[sonyliv] fix extraction(closes #25667)
authorRemita Amine <remitamine@gmail.com>
Thu, 24 Dec 2020 12:09:58 +0000 (13:09 +0100)
committerRemita Amine <remitamine@gmail.com>
Thu, 24 Dec 2020 12:10:20 +0000 (13:10 +0100)
youtube_dl/extractor/sonyliv.py

index 58a8c0d4ddb2f282241af2afad37e9d4b8403085..b460b343acc748ec9d655b1be4e5dad7a4a11926 100644 (file)
 # coding: utf-8
 from __future__ import unicode_literals
 
+import time
+import uuid
+
 from .common import InfoExtractor
-from ..utils import smuggle_url
+from ..compat import compat_HTTPError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
 
 
 class SonyLIVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?sonyliv\.com/details/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?sonyliv\.com/(?:s(?:how|port)s/[^/]+|movies|clip|trailer|music-videos)/[^/?#&]+-(?P<id>\d+)'
     _TESTS = [{
-        'url': "http://www.sonyliv.com/details/episodes/5024612095001/Ep.-1---Achaari-Cheese-Toast---Bachelor's-Delight",
+        'url': 'https://www.sonyliv.com/shows/bachelors-delight-1700000113/achaari-cheese-toast-1000022678?watch=true',
         'info_dict': {
-            'title': "Ep. 1 - Achaari Cheese Toast - Bachelor's Delight",
-            'id': 'ref:5024612095001',
+            'title': 'Bachelors Delight - Achaari Cheese Toast',
+            'id': '1000022678',
             'ext': 'mp4',
-            'upload_date': '20170923',
-            'description': 'md5:7f28509a148d5be9d0782b4d5106410d',
-            'uploader_id': '5182475815001',
-            'timestamp': 1506200547,
+            'upload_date': '20200411',
+            'description': 'md5:3957fa31d9309bf336ceb3f37ad5b7cb',
+            'timestamp': 1586632091,
+            'duration': 185,
+            'season_number': 1,
+            'episode': 'Achaari Cheese Toast',
+            'episode_number': 1,
+            'release_year': 2016,
         },
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['BrightcoveNew'],
     }, {
-        'url': 'http://www.sonyliv.com/details/full%20movie/4951168986001/Sei-Raat-(Bangla)',
+        'url': 'https://www.sonyliv.com/movies/tahalka-1000050121?watch=true',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.sonyliv.com/clip/jigarbaaz-1000098925',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.sonyliv.com/trailer/sandwiched-forever-1000100286?watch=true',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.sonyliv.com/sports/india-tour-of-australia-2020-21-1700000286/cricket-hls-day-3-1st-test-aus-vs-ind-19-dec-2020-1000100959?watch=true',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.sonyliv.com/music-videos/yeh-un-dinon-ki-baat-hai-1000018779',
         'only_matching': True,
     }]
+    _GEO_COUNTRIES = ['IN']
+    _TOKEN = None
 
-    # BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s'
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5182475815001/default_default/index.html?videoId=ref:%s'
+    def _call_api(self, version, path, video_id):
+        headers = {}
+        if self._TOKEN:
+            headers['security_token'] = self._TOKEN
+        try:
+            return self._download_json(
+                'https://apiv2.sonyliv.com/AGL/%s/A/ENG/WEB/%s' % (version, path),
+                video_id, headers=headers)['resultObj']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                message = self._parse_json(
+                    e.cause.read().decode(), video_id)['message']
+                if message == 'Geoblocked Country':
+                    self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+                raise ExtractorError(message)
+            raise
+
+    def _real_initialize(self):
+        self._TOKEN = self._call_api('1.4', 'ALL/GETTOKEN', None)
 
     def _real_extract(self, url):
-        brightcove_id = self._match_id(url)
-        return self.url_result(
-            smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {
-                'geo_countries': ['IN'],
-                'referrer': url,
-            }),
-            'BrightcoveNew', brightcove_id)
+        video_id = self._match_id(url)
+        content = self._call_api(
+            '1.5', 'IN/CONTENT/VIDEOURL/VOD/' + video_id, video_id)
+        if content.get('isEncrypted'):
+            raise ExtractorError('This video is DRM protected.', expected=True)
+        dash_url = content['videoURL']
+        headers = {
+            'x-playback-session-id': '%s-%d' % (uuid.uuid4().hex, time.time() * 1000)
+        }
+        formats = self._extract_mpd_formats(
+            dash_url, video_id, mpd_id='dash', headers=headers, fatal=False)
+        formats.extend(self._extract_m3u8_formats(
+            dash_url.replace('.mpd', '.m3u8').replace('/DASH/', '/HLS/'),
+            video_id, 'mp4', m3u8_id='hls', headers=headers, fatal=False))
+        for f in formats:
+            f.setdefault('http_headers', {}).update(headers)
+        self._sort_formats(formats)
+
+        metadata = self._call_api(
+            '1.6', 'IN/DETAIL/' + video_id, video_id)['containers'][0]['metadata']
+        title = metadata['title']
+        episode = metadata.get('episodeTitle')
+        if episode:
+            title += ' - ' + episode
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': content.get('posterURL'),
+            'description': metadata.get('longDescription') or metadata.get('shortDescription'),
+            'timestamp': int_or_none(metadata.get('creationDate'), 1000),
+            'duration': int_or_none(metadata.get('duration')),
+            'season_number': int_or_none(metadata.get('season')),
+            'episode': episode,
+            'episode_number': int_or_none(metadata.get('episodeNumber')),
+            'release_year': int_or_none(metadata.get('year')),
+        }