Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
W
webmagic
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
沈俊林
webmagic
Commits
4f22f121
Commit
4f22f121
authored
May 02, 2014
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
some bug fix #118
parent
186b9051
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
13 additions
and
7 deletions
+13
-7
DuplicateRemovedScheduler.java
...decraft/webmagic/scheduler/DuplicateRemovedScheduler.java
+2
-1
BloomFilterDuplicateRemover.java
...agic/scheduler/component/BloomFilterDuplicateRemover.java
+1
-1
BloomFilterDuplicateRemoverTest.java
...t/webmagic/scheduler/BloomFilterDuplicateRemoverTest.java
+2
-2
OschinaBlogPageProcesser.java
.../codecraft/webmagic/samples/OschinaBlogPageProcesser.java
+8
-3
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/DuplicateRemovedScheduler.java
View file @
4f22f121
...
...
@@ -5,6 +5,7 @@ import org.slf4j.LoggerFactory;
import
us.codecraft.webmagic.Request
;
import
us.codecraft.webmagic.Task
;
import
us.codecraft.webmagic.scheduler.component.DuplicateRemover
;
import
us.codecraft.webmagic.scheduler.component.HashSetDuplicateRemover
;
/**
* Remove duplicate urls and only push urls which are not duplicate.<br></br>
...
...
@@ -16,7 +17,7 @@ public abstract class DuplicateRemovedScheduler implements Scheduler {
protected
Logger
logger
=
LoggerFactory
.
getLogger
(
getClass
());
private
DuplicateRemover
duplicatedRemover
;
private
DuplicateRemover
duplicatedRemover
=
new
HashSetDuplicateRemover
()
;
public
DuplicateRemover
getDuplicateRemover
()
{
return
duplicatedRemover
;
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/component/BloomFilterDuplicateRemover.java
View file @
4f22f121
...
...
@@ -43,7 +43,7 @@ public class BloomFilterDuplicateRemover implements DuplicateRemover {
public
boolean
isDuplicate
(
Request
request
,
Task
task
)
{
boolean
isDuplicate
=
bloomFilter
.
mightContain
(
request
.
getUrl
());
if
(!
isDuplicate
)
{
bloomFilter
.
apply
(
request
.
getUrl
());
bloomFilter
.
put
(
request
.
getUrl
());
counter
.
incrementAndGet
();
}
return
isDuplicate
;
...
...
webmagic-core/src/test/java/us/codecraft/webmagic/scheduler/BloomFilterDuplicateRemoverTest.java
View file @
4f22f121
...
...
@@ -17,11 +17,11 @@ public class BloomFilterDuplicateRemoverTest {
boolean
isDuplicate
=
bloomFilterDuplicateRemover
.
isDuplicate
(
new
Request
(
"a"
),
null
);
assertThat
(
isDuplicate
).
isFalse
();
isDuplicate
=
bloomFilterDuplicateRemover
.
isDuplicate
(
new
Request
(
"a"
),
null
);
assertThat
(
isDuplicate
);
assertThat
(
isDuplicate
)
.
isTrue
()
;
isDuplicate
=
bloomFilterDuplicateRemover
.
isDuplicate
(
new
Request
(
"b"
),
null
);
assertThat
(
isDuplicate
).
isFalse
();
isDuplicate
=
bloomFilterDuplicateRemover
.
isDuplicate
(
new
Request
(
"b"
),
null
);
assertThat
(
isDuplicate
);
assertThat
(
isDuplicate
)
.
isTrue
()
;
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/OschinaBlogPageProcesser.java
View file @
4f22f121
...
...
@@ -3,9 +3,12 @@ package us.codecraft.webmagic.samples;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.monitor.SpiderMonitor
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
us.codecraft.webmagic.scheduler.RedisScheduler
;
import
us.codecraft.webmagic.scheduler.QueueScheduler
;
import
us.codecraft.webmagic.scheduler.component.BloomFilterDuplicateRemover
;
import
javax.management.JMException
;
import
java.util.List
;
/**
...
...
@@ -30,7 +33,9 @@ public class OschinaBlogPageProcesser implements PageProcessor {
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
OschinaBlogPageProcesser
()).
setScheduler
(
new
RedisScheduler
(
"localhost"
)).
run
();
public
static
void
main
(
String
[]
args
)
throws
JMException
{
Spider
spider
=
Spider
.
create
(
new
OschinaBlogPageProcesser
()).
setScheduler
(
new
QueueScheduler
().
setDuplicateRemover
(
new
BloomFilterDuplicateRemover
(
2000
)));
SpiderMonitor
.
instance
().
register
(
spider
);
spider
.
run
();
}
}
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment