From b9237268c61777a28f5d8e512b326337715aab44 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 28 Jan 2020 12:52:48 -0800
Subject: block springer page-one domain

---
 python/sandcrawler/ingest.py | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'python')

diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py
index 148abdb..9f07fc3 100644
--- a/python/sandcrawler/ingest.py
+++ b/python/sandcrawler/ingest.py
@@ -78,6 +78,9 @@ class IngestFileWorker(SandcrawlerWorker):
             "://jist.net.in",
             "://croisements-revue.org",
 
+            # all stubs/previews, not full papers
+            "://page-one.live.cf.public.springer.com",
+
         ]
 
     def check_existing_ingest(self, base_url):
-- 
cgit v1.2.3