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
700898fe
Commit
700898fe
authored
Aug 29, 2016
by
郭玉昆
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fixed #301 修复使用注解抽取JSON数据的问题
parent
e22d6426
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
32 additions
and
8 deletions
+32
-8
GithubRepoApi.java
...ain/java/us/codecraft/webmagic/example/GithubRepoApi.java
+5
-5
Extractor.java
.../src/main/java/us/codecraft/webmagic/model/Extractor.java
+1
-1
PageModelExtractor.java
.../java/us/codecraft/webmagic/model/PageModelExtractor.java
+24
-1
ExtractBy.java
...ava/us/codecraft/webmagic/model/annotation/ExtractBy.java
+2
-1
No files found.
webmagic-extension/src/main/java/us/codecraft/webmagic/example/GithubRepoApi.java
View file @
700898fe
...
@@ -15,19 +15,19 @@ import java.util.List;
...
@@ -15,19 +15,19 @@ import java.util.List;
*/
*/
public
class
GithubRepoApi
implements
HasKey
{
public
class
GithubRepoApi
implements
HasKey
{
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.name"
)
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.name"
,
source
=
ExtractBy
.
Source
.
RawText
)
private
String
name
;
private
String
name
;
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$..owner.login"
)
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$..owner.login"
,
source
=
ExtractBy
.
Source
.
RawText
)
private
String
author
;
private
String
author
;
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.language"
,
multi
=
true
)
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.language"
,
multi
=
true
,
source
=
ExtractBy
.
Source
.
RawText
)
private
List
<
String
>
language
;
private
List
<
String
>
language
;
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.stargazers_count"
)
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.stargazers_count"
,
source
=
ExtractBy
.
Source
.
RawText
)
private
int
star
;
private
int
star
;
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.
homepage"
)
@ExtractBy
(
type
=
ExtractBy
.
Type
.
JsonPath
,
value
=
"$.
forks_count"
,
source
=
ExtractBy
.
Source
.
RawText
)
private
int
fork
;
private
int
fork
;
@ExtractByUrl
@ExtractByUrl
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/model/Extractor.java
View file @
700898fe
...
@@ -17,7 +17,7 @@ class Extractor {
...
@@ -17,7 +17,7 @@ class Extractor {
protected
final
boolean
multi
;
protected
final
boolean
multi
;
static
enum
Source
{
Html
,
Url
,
RawHtml
}
static
enum
Source
{
Html
,
Url
,
RawHtml
,
RawText
}
public
Extractor
(
Selector
selector
,
Source
source
,
boolean
notNull
,
boolean
multi
)
{
public
Extractor
(
Selector
selector
,
Source
source
,
boolean
notNull
,
boolean
multi
)
{
this
.
selector
=
selector
;
this
.
selector
=
selector
;
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/model/PageModelExtractor.java
View file @
700898fe
...
@@ -179,7 +179,24 @@ class PageModelExtractor {
...
@@ -179,7 +179,24 @@ class PageModelExtractor {
ExtractBy
extractBy
=
field
.
getAnnotation
(
ExtractBy
.
class
);
ExtractBy
extractBy
=
field
.
getAnnotation
(
ExtractBy
.
class
);
if
(
extractBy
!=
null
)
{
if
(
extractBy
!=
null
)
{
Selector
selector
=
ExtractorUtils
.
getSelector
(
extractBy
);
Selector
selector
=
ExtractorUtils
.
getSelector
(
extractBy
);
fieldExtractor
=
new
FieldExtractor
(
field
,
selector
,
extractBy
.
source
()
==
ExtractBy
.
Source
.
RawHtml
?
FieldExtractor
.
Source
.
RawHtml
:
FieldExtractor
.
Source
.
Html
,
FieldExtractor
.
Source
source
=
null
;
switch
(
extractBy
.
source
()){
case
RawText:
source
=
FieldExtractor
.
Source
.
RawText
;
break
;
case
RawHtml:
source
=
FieldExtractor
.
Source
.
RawHtml
;
break
;
case
SelectedHtml:
source
=
FieldExtractor
.
Source
.
Html
;
break
;
default
:
source
=
FieldExtractor
.
Source
.
Html
;
}
fieldExtractor
=
new
FieldExtractor
(
field
,
selector
,
source
,
extractBy
.
notNull
(),
extractBy
.
multi
()
||
List
.
class
.
isAssignableFrom
(
field
.
getType
()));
extractBy
.
notNull
(),
extractBy
.
multi
()
||
List
.
class
.
isAssignableFrom
(
field
.
getType
()));
Method
setterMethod
=
getSetterMethod
(
clazz
,
field
);
Method
setterMethod
=
getSetterMethod
(
clazz
,
field
);
if
(
setterMethod
!=
null
)
{
if
(
setterMethod
!=
null
)
{
...
@@ -284,6 +301,9 @@ class PageModelExtractor {
...
@@ -284,6 +301,9 @@ class PageModelExtractor {
case
Url:
case
Url:
value
=
fieldExtractor
.
getSelector
().
selectList
(
page
.
getUrl
().
toString
());
value
=
fieldExtractor
.
getSelector
().
selectList
(
page
.
getUrl
().
toString
());
break
;
break
;
case
RawText:
value
=
fieldExtractor
.
getSelector
().
selectList
(
page
.
getRawText
());
break
;
default
:
default
:
value
=
fieldExtractor
.
getSelector
().
selectList
(
html
);
value
=
fieldExtractor
.
getSelector
().
selectList
(
html
);
}
}
...
@@ -312,6 +332,9 @@ class PageModelExtractor {
...
@@ -312,6 +332,9 @@ class PageModelExtractor {
case
Url:
case
Url:
value
=
fieldExtractor
.
getSelector
().
select
(
page
.
getUrl
().
toString
());
value
=
fieldExtractor
.
getSelector
().
select
(
page
.
getUrl
().
toString
());
break
;
break
;
case
RawText:
value
=
fieldExtractor
.
getSelector
().
select
(
page
.
getRawText
());
break
;
default
:
default
:
value
=
fieldExtractor
.
getSelector
().
select
(
html
);
value
=
fieldExtractor
.
getSelector
().
select
(
html
);
}
}
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/model/annotation/ExtractBy.java
View file @
700898fe
...
@@ -52,7 +52,8 @@ public @interface ExtractBy {
...
@@ -52,7 +52,8 @@ public @interface ExtractBy {
/**
/**
* extract from the raw html
* extract from the raw html
*/
*/
RawHtml
RawHtml
,
RawText
}
}
/**
/**
...
...
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