From fd2d3f95fcdb10084d8c9e52f3696c3095e9dde7 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 3 Nov 2020 15:44:47 -0800
Subject: ingest: add more IA domains

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

(limited to 'python/sandcrawler/ingest.py')

diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py
index 6d8b162..35b37fc 100644
--- a/python/sandcrawler/ingest.py
+++ b/python/sandcrawler/ingest.py
@@ -76,8 +76,10 @@ class IngestFileWorker(SandcrawlerWorker):
 
             # temporary, until we implement specific fetch and 'petabox' output
             "://archive.org/",
+            "://www.archive.org/",
             "://web.archive.org/web/",
             "://openlibrary.org/",
+            "://www.openlibrary.org/",
             "://fatcat.wiki/",
 
             # Domain squats
-- 
cgit v1.2.3