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
42a30074
Commit
42a30074
authored
Sep 11, 2014
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update urls.contains to DuplicateRemover in FileCacheQueueScheduler #157
parent
689e89a9
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
22 additions
and
2 deletions
+22
-2
FileCacheQueueScheduler.java
...codecraft/webmagic/scheduler/FileCacheQueueScheduler.java
+22
-2
No files found.
webmagic-extension/src/main/java/us/codecraft/webmagic/scheduler/FileCacheQueueScheduler.java
View file @
42a30074
...
...
@@ -4,6 +4,7 @@ import org.apache.commons.io.IOUtils;
import
org.apache.commons.lang3.math.NumberUtils
;
import
us.codecraft.webmagic.Request
;
import
us.codecraft.webmagic.Task
;
import
us.codecraft.webmagic.scheduler.component.DuplicateRemover
;
import
java.io.*
;
import
java.util.LinkedHashSet
;
...
...
@@ -68,6 +69,26 @@ public class FileCacheQueueScheduler extends DuplicateRemovedScheduler implement
logger
.
info
(
"init cache scheduler success"
);
}
private
void
initDuplicateRemover
()
{
setDuplicateRemover
(
new
DuplicateRemover
()
{
@Override
public
boolean
isDuplicate
(
Request
request
,
Task
task
)
{
return
!
urls
.
add
(
request
.
getUrl
());
}
@Override
public
void
resetDuplicateCheck
(
Task
task
)
{
urls
.
clear
();
}
@Override
public
int
getTotalRequestsCount
(
Task
task
)
{
return
urls
.
size
();
}
});
}
private
void
initFlushThread
()
{
Executors
.
newScheduledThreadPool
(
1
).
scheduleAtFixedRate
(
new
Runnable
()
{
@Override
...
...
@@ -92,6 +113,7 @@ public class FileCacheQueueScheduler extends DuplicateRemovedScheduler implement
urls
=
new
LinkedHashSet
<
String
>();
readCursorFile
();
readUrlFile
();
initDuplicateRemover
();
}
catch
(
FileNotFoundException
e
)
{
//init
logger
.
info
(
"init cache file "
+
getFileName
(
fileUrlAllName
));
...
...
@@ -145,8 +167,6 @@ public class FileCacheQueueScheduler extends DuplicateRemovedScheduler implement
if
(!
inited
.
get
())
{
init
(
task
);
}
if
(
urls
.
contains
(
request
.
getUrl
()))
//已存在此URL 表示已抓取过 跳过
return
;
queue
.
add
(
request
);
fileUrlWriter
.
println
(
request
.
getUrl
());
}
...
...
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