[atresplayer] fix extraction(closes #16277)(closes #16716)

youtube_dl/extractor/atresplayer.py

@@ -1,202 +1,117 @@
 from __future__ import unicode_literals
 
-import time
-import hmac
-import hashlib
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import compat_HTTPError
 from ..utils import (
     ExtractorError,
-    float_or_none,
     int_or_none,
-    sanitized_Request,
     urlencode_postdata,
-    xpath_text,
 )
 
 
 class AtresPlayerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
+    _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P<display_id>.+?)_(?P<id>[0-9a-f]{24})'
     _NETRC_MACHINE = 'atresplayer'
     _TESTS = [
         {
-            'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
+            'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/',
-            'md5': 'efd56753cda1bb64df52a3074f62e38a',
             'info_dict': {
-                'id': 'capitulo-10-especial-solidario-nochebuena',
+                'id': '5d4aa2c57ed1a88fc715a615',
                 'ext': 'mp4',
-                'title': 'Especial Solidario de Nochebuena',
+                'title': 'Capítulo 7: Asuntos pendientes',
-                'description': 'md5:e2d52ff12214fa937107d21064075bf1',
+                'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc',
-                'duration': 5527.6,
+                'duration': 3413,
-                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'format': 'bestvideo',
             },
             'skip': 'This video is only available for registered users'
         },
         {
-            'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
+            'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/',
-            'md5': '6e52cbb513c405e403dbacb7aacf8747',
+            'only_matching': True,
-            'info_dict': {
-                'id': 'capitulo-112-david-bustamante',
-                'ext': 'flv',
-                'title': 'David Bustamante',
-                'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
-                'duration': 1439.0,
-                'thumbnail': r're:^https?://.*\.jpg$',
-            },
         },
         {
-            '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',
+            'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/',
             'only_matching': True,
         },
     ]
-
+    _API_BASE = 'https://api.atresplayer.com/'
-    _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
-    _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
-    _TIMESTAMP_SHIFT = 30000
-
-    _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
-    _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
-    _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
-    _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
-
-    _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
-
-    _ERRORS = {
-        'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
-        'DELETED': 'This video has expired and is no longer available for online streaming.',
-        'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
-        # 'PREMIUM': 'PREMIUM',
-    }
 
     def _real_initialize(self):
         self._login()
 
+    def _handle_error(self, e, code):
+        if isinstance(e.cause, compat_HTTPError) and e.cause.code == code:
+            error = self._parse_json(e.cause.read(), None)
+            if error.get('error') == 'required_registered':
+                self.raise_login_required()
+            raise ExtractorError(error['error_description'], expected=True)
+        raise
+
     def _login(self):
         username, password = self._get_login_info()
         if username is None:
             return
 
-        login_form = {
+        self._request_webpage(
-            'j_username': username,
+            self._API_BASE + 'login', None, 'Downloading login page')
-            'j_password': password,
-        }
 
-        request = sanitized_Request(
+        try:
-            self._LOGIN_URL, urlencode_postdata(login_form))
+            target_url = self._download_json(
-        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+                'https://account.atresmedia.com/api/login', None,
-        response = self._download_webpage(
+                'Logging in', headers={
-            request, None, 'Logging in')
+                    'Content-Type': 'application/x-www-form-urlencoded'
+                }, data=urlencode_postdata({
+                    'username': username,
+                    'password': password,
+                }))['targetUrl']
+        except ExtractorError as e:
+            self._handle_error(e, 400)
 
-        error = self._html_search_regex(
+        self._request_webpage(target_url, None, 'Following Target URL')
-            r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>',
-            response, 'error', default=None)
-        if error:
-            raise ExtractorError(
-                'Unable to login: %s' % error, expected=True)
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        display_id, video_id = re.match(self._VALID_URL, url).groups()
 
-        webpage = self._download_webpage(url, video_id)
+        try:
+            episode = self._download_json(
+                self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
+        except ExtractorError as e:
+            self._handle_error(e, 403)
 
