Revision: 3247 http://archive-access.svn.sourceforge.net/archive-access/?rev=3247&view=rev Author: bradtofel Date: 2010-09-03 23:19:28 +0000 (Fri, 03 Sep 2010) Log Message: ----------- FEATURE: explicitly allowing download of /robots.txt paths, without consulting the robots.txt file. Modified Paths: -------------- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java =================================================================== --- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java 2010-09-03 22:32:51 UTC (rev 3246) +++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/accesscontrol/robotstxt/RobotExclusionFilter.java 2010-09-03 23:19:28 UTC (rev 3247) @@ -236,7 +236,9 @@ URL url; try { url = new URL(ArchiveUtils.addImpliedHttpIfNecessary(resultURL)); - if(!rules.blocksPathForUA(url.getPath(), userAgent)) { + String path = url.getPath(); + if(path.equals(ROBOT_SUFFIX) || + !rules.blocksPathForUA(path, userAgent)) { if(!notifiedPassed) { if(filterGroup != null) { filterGroup.setPassedRobots(); This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site. |