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
36494bcf
Commit
36494bcf
authored
Aug 06, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add xpath2.0 api
parent
5c96407a
Changes
15
Show whitespace changes
Inline
Side-by-side
Showing
15 changed files
with
38 additions
and
22 deletions
+38
-22
ConsolePipeline.java
.../java/us/codecraft/webmagic/pipeline/ConsolePipeline.java
+7
-14
Html.java
...re/src/main/java/us/codecraft/webmagic/selector/Html.java
+6
-0
PlainText.java
...c/main/java/us/codecraft/webmagic/selector/PlainText.java
+5
-0
Selectable.java
.../main/java/us/codecraft/webmagic/selector/Selectable.java
+8
-0
SelectorFactory.java
.../java/us/codecraft/webmagic/selector/SelectorFactory.java
+4
-0
FileDownloader.java
...java/us/codecraft/webmagic/downloader/FileDownloader.java
+0
-0
FileCacheQueueScheduler.java
...codecraft/webmagic/scheduler/FileCacheQueueScheduler.java
+2
-1
DoubleKeyMap.java
...c/main/java/us/codecraft/webmagic/utils/DoubleKeyMap.java
+0
-0
MultiKeyMapBase.java
...ain/java/us/codecraft/webmagic/utils/MultiKeyMapBase.java
+0
-0
OschinaBlog.java
...java/us/codecraft/webmagic/model/samples/OschinaBlog.java
+1
-2
GuoxueProcessor.java
...n/java/us/codecraft/webmagic/samples/GuoxueProcessor.java
+1
-1
SpiderTest.java
...mples/src/test/java/us/codecraft/webmagic/SpiderTest.java
+1
-1
DiandianProcessorTest.java
...s/codecraft/webmagic/processor/DiandianProcessorTest.java
+1
-1
DiaoyuwengProcessorTest.java
...codecraft/webmagic/processor/DiaoyuwengProcessorTest.java
+1
-1
SinablogProcessorTest.java
...s/codecraft/webmagic/processor/SinablogProcessorTest.java
+1
-1
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/pipeline/ConsolePipeline.java
View file @
36494bcf
...
...
@@ -7,25 +7,18 @@ import java.util.Map;
/**
* 命令行输出抽取结果。可用于测试。<br>
*
* @author code4crafter@gmail.com <br>
* Date: 13-4-21
* Time: 下午1:45
*/
public
class
ConsolePipeline
implements
Pipeline
{
public
class
ConsolePipeline
implements
Pipeline
{
@Override
public
void
process
(
ResultItems
resultItems
,
Task
task
)
{
System
.
out
.
println
(
"get page: "
+
resultItems
.
getRequest
().
getUrl
());
public
void
process
(
ResultItems
resultItems
,
Task
task
)
{
System
.
out
.
println
(
"get page: "
+
resultItems
.
getRequest
().
getUrl
());
for
(
Map
.
Entry
<
String
,
Object
>
entry
:
resultItems
.
getAll
().
entrySet
())
{
if
(
entry
.
getValue
()
instanceof
Iterable
)
{
Iterable
value
=
(
Iterable
)
entry
.
getValue
();
System
.
out
.
println
(
entry
.
getKey
()
+
":"
);
for
(
Object
o
:
value
)
{
System
.
out
.
println
(
o
);
}
}
else
{
System
.
out
.
println
(
entry
.
getKey
()
+
":\t"
+
entry
.
getValue
());
}
}
}
}
webmagic-core/src/main/java/us/codecraft/webmagic/selector/Html.java
View file @
36494bcf
...
...
@@ -63,6 +63,12 @@ public class Html extends PlainText {
return
selectList
(
xpathSelector
,
strings
);
}
@Override
public
Selectable
xpath2
(
String
xpath
)
{
Xpath2Selector
xpathSelector
=
SelectorFactory
.
getInstatnce
().
newXpath2Selector
(
xpath
);
return
selectList
(
xpathSelector
,
strings
);
}
@Override
public
Selectable
$
(
String
selector
)
{
CssSelector
cssSelector
=
new
CssSelector
(
selector
);
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/PlainText.java
View file @
36494bcf
...
...
@@ -34,6 +34,11 @@ public class PlainText implements Selectable {
throw
new
UnsupportedOperationException
();
}
@Override
public
Selectable
xpath2
(
String
xpath
)
{
throw
new
UnsupportedOperationException
();
}
@Override
public
Selectable
$
(
String
selector
)
{
throw
new
UnsupportedOperationException
();
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/Selectable.java
View file @
36494bcf
...
...
@@ -18,6 +18,14 @@ public interface Selectable {
*/
public
Selectable
xpath
(
String
xpath
);
/**
* select list with xpath 2.0 syntax
*
* @param xpath
* @return new Selectable after extract
*/
public
Selectable
xpath2
(
String
xpath
);
/**
* select list with css selector
*
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/SelectorFactory.java
View file @
36494bcf
...
...
@@ -34,6 +34,10 @@ public class SelectorFactory {
return
newSelector
(
XpathSelector
.
class
,
xpath
);
}
public
Xpath2Selector
newXpath2Selector
(
String
xpath
)
{
return
newSelector
(
Xpath2Selector
.
class
,
xpath
);
}
public
SmartContentSelector
newSmartContentSelector
(){
return
newSelector
(
SmartContentSelector
.
class
);
}
...
