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
85b7cf15
Commit
85b7cf15
authored
Sep 02, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
complete test
parent
d7cd9e57
Changes
7
Hide whitespace changes
Inline
Side-by-side
Showing
7 changed files
with
20 additions
and
17 deletions
+20
-17
Html.java
...re/src/main/java/us/codecraft/webmagic/selector/Html.java
+1
-1
HuxiuProcessor.java
...in/java/us/codecraft/webmagic/samples/HuxiuProcessor.java
+2
-3
InfoQMiniBookProcessor.java
...us/codecraft/webmagic/samples/InfoQMiniBookProcessor.java
+0
-4
IteyeBlogProcessor.java
...ava/us/codecraft/webmagic/samples/IteyeBlogProcessor.java
+1
-2
KaichibaProcessor.java
...java/us/codecraft/webmagic/samples/KaichibaProcessor.java
+5
-0
MeicanProcessor.java
...n/java/us/codecraft/webmagic/samples/MeicanProcessor.java
+7
-2
OschinaBlogPageProcesser.java
.../codecraft/webmagic/samples/OschinaBlogPageProcesser.java
+4
-5
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/selector/Html.java
View file @
85b7cf15
...
...
@@ -53,7 +53,7 @@ public class Html extends PlainText {
@Override
public
Selectable
links
()
{
X
pathSelector
xpathSelector
=
Selectors
.
xpath
(
"//a/@href"
);
X
soupSelector
xpathSelector
=
new
XsoupSelector
(
"//a/@href"
);
return
selectList
(
xpathSelector
,
strings
);
}
...
...
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/HuxiuProcessor.java
View file @
85b7cf15
...
...
@@ -15,10 +15,9 @@ import java.util.List;
public
class
HuxiuProcessor
implements
PageProcessor
{
@Override
public
void
process
(
Page
page
)
{
//http://progressdaily.diandian.com/post/2013-01-24/40046867275
List
<
String
>
requests
=
page
.
getHtml
().
regex
(
"<a[^<>\"']*href=[\"']{1}([/]{0,1}article[^<>#\"']*?)[\"']{1}"
).
all
();
List
<
String
>
requests
=
page
.
getHtml
().
links
().
regex
(
".*article.*"
).
all
();
page
.
addTargetRequests
(
requests
);
page
.
putField
(
"title"
,
page
.
getHtml
().
xpath
(
"//div[@class='
neirong']//h1[@class='ph xs5']
"
));
page
.
putField
(
"title"
,
page
.
getHtml
().
xpath
(
"//div[@class='
clearfix neirong']//h1/text()
"
));
page
.
putField
(
"content"
,
page
.
getHtml
().
smartContent
());
}
...
...
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/InfoQMiniBookProcessor.java
View file @
85b7cf15
...
...
@@ -4,9 +4,7 @@ import org.apache.commons.collections.CollectionUtils;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
us.codecraft.webmagic.scheduler.RedisScheduler
;
import
java.util.List
;
...
...
@@ -41,8 +39,6 @@ public class InfoQMiniBookProcessor implements PageProcessor {
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
InfoQMiniBookProcessor
())
.
scheduler
(
new
RedisScheduler
(
"localhost"
))
.
pipeline
(
new
FilePipeline
(
"/data/temp/webmagic/"
))
.
thread
(
5
)
.
run
();
}
...
...
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/IteyeBlogProcessor.java
View file @
85b7cf15
...
...
@@ -3,7 +3,6 @@ package us.codecraft.webmagic.samples;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.processor.PageProcessor
;
/**
...
...
@@ -32,6 +31,6 @@ public class IteyeBlogProcessor implements PageProcessor {
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
IteyeBlogProcessor
()).
thread
(
5
).
pipeline
(
new
FilePipeline
(
"/data/webmagic/"
)).
run
();
Spider
.
create
(
new
IteyeBlogProcessor
()).
thread
(
5
).
run
();
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/KaichibaProcessor.java
View file @
85b7cf15
...
...
@@ -2,6 +2,7 @@ package us.codecraft.webmagic.samples;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.processor.PageProcessor
;
/**
...
...
@@ -24,4 +25,8 @@ public class KaichibaProcessor implements PageProcessor {
return
Site
.
me
().
setDomain
(
"kaichiba.com"
).
addStartUrl
(
"http://kaichiba.com/shop/41725781"
).
setCharset
(
"utf-8"
).
setUserAgent
(
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31"
);
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
KaichibaProcessor
()).
run
();
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/MeicanProcessor.java
View file @
85b7cf15
...
...
@@ -2,6 +2,7 @@ package us.codecraft.webmagic.samples;
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
;
...
...
@@ -21,8 +22,8 @@ public class MeicanProcessor implements PageProcessor {
}
page
.
addTargetRequests
(
requests
);
page
.
addTargetRequests
(
page
.
getHtml
().
links
().
regex
(
"(.*/restaurant/[^#]+)"
).
all
());
page
.
putField
(
"items"
,
page
.
getHtml
().
xpath
(
"//ul[@class=\"dishes menu_dishes\"]/li/span[@class=\"name\"]"
));
page
.
putField
(
"prices"
,
page
.
getHtml
().
xpath
(
"//ul[@class=\"dishes menu_dishes\"]/li/span[@class=\"price_outer\"]/span[@class=\"price\"]"
));
page
.
putField
(
"items"
,
page
.
getHtml
().
xpath
(
"//ul[@class=\"dishes menu_dishes\"]/li/span[@class=\"name\"]
/text()
"
));
page
.
putField
(
"prices"
,
page
.
getHtml
().
xpath
(
"//ul[@class=\"dishes menu_dishes\"]/li/span[@class=\"price_outer\"]/span[@class=\"price\"]
/text()
"
));
}
@Override
...
...
@@ -30,4 +31,8 @@ public class MeicanProcessor implements PageProcessor {
return
Site
.
me
().
setDomain
(
"meican.com"
).
addStartUrl
(
"http://www.meican.com/shanghai/districts"
).
setCharset
(
"utf-8"
).
setUserAgent
(
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31"
);
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
MeicanProcessor
()).
run
();
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/OschinaBlogPageProcesser.java
View file @
85b7cf15
package
us
.
codecraft
.
webmagic
.
samples
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.pipeline.ConsolePipeline
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
java.util.List
;
...
...
@@ -21,8 +20,8 @@ public class OschinaBlogPageProcesser implements PageProcessor {
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"
).
toString
());
page
.
putField
(
"content"
,
page
.
getHtml
().
$
(
"div.content
"
).
toString
());
page
.
putField
(
"title"
,
page
.
getHtml
().
xpath
(
"//div[@class='BlogEntity']/div[@class='BlogTitle']/h1
/text()
"
).
toString
());
page
.
putField
(
"content"
,
page
.
getHtml
().
xpath
(
"//div[@class='BlogContent']/tidyText()
"
).
toString
());
page
.
putField
(
"tags"
,
page
.
getHtml
().
xpath
(
"//div[@class='BlogTags']/a/text()"
).
all
());
}
...
...
@@ -33,6 +32,6 @@ public class OschinaBlogPageProcesser implements PageProcessor {
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
OschinaBlogPageProcesser
()).
pipeline
(
new
ConsolePipeline
()).
run
();
Spider
.
create
(
new
OschinaBlogPageProcesser
()).
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