From 8782f83631365bffdd6a54fa436f5c477386fd1f Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 11 Aug 2020 19:49:08 -0700
Subject: additional loginwall patterns

---
 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 d910665..c45437d 100644
--- a/python/sandcrawler/ingest.py
+++ b/python/sandcrawler/ingest.py
@@ -105,6 +105,8 @@ class IngestFileWorker(SandcrawlerWorker):
         self.wall_blocklist = [
             # loginwall
             "://profile.thieme.de/HTML/sso/ejournals/login.htm",
+            "://login.bepress.com/"
+            "?SAMLRequest="
         ]
 
         # these are special-case web domains for which we want SPN2 to not run
-- 
cgit v1.2.3