depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-22 18:22:21 +00:00
Code Issues Releases Wiki Activity

[common] Avoid erasing extracted ld+json data with None values

Browse source
This commit is contained in:
dirkf 2022-05-04 19:25:41 +01:00
parent 2e8984e8c2
commit 48c366cd89
1 changed files with 10 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/common.py
View file

@ -1228,6 +1228,10 @@ class InfoExtractor(object):
if isinstance(json_ld, dict): if isinstance(json_ld, dict):
json_ld = [json_ld] json_ld = [json_ld]
def valued_dict(items):
"""Return dict from dict or iterable of pairs omitting None values"""
return dict((k, v) for k, v in (items.items() if isinstance(items, dict) else items) if v is not None)
INTERACTION_TYPE_MAP = { INTERACTION_TYPE_MAP = {
'CommentAction': 'comment', 'CommentAction': 'comment',
'AgreeAction': 'like', 'AgreeAction': 'like',
@ -1325,18 +1329,19 @@ class InfoExtractor(object):
'series': series_name, 'series': series_name,
}) })
elif item_type == 'Movie': elif item_type == 'Movie':
info.update({ # here and in the next, don't erase existing value with None
info.update(valued_dict({
'title': unescapeHTML(e.get('name')), 'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')), 'description': unescapeHTML(e.get('description')),
'duration': parse_duration(e.get('duration')), 'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('dateCreated')), 'timestamp': unified_timestamp(e.get('dateCreated')),
}) }))
elif item_type in ('Article', 'NewsArticle'): elif item_type in ('Article', 'NewsArticle'):
info.update({ info.update(valued_dict({
'timestamp': parse_iso8601(e.get('datePublished')), 'timestamp': parse_iso8601(e.get('datePublished')),
'title': unescapeHTML(e.get('headline')), 'title': unescapeHTML(e.get('headline')),
'description': unescapeHTML(e.get('articleBody')), 'description': unescapeHTML(e.get('articleBody')),
}) }))
elif item_type == 'VideoObject': elif item_type == 'VideoObject':
extract_video_object(e) extract_video_object(e)
if expected_type is None: if expected_type is None:
@ -1350,7 +1355,7 @@ class InfoExtractor(object):
continue continue
else: else:
break break
return dict((k, v) for k, v in info.items() if v is not None) return valued_dict(info)
@staticmethod @staticmethod
def _hidden_inputs(html): def _hidden_inputs(html):