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
b1650904
Commit
b1650904
authored
May 27, 2014
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Bugfix:Type convert error in JsonPathSelector #129
parent
95bdb302
Changes
5
Hide whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
24 additions
and
25 deletions
+24
-25
JsonPathSelector.java
...java/us/codecraft/webmagic/selector/JsonPathSelector.java
+5
-2
ExtractorsTest.java
...t/java/us/codecraft/webmagic/selector/ExtractorsTest.java
+10
-10
JsonPathSelectorTest.java
.../us/codecraft/webmagic/selector/JsonPathSelectorTest.java
+7
-6
RegexSelectorTest.java
...ava/us/codecraft/webmagic/selector/RegexSelectorTest.java
+2
-2
UrlUtilsTest.java
...c/test/java/us/codecraft/webmagic/utils/UrlUtilsTest.java
+0
-5
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/selector/JsonPathSelector.java
View file @
b1650904
...
...
@@ -46,9 +46,12 @@ public class JsonPathSelector implements Selector {
return
list
;
}
if
(
object
instanceof
List
)
{
return
(
List
<
String
>)
object
;
List
<
Object
>
items
=
(
List
<
Object
>)
object
;
for
(
Object
item
:
items
)
{
list
.
add
(
String
.
valueOf
(
item
));
}
}
else
{
list
.
add
(
object
.
toString
(
));
list
.
add
(
String
.
valueOf
(
object
));
}
return
list
;
}
...
...
webmagic-core/src/test/java/us/codecraft/webmagic/selector/ExtractorsTest.java
View file @
b1650904
package
us
.
codecraft
.
webmagic
.
selector
;
import
junit.framework.Assert
;
import
org.junit.Test
;
import
static
org
.
assertj
.
core
.
api
.
Assertions
.
assertThat
;
import
static
us
.
codecraft
.
webmagic
.
selector
.
Selectors
.*;
/**
...
...
@@ -16,19 +16,19 @@ public class ExtractorsTest {
@Test
public
void
testEach
()
{
Assert
.
assertEquals
(
"<a href=\"xxx\">aabbcc</a>"
,
$
(
"div h1 a"
).
select
(
html
)
);
Assert
.
assertEquals
(
"xxx"
,
$
(
"div h1 a"
,
"href"
).
select
(
html
)
);
Assert
.
assertEquals
(
"aabbcc"
,
$
(
"div h1 a"
,
"innerHtml"
).
select
(
html
)
);
Assert
.
assertEquals
(
"xxx"
,
xpath
(
"//a/@href"
).
select
(
html
)
);
Assert
.
assertEquals
(
"xxx"
,
regex
(
"a href=\"(.*)\""
).
select
(
html
)
);
Assert
.
assertEquals
(
"xxx"
,
regex
(
"(a href)=\"(.*)\""
,
2
).
select
(
html
)
);
assertThat
(
$
(
"div h1 a"
).
select
(
html
)).
isEqualTo
(
"<a href=\"xxx\">aabbcc</a>"
);
assertThat
(
$
(
"div h1 a"
,
"href"
).
select
(
html
)).
isEqualTo
(
"xxx"
);
assertThat
(
$
(
"div h1 a"
,
"innerHtml"
).
select
(
html
)).
isEqualTo
(
"aabbcc"
);
assertThat
(
xpath
(
"//a/@href"
).
select
(
html
)).
isEqualTo
(
"xxx"
);
assertThat
(
regex
(
"a href=\"(.*)\""
).
select
(
html
)).
isEqualTo
(
"xxx"
);
assertThat
(
regex
(
"(a href)=\"(.*)\""
,
2
).
select
(
html
)).
isEqualTo
(
"xxx"
);
}
@Test
public
void
testCombo
()
{
Assert
.
assertEquals
(
"bb"
,
and
(
$
(
"title"
),
regex
(
"aa(bb)cc"
)).
