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
e8d4a9be
Commit
e8d4a9be
authored
Apr 29, 2014
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fix remove duplicate error #117
parent
22652c45
Changes
5
Hide whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
58 additions
and
4 deletions
+58
-4
DuplicatedRemoveScheduler.java
...decraft/webmagic/scheduler/DuplicatedRemoveScheduler.java
+1
-1
LocalDuplicatedRemoveScheduler.java
...ft/webmagic/scheduler/LocalDuplicatedRemoveScheduler.java
+1
-1
RedisScheduler.java
.../java/us/codecraft/webmagic/scheduler/RedisScheduler.java
+1
-1
AmanzonPageProcessor.java
...a/us/codecraft/webmagic/samples/AmanzonPageProcessor.java
+53
-0
OschinaBlogPageProcesser.java
.../codecraft/webmagic/samples/OschinaBlogPageProcesser.java
+2
-1
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/DuplicatedRemoveScheduler.java
View file @
e8d4a9be
...
...
@@ -18,7 +18,7 @@ public abstract class DuplicatedRemoveScheduler implements Scheduler {
@Override
public
void
push
(
Request
request
,
Task
task
)
{
logger
.
trace
(
"get a candidate url {}"
,
request
.
getUrl
());
if
(
isDuplicate
(
request
,
task
)
||
shouldReserved
(
request
))
{
if
(
!
isDuplicate
(
request
,
task
)
||
shouldReserved
(
request
))
{
logger
.
debug
(
"push to queue {}"
,
request
.
getUrl
());
pushWhenNoDuplicate
(
request
,
task
);
}
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/scheduler/LocalDuplicatedRemoveScheduler.java
View file @
e8d4a9be
...
...
@@ -24,7 +24,7 @@ public abstract class LocalDuplicatedRemoveScheduler extends DuplicatedRemoveSch
@Override
protected
boolean
isDuplicate
(
Request
request
,
Task
task
)
{
return
urls
.
add
(
request
.
getUrl
());
return
!
urls
.
add
(
request
.
getUrl
());
}
@Override
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/scheduler/RedisScheduler.java
View file @
e8d4a9be
...
...
@@ -46,7 +46,7 @@ public class RedisScheduler extends DuplicatedRemoveScheduler implements Monitor
protected
boolean
isDuplicate
(
Request
request
,
Task
task
)
{
Jedis
jedis
=
pool
.
getResource
();
try
{
boolean
isDuplicate
=
!
jedis
.
sismember
(
getSetKey
(
task
),
request
.
getUrl
());
boolean
isDuplicate
=
jedis
.
sismember
(
getSetKey
(
task
),
request
.
getUrl
());
if
(!
isDuplicate
)
{
jedis
.
sadd
(
getSetKey
(
task
),
request
.
getUrl
());
}
...
...
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/AmanzonPageProcessor.java
0 → 100644
View file @
e8d4a9be
package
us
.
codecraft
.
webmagic
.
samples
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
us.codecraft.webmagic.selector.Html
;
import
java.util.List
;
/**
* @author code4crafer@gmail.com
*/
public
class
AmanzonPageProcessor
implements
PageProcessor
{
public
void
process
(
Page
page
)
{
Html
html
=
page
.
getHtml
();
List
<
String
>
questionList
=
html
.
xpath
(
"//table[@class='tgCustomerCommunityCenterColumn']//div[@class='content']//table[@class='dataGrid']//tr"
).
all
();
if
(
questionList
!=
null
&&
questionList
.
size
()
>
1
)
{
//i=0是列名称,所以i从1开始
for
(
int
i
=
1
;
i
<
questionList
.
size
();
i
++)
{
System
.
out
.
println
(
questionList
.
get
(
i
));
Html
tempHtml
=
Html
.
create
(
"<table>"
+
questionList
.
get
(
i
)+
"</table>"
);
String
comment
=
tempHtml
.
xpath
(
"//td[@class='title']//a/text()"
).
toString
();
System
.
out
.
println
(
comment
);
String
answerNum
=
tempHtml
.
xpath
(
"//td[@class='num']/text()"
).
toString
();
System
.
out
.
println
(
answerNum
);
String
createTime
=
tempHtml
.
xpath
(
"//td[3]/text()"
).
toString
();
System
.
out
.
println
(
createTime
);
/* Document doc = Jsoup.parse(questionList.get(i));
Html hmt = Html.create(questionList.get(i)) ;
String str = hmt.links().toString();
String content = doc.getElementsByTag("a").text();
String ss = doc.text();*/
}
}
}
@Override
public
Site
getSite
()
{
return
Site
.
me
();
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
AmanzonPageProcessor
()).
test
(
"http://www.amazon.de/forum/Fx27CUFD8S7LJ5D"
);
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/OschinaBlogPageProcesser.java
View file @
e8d4a9be
...
...
@@ -4,6 +4,7 @@ import us.codecraft.webmagic.Page;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
us.codecraft.webmagic.scheduler.RedisScheduler
;
import
java.util.List
;
...
...
@@ -30,6 +31,6 @@ public class OschinaBlogPageProcesser implements PageProcessor {
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
OschinaBlogPageProcesser
()).
run
();
Spider
.
create
(
new
OschinaBlogPageProcesser
()).
setScheduler
(
new
RedisScheduler
(
"localhost"
)).
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