[brightcove:legacy] skip None value for uploader_id

[youtube-dl] / youtube_dl / extractor / brightcove.py

diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index a5091238bcefc4e131d357d47cba3051903e0849..c718cf38509507ce6f314571dd59444ae4f3c647 100644 (file)
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -48,7 +48,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
                 'timestamp': 1368213670,
                 'upload_date': '20130510',
-                'uploader_id': 1589608506001,
+                'uploader_id': '1589608506001',
             }
         },
         {
@@ -62,7 +62,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'uploader': 'Oracle',
                 'timestamp': 1344975024,
                 'upload_date': '20120814',
-                'uploader_id': 1460825906,
+                'uploader_id': '1460825906',
             },
         },
         {
@@ -76,7 +76,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'uploader': 'Mashable',
                 'timestamp': 1382041798,
                 'upload_date': '20131017',
-                'uploader_id': 1130468786001,
+                'uploader_id': '1130468786001',
             },
         },
         {
@@ -104,7 +104,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
                 'timestamp': 1409122195,
                 'upload_date': '20140827',
-                'uploader_id': 710858724001,
+                'uploader_id': '710858724001',
             },
         },
         {
@@ -307,13 +307,14 @@ class BrightcoveLegacyIE(InfoExtractor):
                                     playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
 
     def _extract_video_info(self, video_info):
+        publisher_id = video_info.get('publisherId')
         info = {
             'id': compat_str(video_info['id']),
             'title': video_info['displayName'].strip(),
             'description': video_info.get('shortDescription'),
             'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
             'uploader': video_info.get('publisherName'),
-            'uploader_id': video_info.get('publisherId'),
+            'uploader_id': compat_str(publisher_id) if publisher_id else None,
             'duration': float_or_none(video_info.get('length'), 1000),
             'timestamp': int_or_none(video_info.get('creationDate'), 1000),
         }
@@ -515,7 +516,7 @@ class BrightcoveNewIE(InfoExtractor):
                 raise ExtractorError(json_data[0]['message'], expected=True)
             raise
 
-        title = json_data['name']
+        title = json_data['name'].strip()
 
         formats = []
         for source in json_data.get('sources', []):
@@ -579,20 +580,22 @@ class BrightcoveNewIE(InfoExtractor):
                 formats.append(f)
         self._sort_formats(formats)
 
-        description = json_data.get('description')
-        thumbnail = json_data.get('thumbnail')
-        timestamp = parse_iso8601(json_data.get('published_at'))
-        duration = float_or_none(json_data.get('duration'), 1000)
-        tags = json_data.get('tags', [])
+        subtitles = {}
+        for text_track in json_data.get('text_tracks', []):
+            if text_track.get('src'):
+                subtitles.setdefault(text_track.get('srclang'), []).append({
+                    'url': text_track['src'],
+                })
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
+            'description': json_data.get('description'),
+            'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
+            'duration': float_or_none(json_data.get('duration'), 1000),
+            'timestamp': parse_iso8601(json_data.get('published_at')),
             'uploader_id': account_id,
             'formats': formats,
-            'tags': tags,
+            'subtitles': subtitles,
+            'tags': json_data.get('tags', []),
         }