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
20705b34
Commit
20705b34
authored
Aug 20, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add more option to extractors
parent
c70ed570
Changes
5
Hide whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
60 additions
and
3 deletions
+60
-3
CssSelector.java
...main/java/us/codecraft/webmagic/selector/CssSelector.java
+20
-2
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
+11
-0
Selectable.java
.../main/java/us/codecraft/webmagic/selector/Selectable.java
+19
-1
SelectorFactory.java
.../java/us/codecraft/webmagic/selector/SelectorFactory.java
+4
-0
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/selector/CssSelector.java
View file @
20705b34
...
@@ -19,10 +19,17 @@ public class CssSelector implements Selector {
...
@@ -19,10 +19,17 @@ public class CssSelector implements Selector {
private
String
selectorText
;
private
String
selectorText
;
private
String
attrName
;
public
CssSelector
(
String
selectorText
)
{
public
CssSelector
(
String
selectorText
)
{
this
.
selectorText
=
selectorText
;
this
.
selectorText
=
selectorText
;
}
}
public
CssSelector
(
String
selectorText
,
String
attrName
)
{
this
.
selectorText
=
selectorText
;
this
.
attrName
=
attrName
;
}
@Override
@Override
public
String
select
(
String
text
)
{
public
String
select
(
String
text
)
{
Document
doc
=
Jsoup
.
parse
(
text
);
Document
doc
=
Jsoup
.
parse
(
text
);
...
@@ -30,7 +37,15 @@ public class CssSelector implements Selector {
...
@@ -30,7 +37,15 @@ public class CssSelector implements Selector {
if
(
CollectionUtils
.
isEmpty
(
elements
))
{
if
(
CollectionUtils
.
isEmpty
(
elements
))
{
return
null
;
return
null
;
}
}
return
elements
.
get
(
0
).
outerHtml
();
return
getValue
(
elements
.
get
(
0
));
}
private
String
getValue
(
Element
element
)
{
if
(
attrName
==
null
)
{
return
element
.
outerHtml
();
}
else
{
return
element
.
attr
(
attrName
);
}
}
}
@Override
@Override
...
@@ -40,7 +55,10 @@ public class CssSelector implements Selector {
...
@@ -40,7 +55,10 @@ public class CssSelector implements Selector {
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
)
{
strings
.
add
(
element
.
outerHtml
());
String
value
=
getValue
(
element
);
if
(
value
!=
null
)
{
strings
.
add
(
value
);
}
}
}
}
}
return
strings
;
return
strings
;
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/Html.java
View file @
20705b34
...
@@ -69,4 +69,10 @@ public class Html extends PlainText {
...
@@ -69,4 +69,10 @@ public class Html extends PlainText {
return
selectList
(
cssSelector
,
strings
);
return
selectList
(
cssSelector
,
strings
);
}
}
@Override
public
Selectable
$
(
String
selector
,
String
attrName
)
{
CssSelector
cssSelector
=
new
CssSelector
(
selector
,
attrName
);
return
selectList
(
cssSelector
,
strings
);
}
}
}
webmagic-core/src/main/java/us/codecraft/webmagic/selector/PlainText.java
View file @
20705b34
...
@@ -40,6 +40,11 @@ public class PlainText implements Selectable {
...
@@ -40,6 +40,11 @@ public class PlainText implements Selectable {
throw
new
UnsupportedOperationException
();
throw
new
UnsupportedOperationException
();
}
}
@Override
public
Selectable
$
(
String
selector
,
String
attrName
)
{
throw
new
UnsupportedOperationException
();
}
@Override
@Override
public
Selectable
smartContent
()
{
public
Selectable
smartContent
()
{
throw
new
UnsupportedOperationException
();
throw
new
UnsupportedOperationException
();
...
@@ -56,6 +61,12 @@ public class PlainText implements Selectable {
...
@@ -56,6 +61,12 @@ public class PlainText implements Selectable {
return
selectList
(
regexSelector
,
strings
);
return
selectList
(
regexSelector
,
strings
);
}
}
@Override
public
Selectable
regex
(
String
regex
,
int
group
)
{
RegexSelector
regexSelector
=
SelectorFactory
.
getInstatnce
().
newRegexSelector
(
regex
,
group
);
return
selectList
(
regexSelector
,
strings
);
}
protected
Selectable
select
(
Selector
selector
,
List
<
String
>
strings
)
{
protected
Selectable
select
(
Selector
selector
,
List
<
String
>
strings
)
{
List
<
String
>
results
=
new
ArrayList
<
String
>();
List
<
String
>
results
=
new
ArrayList
<
String
>();
for
(
String
string
:
strings
)
{
for
(
String
string
:
strings
)
{
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/Selectable.java
View file @
20705b34
...
@@ -26,6 +26,15 @@ public interface Selectable {
...
@@ -26,6 +26,15 @@ public interface Selectable {
*/
*/
public
Selectable
$
(
String
selector
);
public
Selectable
$
(
String
selector
);
/**
* select list with css selector
*
* @param selector css selector expression
* @param attrName attribute name of css selector
* @return new Selectable after extract
*/
public
Selectable
$
(
String
selector
,
String
attrName
);
/**
/**
* select smart content with ReadAbility algorithm
* select smart content with ReadAbility algorithm
*
*
...
@@ -41,13 +50,22 @@ public interface Selectable {
...
@@ -41,13 +50,22 @@ public interface Selectable {
public
Selectable
links
();
public
Selectable
links
();
/**
/**
* select list with regex
* select list with regex
, default group is group 1
*
*
* @param regex
* @param regex
* @return new Selectable after extract
* @return new Selectable after extract
*/
*/
public
Selectable
regex
(
String
regex
);
public
Selectable
regex
(
String
regex
);
/**
* select list with regex
*
* @param regex
* @param group
* @return new Selectable after extract
*/
public
Selectable
regex
(
String
regex
,
int
group
);
/**
/**
* replace with regex
* replace with regex
*
*
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/selector/SelectorFactory.java
View file @
20705b34
...
@@ -26,6 +26,10 @@ public class SelectorFactory {
...
@@ -26,6 +26,10 @@ public class SelectorFactory {
return
newSelector
(
RegexSelector
.
class
,
regex
);
return
newSelector
(
RegexSelector
.
class
,
regex
);
}
}
public
RegexSelector
newRegexSelector
(
String
regex
,
int
group
)
{
return
newSelector
(
RegexSelector
.
class
,
regex
,
String
.
valueOf
(
group
));
}
public
ReplaceSelector
newReplaceSelector
(
String
regex
,
String
replacement
)
{
public
ReplaceSelector
newReplaceSelector
(
String
regex
,
String
replacement
)
{
return
newSelector
(
ReplaceSelector
.
class
,
regex
,
replacement
);
return
newSelector
(
ReplaceSelector
.
class
,
regex
,
replacement
);
}
}
...
...
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