[extractor/common] Improve _json_ld for articles

This commit is contained in:
Sergey M․ 2018-01-27 23:23:36 +07:00
parent a0ee342b50
commit 3931b84597
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -1027,7 +1027,7 @@ def extract_video_object(e):
part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'):
info['series'] = unescapeHTML(part_of_series.get('name'))
elif item_type == 'Article':
elif item_type in ('Article', 'NewsArticle'):
info.update({
'timestamp': parse_iso8601(e.get('datePublished')),
'title': unescapeHTML(e.get('headline')),