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
95ab4ede
Commit
95ab4ede
authored
Sep 23, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
some bugfix
parent
250cc5e6
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
64 additions
and
9 deletions
+64
-9
Site.java
webmagic-core/src/main/java/us/codecraft/webmagic/Site.java
+5
-5
OschinaBlog.java
.../main/java/us/codecraft/webmagic/example/OschinaBlog.java
+59
-0
OschinaBlog.java
...java/us/codecraft/webmagic/model/samples/OschinaBlog.java
+0
-4
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/Site.java
View file @
95ab4ede
...
@@ -96,11 +96,6 @@ public class Site {
...
@@ -96,11 +96,6 @@ public class Site {
* @return get domain
* @return get domain
*/
*/
public
String
getDomain
()
{
public
String
getDomain
()
{
if
(
domain
==
null
)
{
if
(
startUrls
.
size
()
>
0
)
{
domain
=
UrlUtils
.
getDomain
(
startUrls
.
get
(
0
));
}
}
return
domain
;
return
domain
;
}
}
...
@@ -176,6 +171,11 @@ public class Site {
...
@@ -176,6 +171,11 @@ public class Site {
*/
*/
public
Site
addStartUrl
(
String
startUrl
)
{
public
Site
addStartUrl
(
String
startUrl
)
{
this
.
startUrls
.
add
(
startUrl
);
this
.
startUrls
.
add
(
startUrl
);
if
(
domain
==
null
)
{
if
(
startUrls
.
size
()
>
0
)
{
domain
=
UrlUtils
.
getDomain
(
startUrls
.
get
(
0
));
}
}
return
this
;
return
this
;
}
}
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/example/OschinaBlog.java
0 → 100644
View file @
95ab4ede
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.List
;
/**
* @author code4crafter@gmail.com <br>
*/
@TargetUrl
(
"http://my.oschina.net/flashsword/blog/\\d+"
)
public
class
OschinaBlog
implements
AfterExtractor
{
@ExtractBy
(
"//title/text()"
)
private
String
title
;
@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"
)
@ExtractBy
(
"//div[@class='BlogStat']/regex('\\d+-\\d+-\\d+\\s+\\d+:\\d+')"
)
private
String
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
();
}
public
String
getTitle
()
{
return
title
;
}
public
String
getContent
()
{
return
content
;
}
public
List
<
String
>
getTags
()
{
return
tags
;
}
// public Date getDate() {
// return date;
// }
@Override
public
void
afterProcess
(
Page
page
)
{
System
.
out
.
println
(
date
);
System
.
out
.
println
(
title
);
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/model/samples/OschinaBlog.java
View file @
95ab4ede
...
@@ -6,7 +6,6 @@ import us.codecraft.webmagic.model.annotation.ExtractBy;
...
@@ -6,7 +6,6 @@ import us.codecraft.webmagic.model.annotation.ExtractBy;
import
us.codecraft.webmagic.model.annotation.TargetUrl
;
import
us.codecraft.webmagic.model.annotation.TargetUrl
;
import
us.codecraft.webmagic.pipeline.JsonFilePageModelPipeline
;
import
us.codecraft.webmagic.pipeline.JsonFilePageModelPipeline
;
import
java.util.Date
;
import
java.util.List
;
import
java.util.List
;
/**
/**
...
@@ -24,9 +23,6 @@ public class OschinaBlog{
...
@@ -24,9 +23,6 @@ public class OschinaBlog{
@ExtractBy
(
value
=
"//div[@class='BlogTags']/a/text()"
,
multi
=
true
)
@ExtractBy
(
value
=
"//div[@class='BlogTags']/a/text()"
,
multi
=
true
)
private
List
<
String
>
tags
;
private
List
<
String
>
tags
;
@ExtractBy
(
"//div[class='BlogStat']/regex('\\d{4}-\\d{1,2}-\\d{1,2} \\d{1,2}:\\d{1,2}')"
)
private
Date
date
;
public
static
void
main
(
String
[]
args
)
{
public
static
void
main
(
String
[]
args
)
{
OOSpider
.
create
(
Site
.
me
().
addStartUrl
(
"http://my.oschina.net/flashsword/blog"
)
OOSpider
.
create
(
Site
.
me
().
addStartUrl
(
"http://my.oschina.net/flashsword/blog"
)
,
new
JsonFilePageModelPipeline
(),
OschinaBlog
.
class
).
run
();
,
new
JsonFilePageModelPipeline
(),
OschinaBlog
.
class
).
run
();
...
...
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