From 5af153683cdd9b883bc142a4bd7bb447612d494a Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 22 May 2019 16:01:37 -0700
Subject: more strict pubmed DOI handling

---
 python/fatcat_tools/importers/pubmed.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'python/fatcat_tools/importers')

diff --git a/python/fatcat_tools/importers/pubmed.py b/python/fatcat_tools/importers/pubmed.py
index b33bbf13..e5d413a7 100644
--- a/python/fatcat_tools/importers/pubmed.py
+++ b/python/fatcat_tools/importers/pubmed.py
@@ -380,7 +380,9 @@ class PubmedImporter(EntityImporter):
             doi = doi.string.lower()
             if doi.startswith('doi:'):
                 doi = doi[4:]
-            assert doi.startswith('10.')
+            if not (doi.startswith('10.') and '/' in doi and doi.split('/')[1]):
+                sys.stderr.write("BOGUS DOI: {}\n".format(doi))
+                doi = None
 
         pmcid = identifiers.find("ArticleId", IdType="pmc")
         if pmcid:
-- 
cgit v1.2.3