From afa7aa6006a0de41de6cb08b61aaff61109e2792 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Fri, 27 Mar 2020 16:37:55 -0700
Subject: ingest: block another large domain (and DOI prefix)

---
 python/sandcrawler/ingest.py | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'python')

diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py
index 4159e26..5cb3ef8 100644
--- a/python/sandcrawler/ingest.py
+++ b/python/sandcrawler/ingest.py
@@ -87,6 +87,8 @@ class IngestFileWorker(SandcrawlerWorker):
             "www.gbif.org/",
             "doi.pangaea.de/",
             "www.plate-archive.org/",
+            "://doi.org/10.25642/ipk/gbis/",
+            "://apex.ipk-gatersleben.de/",
 
             # Historical non-paper content:
             "dhz.uni-passau.de/",   # newspapers
-- 
cgit v1.2.3