*) Undoing robots parser policy changes from svn rev. 1421

- crawling is not allowed if server returned a 403 statuscode (according to rfc)

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@1864 6c8d7289-2bf4-0310-a012-ef5d649a1542
pull/1/head
theli 19 years ago
parent 0ec28b8f8e
commit 915812f597

@ -348,7 +348,7 @@ public final class robotsParser{
"\nRedirecting request to: " + redirectionUrl); "\nRedirecting request to: " + redirectionUrl);
return downloadRobotsTxt(redirectionUrl,redirectionCount,entry); return downloadRobotsTxt(redirectionUrl,redirectionCount,entry);
} else if (res.status.startsWith("401")/* || res.status.startsWith("403") */) { } else if (res.status.startsWith("401") || res.status.startsWith("403")) {
accessCompletelyRestricted = true; accessCompletelyRestricted = true;
serverLog.logFinest("ROBOTS","Access to Robots.txt not allowed on URL '" + robotsURL + "'."); serverLog.logFinest("ROBOTS","Access to Robots.txt not allowed on URL '" + robotsURL + "'.");
} else { } else {

Loading…
Cancel
Save