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
b1318781
Commit
b1318781
authored
Sep 23, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add example
parent
95ab4ede
Changes
8
Hide whitespace changes
Inline
Side-by-side
Showing
8 changed files
with
161 additions
and
20 deletions
+161
-20
GithubRepoPageProcesser.java
...t/webmagic/processor/example/GithubRepoPageProcesser.java
+36
-0
OschinaBlogPageProcesser.java
.../webmagic/processor/example/OschinaBlogPageProcesser.java
+39
-0
GithubRepo.java
...c/main/java/us/codecraft/webmagic/example/GithubRepo.java
+11
-2
OschinaBlog.java
.../main/java/us/codecraft/webmagic/example/OschinaBlog.java
+10
-15
PageModelExtractor.java
.../java/us/codecraft/webmagic/model/PageModelExtractor.java
+13
-2
DateFormatter.java
.../us/codecraft/webmagic/model/formatter/DateFormatter.java
+1
-1
DateFormatterTest.java
...va/us/codecraft/webmagic/formatter/DateFormatterTest.java
+20
-0
log4j.xml
webmagic-extension/src/test/resouces/log4j.xml
+31
-0
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/processor/example/GithubRepoPageProcesser.java
0 → 100644
View file @
b1318781
package
us
.
codecraft
.
webmagic
.
processor
.
example
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.processor.PageProcessor
;
/**
* @author code4crafter@gmail.com <br>
* @since 0.3.2
*/
public
class
GithubRepoPageProcesser
implements
PageProcessor
{
private
Site
site
=
Site
.
me
().
addStartUrl
(
"https://github.com/code4craft"
).
setRetryTimes
(
3
).
setSleepTime
(
100
);
@Override
public
void
process
(
Page
page
)
{
page
.
addTargetRequests
(
page
.
getHtml
().
links
().
regex
(
"(https://github\\.com/\\w+/\\w+)"
).
all
());
page
.
putField
(
"author"
,
page
.
getUrl
().
regex
(
"https://github\\.com/(\\w+)/.*"
).
toString
());
page
.
putField
(
"name"
,
page
.
getHtml
().
xpath
(
"//h1[@class='entry-title public']/strong/a/text()"
).
toString
());
if
(
page
.
getResultItems
().
get
(
"name"
)==
null
){
//skip this page
page
.
setSkip
(
true
);
}
page
.
putField
(
"readme"
,
page
.
getHtml
().
xpath
(
"//div[@id='readme']/tidyText()"
));
}
@Override
public
Site
getSite
()
{
return
site
;
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
GithubRepoPageProcesser
()).
thread
(
5
).
run
();
}
}
webmagic-core/src/main/java/us/codecraft/webmagic/processor/example/OschinaBlogPageProcesser.java
0 → 100644
View file @
b1318781
package
us
.
codecraft
.
webmagic
.
processor
.
example
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
java.util.List
;
/**
* @author code4crafter@gmail.com <br>
*/
public
class
OschinaBlogPageProcesser
implements
PageProcessor
{
private
Site
site
=
Site
.
me
().
setDomain
(
"my.oschina.net"
).
addStartUrl
(
"http://my.oschina.net/flashsword/blog"
);
@Override
public
void
process
(
Page
page
)
{
List
<
String
>
links
=
page
.
getHtml
().
links
().
regex
(
"http://my\\.oschina\\.net/flashsword/blog/\\d+"
).
all
();
page
.
addTargetRequests
(
links
);
page
.
putField
(
"title"
,
page
.
getHtml
().
xpath
(
"//div[@class='BlogEntity']/div[@class='BlogTitle']/h1/text()"
).
toString
());
if
(
page
.
getResultItems
().
get
(
"title"
)
==
null
)
{
//skip this page
page
.
setSkip
(
true
);
}
page
.
putField
(
"content"
,
page
.
getHtml
().
xpath
(
"//div[@class='BlogContent']/tidyText()"
).
toString
());
page
.
putField
(
"tags"
,
page
.
getHtml
().
xpath
(
"//div[@class='BlogTags']/a/text()"
).
all
());
}
@Override
public
Site
getSite
()
{
return
site
;
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
OschinaBlogPageProcesser
()).
thread
(
2
).
run
();
}
}
webmagic-extension/src/main/java/us/codecraft/webmagic/example/GithubRepo.java
View file @
b1318781
package
us
.
codecraft
.
webmagic
.
example
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.model.ConsolePageModelPipeline
;
import
us.codecraft.webmagic.model.HasKey
;
import
us.codecraft.webmagic.model.OOSpider
;
import
us.codecraft.webmagic.model.annotation.ExtractBy
;
import
us.codecraft.webmagic.model.annotation.ExtractByUrl
;
import
us.codecraft.webmagic.model.annotation.HelpUrl
;
...
