diff options
| author | Remita Amine <remitamine@gmail.com> | 2021-04-04 19:16:17 +0100 |
|---|---|---|
| committer | Remita Amine <remitamine@gmail.com> | 2021-04-04 19:16:17 +0100 |
| commit | 6beb1ac65b03415764c487fd139298f22e1e0313 (patch) | |
| tree | 012eb3e73fbaa0bc8454f2723145a4b2c504643d | |
| parent | 3ae9c0f410b1d4f63e8bada67dd62a8d2852be32 (diff) | |
[extractor/common] keep support for non standard JSON-LD VideoObject author values
| -rw-r--r-- | youtube_dl/extractor/common.py | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 8ef22779a..78ff5b6d0 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -70,7 +70,6 @@ from ..utils import ( str_or_none, str_to_int, strip_or_none, - try_get, unescapeHTML, unified_strdate, unified_timestamp, @@ -1276,6 +1275,7 @@ class InfoExtractor(object): def extract_video_object(e): assert e['@type'] == 'VideoObject' + author = e.get('author') info.update({ 'url': url_or_none(e.get('contentUrl')), 'title': unescapeHTML(e.get('name')), @@ -1283,7 +1283,11 @@ class InfoExtractor(object): 'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')), 'duration': parse_duration(e.get('duration')), 'timestamp': unified_timestamp(e.get('uploadDate')), - 'uploader': try_get(e, lambda x: x['author']['name'], compat_str), + # author can be an instance of 'Organization' or 'Person' types. + # both types can have 'name' property(inherited from 'Thing' type). [1] + # however some websites are using 'Text' type instead. + # 1. https://schema.org/VideoObject + 'uploader': author.get('name') if isinstance(author, dict) else author if isinstance(author, compat_str) else None, 'filesize': float_or_none(e.get('contentSize')), 'tbr': int_or_none(e.get('bitrate')), 'width': int_or_none(e.get('width')), |