,
 159             'thumbnail': thumbnail,
 160             'duration': duration,
 161             'formats': formats,
 162             'subtitles': subtitles,
 163         }