...
@@ -10,6 +13,7 @@ import java.util.List;
/**
* @author code4crafter@gmail.com <br>
* @since 0.3.2
*/
@TargetUrl
(
"https://github.com/\\w+/\\w+"
)
@HelpUrl
({
"https://github.com/\\w+\\?tab=repositories"
,
"https://github.com/\\w+"
,
"https://github.com/explore/*"
})
...
...
@@ -27,15 +31,20 @@ public class GithubRepo implements HasKey {
@ExtractBy
(
value
=
"//div[@class='repository-lang-stats']//li//span[@class='lang']/text()"
,
multi
=
true
)
private
List
<
String
>
language
;
@ExtractBy
(
"//ul[@class='pagehead-actions']/li[
2
]//a[@class='social-count js-social-count']/text()"
)
@ExtractBy
(
"//ul[@class='pagehead-actions']/li[
1
]//a[@class='social-count js-social-count']/text()"
)
private
int
star
;
@ExtractBy
(
"//ul[@class='pagehead-actions']/li[
3
]//a[@class='social-count']/text()"
)
@ExtractBy
(
"//ul[@class='pagehead-actions']/li[
2
]//a[@class='social-count']/text()"
)
private
int
fork
;
@ExtractByUrl
private
String
url
;
public
static
void
main
(
String
[]
args
)
{
OOSpider
.
create
(
Site
.
me
().
addStartUrl
(
"https://github.com/code4craft"
).
setSleepTime
(
100
)
,
new
ConsolePageModelPipeline
(),
GithubRepo
.
class
).
thread
(
10
).
run
();
}
@Override
public
String
key
()
{
return
author
+
":"
+
name
;
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/example/OschinaBlog.java
View file @
b1318781
package
us
.
codecraft
.
webmagic
.
example
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.model.AfterExtractor
;
import
us.codecraft.webmagic.model.OOSpider
;
import
us.codecraft.webmagic.model.annotation.ExtractBy
;
import
us.codecraft.webmagic.model.annotation.Formatter
;
import
us.codecraft.webmagic.model.annotation.TargetUrl
;
import
us.codecraft.webmagic.pipeline.JsonFilePageModelPipeline
;
import
java.util.Date
;
import
java.util.List
;
/**
* @author code4crafter@gmail.com <br>
* @since 0.3.2
*/
@TargetUrl
(
"http://my.oschina.net/flashsword/blog/\\d+"
)
public
class
OschinaBlog
implements
AfterExtractor
{
public
class
OschinaBlog
{
@ExtractBy
(
"//title/text()"
)
private
String
title
;
@ExtractBy
(
value
=
"div.BlogContent"
,
type
=
ExtractBy
.
Type
.
Css
)
@ExtractBy
(
value
=
"div.BlogContent"
,
type
=
ExtractBy
.
Type
.
Css
)
private
String
content
;
@ExtractBy
(
value
=
"//div[@class='BlogTags']/a/text()"
,
multi
=
true
)
private
List
<
String
>
tags
;
@Formatter
(
"
YYYY
-MM-dd HH:mm"
)
@Formatter
(
"
yyyy
-MM-dd HH:mm"
)
@ExtractBy
(
"//div[@class='BlogStat']/regex('\\d+-\\d+-\\d+\\s+\\d+:\\d+')"
)
private
String
date
;
private
Date
date
;
public
static
void
main
(
String
[]
args
)
{
OOSpider
.
create
(
Site
.
me
().
addStartUrl
(
"http://my.oschina.net/flashsword/blog"
)
,
new
JsonFilePageModelPipeline
(
"/data/webmagic/"
),
OschinaBlog
.
class
).
run
();
,
new
JsonFilePageModelPipeline
(
"/data/webmagic/"
),
OschinaBlog
.
class
).
run
();
}
public
String
getTitle
()
{
...
...
@@ -47,13 +47,8 @@ public class OschinaBlog implements AfterExtractor{
return
tags
;
}
// public Date getDate() {
// return date;
// }
@Override
public
void
afterProcess
(
Page
page
)
{
System
.
out
.
println
(
date
);
System
.
out
.
println
(
title
);
public
Date
getDate
()
{
return
date
;
}
}
webmagic-extension/src/main/java/us/codecraft/webmagic/model/PageModelExtractor.java
View file @
b1318781
...
...
