Update to ytdl-2021.01.03

[yt-dlp.git] / youtube_dlc / extractor / brightcove.py

diff --git a/youtube_dlc/extractor/brightcove.py b/youtube_dlc/extractor/brightcove.py
index c6ca939ddd4cd323cfcea456502dc57575999253..6022076acaf24727fe436b7fb50a16f1a9029259 100644 (file)
--- a/youtube_dlc/extractor/brightcove.py
+++ b/youtube_dlc/extractor/brightcove.py
@@ -28,6 +28,7 @@
     parse_iso8601,
     smuggle_url,
     str_or_none,
+    try_get,
     unescapeHTML,
     unsmuggle_url,
     UnsupportedError,
@@ -470,18 +471,18 @@ def _extract_urls(ie, webpage):
     def _parse_brightcove_metadata(self, json_data, video_id, headers={}):
         title = json_data['name'].strip()
 
+        num_drm_sources = 0
         formats = []
-        sources_num = len(json_data.get('sources'))
-        key_systems_present = 0
-        for source in json_data.get('sources', []):
+        sources = json_data.get('sources') or []
+        for source in sources:
             container = source.get('container')
             ext = mimetype2ext(source.get('type'))
             src = source.get('src')
-            # https://apis.support.brightcove.com/playback/references/playback-api-video-fields-reference.html
-            if source.get('key_systems'):
-                key_systems_present += 1
+            # https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
+            if container == 'WVM' or source.get('key_systems'):
+                num_drm_sources += 1
                 continue
-            elif ext == 'ism' or container == 'WVM':
+            elif ext == 'ism':
                 continue
             elif ext == 'm3u8' or container == 'M2TS':
                 if not src:
@@ -539,23 +540,14 @@ def build_format_id(kind):
                     })
                 formats.append(f)
 
-        if sources_num == key_systems_present:
-            raise ExtractorError('This video is DRM protected', expected=True)
-
         if not formats:
-            # for sonyliv.com DRM protected videos
-            s3_source_url = json_data.get('custom_fields', {}).get('s3sourceurl')
-            if s3_source_url:
-                formats.append({
-                    'url': s3_source_url,
-                    'format_id': 'source',
-                })
-
-        errors = json_data.get('errors')
-        if not formats and errors:
-            error = errors[0]
-            raise ExtractorError(
-                error.get('message') or error.get('error_subcode') or error['error_code'], expected=True)
+            errors = json_data.get('errors')
+            if errors:
+                error = errors[0]
+                raise ExtractorError(
+                    error.get('message') or error.get('error_subcode') or error['error_code'], expected=True)
+            if sources and num_drm_sources == len(sources):
+                raise ExtractorError('This video is DRM protected.', expected=True)
 
         self._sort_formats(formats)
 
@@ -609,24 +601,27 @@ def _real_extract(self, url):
         store_pk = lambda x: self._downloader.cache.store('brightcove', policy_key_id, x)
 
         def extract_policy_key():
-            webpage = self._download_webpage(
-                'http://players.brightcove.net/%s/%s_%s/index.min.js'
-                % (account_id, player_id, embed), video_id)
-
-            policy_key = None
+            base_url = 'http://players.brightcove.net/%s/%s_%s/' % (account_id, player_id, embed)
+            config = self._download_json(
+                base_url + 'config.json', video_id, fatal=False) or {}
+            policy_key = try_get(
+                config, lambda x: x['video_cloud']['policy_key'])
+            if not policy_key:
+                webpage = self._download_webpage(
+                    base_url + 'index.min.js', video_id)
 
-            catalog = self._search_regex(
-                r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
-            if catalog:
-                catalog = self._parse_json(
-                    js_to_json(catalog), video_id, fatal=False)
+                catalog = self._search_regex(
+                    r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
                 if catalog:
-                    policy_key = catalog.get('policyKey')
-
-            if not policy_key:
-                policy_key = self._search_regex(
-                    r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
-                    webpage, 'policy key', group='pk')
+                    catalog = self._parse_json(
+                        js_to_json(catalog), video_id, fatal=False)
+                    if catalog:
+                        policy_key = catalog.get('policyKey')
+
+                if not policy_key:
+                    policy_key = self._search_regex(
+                        r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
+                        webpage, 'policy key', group='pk')
 
             store_pk(policy_key)
             return policy_key