select
(
html2
)
);
assertThat
(
and
(
$
(
"title"
),
regex
(
"aa(bb)cc"
)).
select
(
html2
)).
isEqualTo
(
"bb"
);
OrSelector
or
=
or
(
$
(
"div h1 a"
,
"innerHtml"
),
xpath
(
"//title"
));
Assert
.
assertEquals
(
"aabbcc"
,
or
.
select
(
html
)
);
Assert
.
assertEquals
(
"<title>aabbcc</title>"
,
or
.
select
(
html2
)
);
assertThat
(
or
.
select
(
html
)).
isEqualTo
(
"aabbcc"
);
assertThat
(
or
.
select
(
html2
)).
isEqualTo
(
"<title>aabbcc</title>"
);
}
}
webmagic-core/src/test/java/us/codecraft/webmagic/selector/JsonPathSelectorTest.java
View file @
b1650904
package
us
.
codecraft
.
webmagic
.
selector
;
import
junit.framework.Assert
;
import
org.junit.Test
;
import
java.util.List
;
import
static
org
.
assertj
.
core
.
api
.
Assertions
.
assertThat
;
/**
* @author code4crafter@gmai.com <br>
*/
...
...
@@ -32,16 +33,16 @@ public class JsonPathSelectorTest {
"}"
;
@Test
public
void
test
()
{
public
void
test
JsonPath
()
{
JsonPathSelector
jsonPathSelector
=
new
JsonPathSelector
(
"$.store.book[*].author"
);
String
select
=
jsonPathSelector
.
select
(
text
);
List
<
String
>
list
=
jsonPathSelector
.
selectList
(
text
);
Assert
.
assertNotNull
(
select
);
Assert
.
assertNotNull
(
list
);
assertThat
(
select
).
isEqualTo
(
"Nigel Rees"
);
assertThat
(
list
).
contains
(
"Nigel Rees"
,
"Evelyn Waugh"
);
jsonPathSelector
=
new
JsonPathSelector
(
"$.store.book[?(@.category == 'reference')]"
);
list
=
jsonPathSelector
.
selectList
(
text
);
select
=
jsonPathSelector
.
select
(
text
);
Assert
.
assertNotNull
(
list
);
Assert
.
assertNotNull
(
select
);
assertThat
(
select
).
isEqualTo
(
"{\"author\":\"Nigel Rees\",\"title\":\"Sayings of the Century\",\"category\":\"reference\",\"price\":8.95}"
);
assertThat
(
list
).
contains
(
"{\"author\":\"Nigel Rees\",\"title\":\"Sayings of the Century\",\"category\":\"reference\",\"price\":8.95}"
);
}
}
webmagic-core/src/test/java/us/codecraft/webmagic/selector/RegexSelectorTest.java
View file @
b1650904
package
us
.
codecraft
.
webmagic
.
selector
;
import
org.
junit.Assert
;
import
org.
assertj.core.api.Assertions
;
import
org.junit.Test
;
/**
...
...
@@ -20,6 +20,6 @@ public class RegexSelectorTest {
String
source
=
"(hello world"
;
RegexSelector
regexSelector
=
new
RegexSelector
(
regex
);
String
select
=
regexSelector
.
select
(
source
);
Assert
.
assertEquals
(
source
,
select
);
Assert
ions
.
assertThat
(
select
).
isEqualTo
(
source
);
}
}
webmagic-core/src/test/java/us/codecraft/webmagic/utils/UrlUtilsTest.java
View file @
b1650904
...
...
@@ -49,11 +49,6 @@ public class UrlUtilsTest {
assertThat
(
replacedHtml
).
isEqualTo
(
"<a href=\"http://www.dianping.com/start\" tag>"
);
}
@Test
public
void
test
(){
UrlUtils
.
canonicalizeUrl
(
"start tag"
,
"http://www.dianping.com/"
);
}
@Test
public
void
testGetDomain
(){
String
url
=
"http://www.dianping.com/aa/"
;
...
...
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