[extractor/common] Improve _json_ld for articles
This commit is contained in:
parent
a0ee342b50
commit
3931b84597
|
@ -1027,7 +1027,7 @@ class InfoExtractor(object):
|
||||||
part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
|
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'):
|
if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'):
|
||||||
info['series'] = unescapeHTML(part_of_series.get('name'))
|
info['series'] = unescapeHTML(part_of_series.get('name'))
|
||||||
elif item_type == 'Article':
|
elif item_type in ('Article', 'NewsArticle'):
|
||||||
info.update({
|
info.update({
|
||||||
'timestamp': parse_iso8601(e.get('datePublished')),
|
'timestamp': parse_iso8601(e.get('datePublished')),
|
||||||
'title': unescapeHTML(e.get('headline')),
|
'title': unescapeHTML(e.get('headline')),
|
||||||
|
|
Loading…
Reference in New Issue