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     compat_urllib_request,
  11 )
  12 from ..utils import (
  13     int_or_none,
  14     float_or_none,
  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     _TESTS = [
  23         {
  24             'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
  25             'md5': 'efd56753cda1bb64df52a3074f62e38a',
  26             'info_dict': {
  27                 'id': 'capitulo-10-especial-solidario-nochebuena',
  28                 'ext': 'mp4',
  29                 'title': 'Especial Solidario de Nochebuena',
  30                 'description': 'md5:e2d52ff12214fa937107d21064075bf1',
  31                 'duration': 5527.6,
  32                 'thumbnail': 're:^https?://.*\.jpg$',
  33             },
  34         },
  35         {
  36             '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',
  37             'only_matching': True,
  38         },
  39     ]
  40
  41     _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
  42     _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
  43     _TIMESTAMP_SHIFT = 30000
  44
  45     _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
  46     _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
  47     _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
  48     _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
  49
  50     _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
  51
  52     def _real_initialize(self):
  53         self._login()
  54
  55     def _login(self):
  56         (username, password) = self._get_login_info()
  57         if username is None:
  58             return
  59
  60         login_form = {
  61             'j_username': username,
  62             'j_password': password,
  63         }
  64
  65         request = compat_urllib_request.Request(
  66             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
  67         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  68         response = self._download_webpage(
  69             request, None, 'Logging in as %s' % username)
  70
  71         error = self._html_search_regex(
  72             r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
  73         if error:
  74             raise ExtractorError(
  75                 'Unable to login: %s' % error, expected=True)
  76
  77     def _real_extract(self, url):
  78         video_id = self._match_id(url)
  79
  80         webpage = self._download_webpage(url, video_id)
  81
  82         episode_id = self._search_regex(
  83             r'episode="([^"]+)"', webpage, 'episode id')
  84
  85         timestamp = int_or_none(self._download_webpage(
  86             self._TIME_API_URL,
  87             video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
  88         timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
  89         token = hmac.new(
  90             self._MAGIC.encode('ascii'),
  91             (episode_id + timestamp_shifted).encode('utf-8')
  92         ).hexdigest()
  93
  94         formats = []
  95         for fmt in ['windows', 'android_tablet']:
  96             request = compat_urllib_request.Request(
  97                 self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
  98             request.add_header('User-Agent', self._USER_AGENT)
  99
 100             fmt_json = self._download_json(
 101                 request, video_id, 'Downloading %s video JSON' % fmt)
 102
 103             result = fmt_json.get('resultDes')
 104             if result.lower() != 'ok':
 105                 raise ExtractorError(
 106                     '%s returned error: %s' % (self.IE_NAME, result), expected=True)
 107
 108             for format_id, video_url in fmt_json['resultObject'].items():
 109                 if format_id == 'token' or not video_url.startswith('http'):
 110                     continue
 111                 if video_url.endswith('/Manifest'):
 112                     if 'geodeswowsmpra3player' in video_url:
 113                         f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
 114                         f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
 115                         # this videos are protected by DRM, the f4m downloader doesn't support them
 116                         continue
 117                     else:
 118                         f4m_url = video_url[:-9] + '/manifest.f4m'
 119                     formats.extend(self._extract_f4m_formats(f4m_url, video_id))
 120                 else:
 121                     formats.append({
 122                         'url': video_url,
 123                         'format_id': 'android-%s' % format_id,
 124                         'preference': 1,
 125                     })
 126         self._sort_formats(formats)
 127
 128         player = self._download_json(
 129             self._PLAYER_URL_TEMPLATE % episode_id,
 130             episode_id)
 131
 132         path_data = player.get('pathData')
 133
 134         episode = self._download_xml(
 135             self._EPISODE_URL_TEMPLATE % path_data,
 136             video_id, 'Downloading episode XML')
 137
 138         duration = float_or_none(xpath_text(
 139             episode, './media/asset/info/technical/contentDuration', 'duration'))
 140
 141         art = episode.find('./media/asset/info/art')
 142         title = xpath_text(art, './name', 'title')
 143         description = xpath_text(art, './description', 'description')
 144         thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
 145
 146         subtitles = {}
 147         subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
 148         if subtitle_url:
 149             subtitles['es'] = [{
 150                 'ext': 'srt',
 151                 'url': subtitle_url,
 152             }]
 153
 154         return {
 155             'id': video_id,
 156             'title': title,
 157             'description': description,
 158             'thumbnail': thumbnail,
 159             'duration': duration,
 160             'formats': formats,
 161             'subtitles': subtitles,
 162         }