From 67c2dd909de3c5dada6efe8db2f59ed09e76d439 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 14 Aug 2020 16:05:55 -0700 Subject: entity updater: es['publisher_type'] not always set This is a small bugfix for a production issue. --- python/fatcat_tools/workers/changelog.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/fatcat_tools/workers/changelog.py b/python/fatcat_tools/workers/changelog.py index 65a8fcd8..b0dca6eb 100644 --- a/python/fatcat_tools/workers/changelog.py +++ b/python/fatcat_tools/workers/changelog.py @@ -212,7 +212,7 @@ class EntityUpdatesWorker(FatcatWorker): # big publishers *generally* have accurate OA metadata, use # preservation networks, and block our crawlers. So unless OA, or # explicitly on accept list, or not preserved, skip crawling - if es['publisher_type'] == 'big5' and es['is_preserved'] and not (es['is_oa'] or in_acceptlist): + if es.get('publisher_type') == 'big5' and es.get('is_preserved') and not (es['is_oa'] or in_acceptlist): return False # if ingest_type is pdf but release_type is almost certainly not a PDF, -- cgit v1.2.3