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
55d4a76a
Commit
55d4a76a
authored
Sep 02, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
newselectors
parent
b1cba78b
Changes
5
Show whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
104 additions
and
15 deletions
+104
-15
pom.xml
webmagic-core/pom.xml
+6
-0
BaseElementSelector.java
...a/us/codecraft/webmagic/selector/BaseElementSelector.java
+23
-0
CssSelector.java
...main/java/us/codecraft/webmagic/selector/CssSelector.java
+11
-15
ElementSelector.java
.../java/us/codecraft/webmagic/selector/ElementSelector.java
+32
-0
XsoupSelector.java
...in/java/us/codecraft/webmagic/selector/XsoupSelector.java
+32
-0
No files found.
webmagic-core/pom.xml
View file @
55d4a76a
...
@@ -25,6 +25,12 @@
...
@@ -25,6 +25,12 @@
<artifactId>
commons-lang3
</artifactId>
<artifactId>
commons-lang3
</artifactId>
</dependency>
</dependency>
<dependency>
<groupId>
us.codecraft
</groupId>
<artifactId>
xsoup
</artifactId>
<version>
0.0.1-SNAPSHOT
</version>
</dependency>
<dependency>
<dependency>
<groupId>
log4j
</groupId>
<groupId>
log4j
</groupId>
<artifactId>
log4j
</artifactId>
<artifactId>
log4j
</artifactId>
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/BaseElementSelector.java
0 → 100644
View file @
55d4a76a
package
us
.
codecraft
.
webmagic
.
selector
;
import
org.jsoup.Jsoup
;
import
java.util.List
;
/**
* @author code4crafter@gmail.com
* @since 0.2.2
*/
public
abstract
class
BaseElementSelector
implements
Selector
,
ElementSelector
{
@Override
public
String
select
(
String
text
)
{
return
select
(
Jsoup
.
parse
(
text
));
}
@Override
public
List
<
String
>
selectList
(
String
text
)
{
return
selectList
(
Jsoup
.
parse
(
text
));
}
}
webmagic-core/src/main/java/us/codecraft/webmagic/selector/CssSelector.java
View file @
55d4a76a
package
us
.
codecraft
.
webmagic
.
selector
;
package
us
.
codecraft
.
webmagic
.
selector
;
import
org.apache.commons.collections.CollectionUtils
;
import
org.apache.commons.collections.CollectionUtils
;
import
org.jsoup.Jsoup
;
import
org.jsoup.nodes.Document
;
import
org.jsoup.nodes.Element
;
import
org.jsoup.nodes.Element
;
import
org.jsoup.select.Elements
;
import
org.jsoup.select.Elements
;
...
@@ -15,7 +13,7 @@ import java.util.List;
...
@@ -15,7 +13,7 @@ import java.util.List;
* @author code4crafter@gmail.com <br>
* @author code4crafter@gmail.com <br>
* @since 0.1.0
* @since 0.1.0
*/
*/
public
class
CssSelector
implements
Selector
{
public
class
CssSelector
extends
BaseElement
Selector
{
private
String
selectorText
;
private
String
selectorText
;
...
@@ -30,16 +28,6 @@ public class CssSelector implements Selector {
...
@@ -30,16 +28,6 @@ public class CssSelector implements Selector {
this
.
attrName
=
attrName
;
this
.
attrName
=
attrName
;
}
}
@Override
public
String
select
(
String
text
)
{
Document
doc
=
Jsoup
.
parse
(
text
);
Elements
elements
=
doc
.
select
(
selectorText
);
if
(
CollectionUtils
.
isEmpty
(
elements
))
{
return
null
;
}
return
getValue
(
elements
.
get
(
0
));
}
private
String
getValue
(
Element
element
)
{
private
String
getValue
(
Element
element
)
{
if
(
attrName
==
null
)
{
if
(
attrName
==
null
)
{
return
element
.
outerHtml
();
return
element
.
outerHtml
();
...
@@ -51,9 +39,17 @@ public class CssSelector implements Selector {
...
@@ -51,9 +39,17 @@ public class CssSelector implements Selector {
}
}
@Override
@Override
public
List
<
String
>
selectList
(
String
text
)
{
public
String
select
(
Element
element
)
{
Elements
elements
=
element
.
select
(
selectorText
);
if
(
CollectionUtils
.
isEmpty
(
elements
))
{
return
null
;
}
return
getValue
(
elements
.
get
(
0
));
}
@Override
public
List
<
String
>
selectList
(
Element
doc
)
{
List
<
String
>
strings
=
new
ArrayList
<
String
>();
List
<
String
>
strings
=
new
ArrayList
<
String
>();
Document
doc
=
Jsoup
.
parse
(
text
);
Elements
elements
=
doc
.
select
(
selectorText
);
Elements
elements
=
doc
.
select
(
selectorText
);
if
(
CollectionUtils
.
isNotEmpty
(
elements
))
{
if
(
CollectionUtils
.
isNotEmpty
(
elements
))
{
for
(
Element
element
:
elements
)
{
for
(
Element
element
:
elements
)
{
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/ElementSelector.java
0 → 100644
View file @
55d4a76a
package
us
.
codecraft
.
webmagic
.
selector
;
import
org.jsoup.nodes.Element
;
import
java.util.List
;
/**
* Selector(extractor) for html elements.<br>
*
* @author code4crafter@gmail.com <br>
* @since 0.2.2
*/
public
interface
ElementSelector
{
/**
* Extract single result in text.<br>
* If there are more than one result, only the first will be chosen.
*
* @param element
* @return result
*/
public
String
select
(
Element
element
);
/**
* Extract all results in text.<br>
*
* @param element
* @return results
*/
public
List
<
String
>
selectList
(
Element
element
);
}
webmagic-core/src/main/java/us/codecraft/webmagic/selector/XsoupSelector.java
0 → 100644
View file @
55d4a76a
package
us
.
codecraft
.
webmagic
.
selector
;
import
org.jsoup.nodes.Element
;
import
us.codecraft.xsoup.XPathEvaluator
;
import
us.codecraft.xsoup.Xsoup
;
import
java.util.List
;
/**
* XPath selector based on Xsoup.<br>
*
* @author code4crafter@gmail.com <br>
* @since 0.2.2
*/
public
class
XsoupSelector
extends
BaseElementSelector
{
private
XPathEvaluator
xPathEvaluator
;
public
XsoupSelector
(
String
xpathStr
)
{
this
.
xPathEvaluator
=
Xsoup
.
compile
(
xpathStr
);
}
@Override
public
String
select
(
Element
element
)
{
return
xPathEvaluator
.
evaluate
(
element
).
get
();
}
@Override
public
List
<
String
>
selectList
(
Element
element
)
{
return
xPathEvaluator
.
evaluate
(
element
).
list
();
}
}
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