@@ -105,7 +105,8 @@ class PageModelExtractor {
Formatter
formatter
=
field
.
getAnnotation
(
Formatter
.
class
);
if
(
formatter
!=
null
)
{
if
(!
formatter
.
formatter
().
equals
(
ObjectFormatter
.
class
))
{
return
initFormatter
(
formatter
.
formatter
());
ObjectFormatter
objectFormatter
=
initFormatter
(
formatter
.
formatter
());
objectFormatter
.
initParam
(
formatter
.
value
());
}
}
return
initFormatter
(
ObjectFormatters
.
get
(
fieldClazz
));
...
...
@@ -311,6 +312,9 @@ class PageModelExtractor {
}
if
(
fieldExtractor
.
getObjectFormatter
()
!=
null
)
{
Object
converted
=
convert
(
value
,
fieldExtractor
.
getObjectFormatter
());
if
(
converted
==
null
&&
fieldExtractor
.
isNotNull
())
{
return
null
;
}
setField
(
o
,
fieldExtractor
,
converted
);
}
else
{
setField
(
o
,
fieldExtractor
,
value
);
...
...
@@ -332,7 +336,11 @@ class PageModelExtractor {
private
Object
convert
(
String
value
,
ObjectFormatter
objectFormatter
)
{
try
{
return
objectFormatter
.
format
(
value
);
Object
format
=
objectFormatter
.
format
(
value
);
if
(
logger
.
isDebugEnabled
())
{
logger
.
debug
(
"String "
+
value
+
" is converted to "
+
format
);
}
return
format
;
}
catch
(
Exception
e
)
{
logger
.
error
(
"convert "
+
value
+
" to "
+
objectFormatter
.
clazz
()
+
" error!"
,
e
);
}
...
...
@@ -351,6 +359,9 @@ class PageModelExtractor {
}
private
void
setField
(
Object
o
,
FieldExtractor
fieldExtractor
,
Object
value
)
throws
IllegalAccessException
,
InvocationTargetException
{
if
(
value
==
null
){
return
;
}
if
(
fieldExtractor
.
getSetterMethod
()
!=
null
)
{
fieldExtractor
.
getSetterMethod
().
invoke
(
o
,
value
);
}
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/model/formatter/DateFormatter.java
View file @
b1318781
...
...
@@ -10,7 +10,7 @@ import java.util.Date;
*/
public
class
DateFormatter
implements
ObjectFormatter
<
Date
>
{
private
String
[]
datePatterns
=
new
String
[]{
"
YYYY
-MM-dd HH:mm"
};
private
String
[]
datePatterns
=
new
String
[]{
"
yyyy
-MM-dd HH:mm"
};
@Override
public
Date
format
(
String
raw
)
throws
Exception
{
...
...
webmagic-extension/src/test/java/us/codecraft/webmagic/formatter/DateFormatterTest.java
0 → 100644
View file @
b1318781
package
us
.
codecraft
.
webmagic
.
formatter
;
import
org.junit.Test
;
import
us.codecraft.webmagic.model.formatter.DateFormatter
;
import
java.util.Date
;
/**
* @author code4crafter@gmail.com
*/
public
class
DateFormatterTest
{
@Test
public
void
testDateFormatter
()
throws
Exception
{
DateFormatter
dateFormatter
=
new
DateFormatter
();
dateFormatter
.
initParam
(
new
String
[]{
"yyyy-MM-dd HH:mm"
});
Date
format
=
dateFormatter
.
format
(
"2013-09-10 22:11"
);
System
.
out
.
println
(
format
);
}
}
webmagic-extension/src/test/resouces/log4j.xml
0 → 100644
View file @
b1318781
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE log4j:configuration SYSTEM "log4j.dtd">
<log4j:configuration
xmlns:log4j=
"http://jakarta.apache.org/log4j/"
>
<appender
name=
"stdout"
class=
"org.apache.log4j.ConsoleAppender"
>
<layout
class=
"org.apache.log4j.PatternLayout"
>
<param
name=
"ConversionPattern"
value=
"%d{yy-MM-dd HH:mm:ss,SSS} %-5p %c(%F:%L) ## %m%n"
/>
</layout>
</appender>
<logger
name=
"org.springframework"
additivity=
"false"
>
<level
value=
"warn"
/>
<appender-ref
ref=
"stdout"
/>
</logger>
<logger
name=
"org.apache"
additivity=
"false"
>
<level
value=
"warn"
/>
<appender-ref
ref=
"stdout"
/>
</logger>
<logger
name=
"net.sf.ehcache"
additivity=
"false"
>
<level
value=
"warn"
/>
<appender-ref
ref=
"stdout"
/>
</logger>
<root>
<level
value=
"debug"
/>
<appender-ref
ref=
"stdout"
/>
</root>
</log4j:configuration>
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