Skip to content
This repository has been archived by the owner on Mar 1, 2023. It is now read-only.

Commit

Permalink
Fixing papers with no author
Browse files Browse the repository at this point in the history
  • Loading branch information
rabdill committed Jul 1, 2019
1 parent 086f04c commit 7fd60cc
Showing 1 changed file with 1 addition and 2 deletions.
3 changes: 1 addition & 2 deletions spider/spider.py
Original file line number Diff line number Diff line change
Expand Up @@ -1005,6 +1005,7 @@ def full_run(spider):
if config.crawl["fetch_missing_fields"] is not False:
spider.get_urls()
spider.get_posted_dates()
spider.refresh_article_stats(get_authors=True) # Fix authorless papers
if config.crawl["fetch_new"] is not False:
spider.find_record_new_articles()
else:
Expand All @@ -1031,8 +1032,6 @@ def full_run(spider):
if config.crawl["refresh_stats"] is not False:
# Refresh the articles without a collection:
spider.refresh_article_stats()
# Grab authors for any articles that don't currently have any:
spider.refresh_article_stats(get_authors=True)

if config.crawl["fetch_crossref"] is not False:
spider.pull_todays_crossref_data()
Expand Down

0 comments on commit 7fd60cc

Please sign in to comment.