boxtec
/
yacy_search_server
mirror of https://github.com/yacy/yacy_search_server
4
1
Fork 0
Code Issues Projects Releases Wiki Activity

*) More graceful logging output in crawler

Browse Source 
See: http://www.yacy-forum.de/viewtopic.php?t=894

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@511 6c8d7289-2bf4-0310-a012-ef5d649a1542
pull/1/head
theli 20 years ago
parent 248c24b60a
commit 89c9faa89e
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File

13
source/de/anomic/plasma/plasmaCrawlWorker.java
Unescape View File

@ -403,20 +403,25 @@ public final class plasmaCrawlWorker extends Thread {
String errorMsg = e.getMessage();
if (errorMsg != null) {
if (e instanceof java.net.BindException) {
log.logWarning("BindException detected while trying to download content from '" + url.toString() +
log.logWarning("CRAWLER BindException detected while trying to download content from '" + url.toString() +
"'. Retrying request.");
retryCrawling = true;
} else if (errorMsg.indexOf("Corrupt GZIP trailer") >= 0) {
log.logWarning("Problems detected while receiving gzip encoded content from '" + url.toString() +
log.logWarning("CRAWLER Problems detected while receiving gzip encoded content from '" + url.toString() +
"'. Retrying request without using gzip content encoding.");
retryCrawling = true;
} else if (errorMsg.indexOf("Socket time-out: Read timed out") >= 0) {
log.logWarning("Read timeout while receiving content from '" + url.toString() +
log.logWarning("CRAWLER Read timeout while receiving content from '" + url.toString() +
"'. Retrying request.");
retryCrawling = true;
} else if (errorMsg.indexOf("Connection timed out") >= 0) {
log.logWarning("CRAWLER Connection timeout while receiving content from '" + url.toString() +
"'. Retrying request.");
retryCrawling = true;
} else if (errorMsg.indexOf("Connection refused") >= 0) {
log.logError("CRAWLER LOADER ERROR2 with URL=" + url.toString() + ": Connection refused");
log.logError("CRAWLER LOADER ERROR2 with URL=" + url.toString() + ": Connection refused");
}
if (retryCrawling) {
load(url,

Write Preview
Loading…
Cancel
Save