From 524835045cc1ee39e290f7cffb76c52914d05388 Mon Sep 17 00:00:00 2001 From: Denis Basargin Date: Wed, 7 Nov 2018 11:33:54 +0300 Subject: [PATCH 1/3] Fix Spider main thread any problem with redis connection (when working with redis-based schedulers) leads to unhandled exception and release the main (control) thread --- webmagic-core/pom.xml | 2 +- .../src/main/java/us/codecraft/webmagic/Spider.java | 8 +++++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/webmagic-core/pom.xml b/webmagic-core/pom.xml index e889cd491..b81d31db7 100644 --- a/webmagic-core/pom.xml +++ b/webmagic-core/pom.xml @@ -3,7 +3,7 @@ us.codecraft webmagic-parent - 0.7.3 + 0.7.5 4.0.0 diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/Spider.java b/webmagic-core/src/main/java/us/codecraft/webmagic/Spider.java index 62c989f1d..421b54e0b 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/Spider.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/Spider.java @@ -305,7 +305,13 @@ public void run() { initComponent(); logger.info("Spider {} started!",getUUID()); while (!Thread.currentThread().isInterrupted() && stat.get() == STAT_RUNNING) { - final Request request = scheduler.poll(this); + final Request request; + try { + request = scheduler.poll(this); + } catch (Exception e) { + logger.warn(e.getMessage()); + continue; + } if (request == null) { if (threadPool.getThreadAlive() == 0 && exitWhenComplete) { break; From 99349dbd4c9fdaea35411aad47ad03c09aae265f Mon Sep 17 00:00:00 2001 From: Denis Basargin Date: Wed, 7 Nov 2018 11:34:14 +0300 Subject: [PATCH 2/3] vesion 0.7.3 --- pom.xml | 9 +-------- webmagic-extension/pom.xml | 2 +- webmagic-samples/pom.xml | 2 +- webmagic-saxon/pom.xml | 2 +- webmagic-scripts/pom.xml | 4 ++-- webmagic-selenium/pom.xml | 2 +- 6 files changed, 7 insertions(+), 14 deletions(-) diff --git a/pom.xml b/pom.xml index 2b2384fd8..02b79d92f 100644 --- a/pom.xml +++ b/pom.xml @@ -6,14 +6,13 @@ 7 us.codecraft - 0.7.3 + 0.7.5 4.0.0 pom UTF-8 UTF-8 4.0.0.RELEASE - webmagic-parent webmagic-parent @@ -64,12 +63,6 @@ 4.11 test - - org.mockito - mockito-all - 1.10.19 - test - org.apache.httpcomponents httpclient diff --git a/webmagic-extension/pom.xml b/webmagic-extension/pom.xml index 7e949ca6f..c71640113 100644 --- a/webmagic-extension/pom.xml +++ b/webmagic-extension/pom.xml @@ -3,7 +3,7 @@ us.codecraft webmagic-parent - 0.7.3 + 0.7.5 4.0.0 diff --git a/webmagic-samples/pom.xml b/webmagic-samples/pom.xml index 072bb3fd5..c02c07421 100644 --- a/webmagic-samples/pom.xml +++ b/webmagic-samples/pom.xml @@ -3,7 +3,7 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0 diff --git a/webmagic-saxon/pom.xml b/webmagic-saxon/pom.xml index 95f706ed5..f8b3c1f24 100644 --- a/webmagic-saxon/pom.xml +++ b/webmagic-saxon/pom.xml @@ -3,7 +3,7 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0 diff --git a/webmagic-scripts/pom.xml b/webmagic-scripts/pom.xml index 22956cb55..af72f18fc 100755 --- a/webmagic-scripts/pom.xml +++ b/webmagic-scripts/pom.xml @@ -3,12 +3,12 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0 - us.codecraft webmagic-scripts + 1.1.2-2 diff --git a/webmagic-selenium/pom.xml b/webmagic-selenium/pom.xml index 1cbf59216..1fa05538d 100644 --- a/webmagic-selenium/pom.xml +++ b/webmagic-selenium/pom.xml @@ -3,7 +3,7 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0 From c22e579cb097c1591852786db62df4bd68aa1dd6 Mon Sep 17 00:00:00 2001 From: Denis Basargin Date: Wed, 7 Nov 2018 11:34:14 +0300 Subject: [PATCH 3/3] vesion 0.7.5 --- pom.xml | 9 +-------- webmagic-extension/pom.xml | 2 +- webmagic-samples/pom.xml | 2 +- webmagic-saxon/pom.xml | 2 +- webmagic-scripts/pom.xml | 4 ++-- webmagic-selenium/pom.xml | 2 +- 6 files changed, 7 insertions(+), 14 deletions(-) diff --git a/pom.xml b/pom.xml index 2b2384fd8..02b79d92f 100644 --- a/pom.xml +++ b/pom.xml @@ -6,14 +6,13 @@ 7 us.codecraft - 0.7.3 + 0.7.5 4.0.0 pom UTF-8 UTF-8 4.0.0.RELEASE - webmagic-parent webmagic-parent @@ -64,12 +63,6 @@ 4.11 test - - org.mockito - mockito-all - 1.10.19 - test - org.apache.httpcomponents httpclient diff --git a/webmagic-extension/pom.xml b/webmagic-extension/pom.xml index 7e949ca6f..c71640113 100644 --- a/webmagic-extension/pom.xml +++ b/webmagic-extension/pom.xml @@ -3,7 +3,7 @@ us.codecraft webmagic-parent - 0.7.3 + 0.7.5 4.0.0 diff --git a/webmagic-samples/pom.xml b/webmagic-samples/pom.xml index 072bb3fd5..c02c07421 100644 --- a/webmagic-samples/pom.xml +++ b/webmagic-samples/pom.xml @@ -3,7 +3,7 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0 diff --git a/webmagic-saxon/pom.xml b/webmagic-saxon/pom.xml index 95f706ed5..f8b3c1f24 100644 --- a/webmagic-saxon/pom.xml +++ b/webmagic-saxon/pom.xml @@ -3,7 +3,7 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0 diff --git a/webmagic-scripts/pom.xml b/webmagic-scripts/pom.xml index 22956cb55..af72f18fc 100755 --- a/webmagic-scripts/pom.xml +++ b/webmagic-scripts/pom.xml @@ -3,12 +3,12 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0 - us.codecraft webmagic-scripts + 1.1.2-2 diff --git a/webmagic-selenium/pom.xml b/webmagic-selenium/pom.xml index 1cbf59216..1fa05538d 100644 --- a/webmagic-selenium/pom.xml +++ b/webmagic-selenium/pom.xml @@ -3,7 +3,7 @@ webmagic-parent us.codecraft - 0.7.3 + 0.7.5 4.0.0