From a0697e1bb582cd157206c0ca437bcada3b4f3158 Mon Sep 17 00:00:00 2001 From: Matt Wells <mattdwells@hotmail.com> Date: Wed, 26 Feb 2014 10:26:09 -0800 Subject: [PATCH] do not allow custom crawls to spider the web any more. --- Collectiondb.cpp | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/Collectiondb.cpp b/Collectiondb.cpp index d19d9800..3c1b912a 100644 --- a/Collectiondb.cpp +++ b/Collectiondb.cpp @@ -2137,11 +2137,13 @@ bool CollectionRec::rebuildUrlFilters ( ) { i++; // 2nd default filter - if ( m_restrictDomain ) { - m_regExs[i].set("!isonsamedomain && !ismanualadd"); - m_spiderPriorities [i] = SPIDER_PRIORITY_FILTERED; - i++; - } + // always turn this on for now. they need to add domains they want + // to crawl as seeds so they do not spider the web. + //if ( m_restrictDomain ) { + m_regExs[i].set("!isonsamedomain && !ismanualadd"); + m_spiderPriorities [i] = SPIDER_PRIORITY_FILTERED; + i++; + //} m_regExs[i].set("errorcount>=1 && !hastmperror"); m_spiderPriorities [i] = 15;