-        episode_id = self._search_regex(
+        title = episode['titulo']
-            r'episode="([^"]+)"', webpage, 'episode id')
-
-        request = sanitized_Request(
-            self._PLAYER_URL_TEMPLATE % episode_id,
-            headers={'User-Agent': self._USER_AGENT})
-        player = self._download_json(request, episode_id, 'Downloading player JSON')
-
-        episode_type = player.get('typeOfEpisode')
-        error_message = self._ERRORS.get(episode_type)
-        if error_message:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
 
         formats = []
-        video_url = player.get('urlVideo')
+        for source in episode.get('sources', []):
-        if video_url:
+            src = source.get('src')
-            format_info = {
+            if not src:
-                'url': video_url,
-                'format_id': 'http',
-            }
-            mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
-            if mobj:
-                format_info.update({
-                    'width': int_or_none(mobj.group('width')),
-                    'height': int_or_none(mobj.group('height')),
-                    'tbr': int_or_none(mobj.group('bitrate')),
-                })
-            formats.append(format_info)
-
-        timestamp = int_or_none(self._download_webpage(
-            self._TIME_API_URL,
-            video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
-        timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
-        token = hmac.new(
-            self._MAGIC.encode('ascii'),
-            (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
-        ).hexdigest()
-
-        request = sanitized_Request(
-            self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
-            headers={'User-Agent': self._USER_AGENT})
-
-        fmt_json = self._download_json(
-            request, video_id, 'Downloading windows video JSON')
-
-        result = fmt_json.get('resultDes')
-        if result.lower() != 'ok':
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, result), expected=True)
-
-        for format_id, video_url in fmt_json['resultObject'].items():
-            if format_id == 'token' or not video_url.startswith('http'):
                 continue
-            if 'geodeswowsmpra3player' in video_url:
+            src_type = source.get('type')
-                # f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
+            if src_type == 'application/vnd.apple.mpegurl':
-                # f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
+                formats.extend(self._extract_m3u8_formats(
-                # this videos are protected by DRM, the f4m downloader doesn't support them
+                    src, video_id, 'mp4', 'm3u8_native',
-                continue
+                    m3u8_id='hls', fatal=False))
-            video_url_hd = video_url.replace('free_es', 'es')
+            elif src_type == 'application/dash+xml':
-            formats.extend(self._extract_f4m_formats(
+                formats.extend(self._extract_mpd_formats(
-                video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds',
+                    src, video_id, mpd_id='dash', fatal=False))
-                fatal=False))
-            formats.extend(self._extract_mpd_formats(
-                video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash',
-                fatal=False))
         self._sort_formats(formats)
 
-        path_data = player.get('pathData')
+        heartbeat = episode.get('heartbeat') or {}
-
+        omniture = episode.get('omniture') or {}
-        episode = self._download_xml(
+        get_meta = lambda x: heartbeat.get(x) or omniture.get(x)
-            self._EPISODE_URL_TEMPLATE % path_data, video_id,
-            'Downloading episode XML')
-
-        duration = float_or_none(xpath_text(
-            episode, './media/asset/info/technical/contentDuration', 'duration'))
-
-        art = episode.find('./media/asset/info/art')
-        title = xpath_text(art, './name', 'title')
-        description = xpath_text(art, './description', 'description')
-        thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
-
-        subtitles = {}
-        subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
-        if subtitle_url:
-            subtitles['es'] = [{
-                'ext': 'srt',
-                'url': subtitle_url,
-            }]
 
         return {
+            'display_id': display_id,
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': episode.get('descripcion'),
-            'thumbnail': thumbnail,
+            'thumbnail': episode.get('imgPoster'),
-            'duration': duration,
+            'duration': int_or_none(episode.get('duration')),
             'formats': formats,
-            'subtitles': subtitles,
+            'channel': get_meta('channel'),
+            'season': get_meta('season'),
+            'episode_number': int_or_none(get_meta('episodeNumber')),
         }