From 762a3973fd912b6812d0bc059930ed4567a2677a Mon Sep 17 00:00:00 2001 From: Bo LIANG Date: Fri, 4 Apr 2014 15:53:46 +0800 Subject: [PATCH] Modify the log levels of LocalDuplicatedRemovedScheduler.java The old version will print a debug level log each time the push method is called. So sometimes, when a html page have multiple links for the same page, the debug log will appears more than once. Also, when we meet a duplicate URL, it will also print a log, which will be confusing. I change the level of it to trace. And each time a URL is really push into queue, print a debug level log. --- .../webmagic/scheduler/LocalDuplicatedRemovedScheduler.java | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/LocalDuplicatedRemovedScheduler.java b/webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/LocalDuplicatedRemovedScheduler.java index c4b08f37..da32c66b 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/LocalDuplicatedRemovedScheduler.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/LocalDuplicatedRemovedScheduler.java @@ -23,8 +23,9 @@ public abstract class LocalDuplicatedRemovedScheduler implements Scheduler { @Override public void push(Request request, Task task) { - logger.debug("push to queue " + request.getUrl()); + logger.trace("get a candidate url " + request.getUrl()); if (request.getExtra(Request.CYCLE_TRIED_TIMES) != null || urls.add(request.getUrl())) { + logger.debug("push to queue " + request.getUrl()); pushWhenNoDuplicate(request, task); } }