...
webmagic-
core
/src/main/java/us/codecraft/webmagic/downloader/FileDownloader.java
→
webmagic-
plugin/webmagic-misc
/src/main/java/us/codecraft/webmagic/downloader/FileDownloader.java
View file @
36494bcf
File moved
webmagic-
core/src/main/java/us/codecraft/webmagic/schedula
r/FileCacheQueueScheduler.java
→
webmagic-
plugin/webmagic-misc/src/main/java/us/codecraft/webmagic/schedule
r/FileCacheQueueScheduler.java
View file @
36494bcf
package
us
.
codecraft
.
webmagic
.
schedul
a
r
;
package
us
.
codecraft
.
webmagic
.
schedul
e
r
;
import
org.apache.commons.lang3.math.NumberUtils
;
import
org.apache.log4j.Logger
;
import
us.codecraft.webmagic.Request
;
import
us.codecraft.webmagic.Task
;
import
us.codecraft.webmagic.schedular.Scheduler
;
import
java.io.*
;
import
java.util.LinkedHashSet
;
...
...
webmagic-
core
/src/main/java/us/codecraft/webmagic/utils/DoubleKeyMap.java
→
webmagic-
plugin/webmagic-misc
/src/main/java/us/codecraft/webmagic/utils/DoubleKeyMap.java
View file @
36494bcf
File moved
webmagic-
core
/src/main/java/us/codecraft/webmagic/utils/MultiKeyMapBase.java
→
webmagic-
plugin/webmagic-misc
/src/main/java/us/codecraft/webmagic/utils/MultiKeyMapBase.java
View file @
36494bcf
File moved
webmagic-samples/src/main/java/us/codecraft/webmagic/model/samples/OschinaBlog.java
View file @
36494bcf
...
...
@@ -4,7 +4,6 @@ import us.codecraft.webmagic.Site;
import
us.codecraft.webmagic.model.ExtractBy
;
import
us.codecraft.webmagic.model.OOSpider
;
import
us.codecraft.webmagic.model.TargetUrl
;
import
us.codecraft.webmagic.pipeline.ConsolePipeline
;
import
us.codecraft.webmagic.pipeline.JsonFilePipeline
;
/**
...
...
@@ -30,7 +29,7 @@ public class OschinaBlog implements Blog{
}
public
static
void
main
(
String
[]
args
)
{
OOSpider
.
create
(
Site
.
me
().
addStartUrl
(
"http://my.oschina.net/flashsword/blog"
),
OschinaBlog
.
class
).
pipeline
(
new
ConsolePipeline
()).
pipeline
(
new
JsonFilePipeline
()).
run
();
OOSpider
.
create
(
Site
.
me
().
addStartUrl
(
"http://my.oschina.net/flashsword/blog"
),
OschinaBlog
.
class
).
pipeline
(
new
JsonFilePipeline
()).
run
();
}
public
String
getTitle
()
{
...
...
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/GuoxueProcessor.java
View file @
36494bcf
...
...
@@ -3,7 +3,7 @@ package us.codecraft.webmagic.samples;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.processor.SimplePageProcessor
;
import
us.codecraft.webmagic.schedul
a
r.FileCacheQueueScheduler
;
import
us.codecraft.webmagic.schedul
e
r.FileCacheQueueScheduler
;
/**
* @author code4crafter@gmail.com <br>
...
...
webmagic-samples/src/test/java/us/codecraft/webmagic/SpiderTest.java
View file @
36494bcf
...
...
@@ -5,7 +5,7 @@ import org.junit.Test;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.processor.SimplePageProcessor
;
import
us.codecraft.webmagic.samples.HuxiuProcessor
;
import
us.codecraft.webmagic.schedul
a
r.FileCacheQueueScheduler
;
import
us.codecraft.webmagic.schedul
e
r.FileCacheQueueScheduler
;
/**
* @author code4crafter@gmail.com <br>
...
...
webmagic-samples/src/test/java/us/codecraft/webmagic/processor/DiandianProcessorTest.java
View file @
36494bcf
...
...
@@ -6,7 +6,7 @@ import us.codecraft.webmagic.Spider;
import
us.codecraft.webmagic.pipeline.ConsolePipeline
;
import
us.codecraft.webmagic.pipeline.FreemarkerPipeline
;
import
us.codecraft.webmagic.samples.DiandianBlogProcessor
;
import
us.codecraft.webmagic.schedul
a
r.FileCacheQueueScheduler
;
import
us.codecraft.webmagic.schedul
e
r.FileCacheQueueScheduler
;
import
java.io.IOException
;
...
...
webmagic-samples/src/test/java/us/codecraft/webmagic/processor/DiaoyuwengProcessorTest.java
View file @
36494bcf
...
...
@@ -6,7 +6,7 @@ import us.codecraft.webmagic.Spider;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.pipeline.FreemarkerPipeline
;
import
us.codecraft.webmagic.samples.DiaoyuwengProcessor
;
import
us.codecraft.webmagic.schedul
a
r.FileCacheQueueScheduler
;
import
us.codecraft.webmagic.schedul
e
r.FileCacheQueueScheduler
;
import
java.io.IOException
;
...
...
webmagic-samples/src/test/java/us/codecraft/webmagic/processor/SinablogProcessorTest.java
View file @
36494bcf
...
...
@@ -6,7 +6,7 @@ import us.codecraft.webmagic.Spider;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.pipeline.FreemarkerPipeline
;
import
us.codecraft.webmagic.samples.SinaBlogProcesser
;
import
us.codecraft.webmagic.schedul
a
r.FileCacheQueueScheduler
;
import
us.codecraft.webmagic.schedul
e
r.FileCacheQueueScheduler
;
import
java.io.IOException
;
...
...
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