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
d7cd9e57
Commit
d7cd9e57
authored
Sep 02, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update pom
parent
55d4a76a
Changes
6
Show whitespace changes
Inline
Side-by-side
Showing
6 changed files
with
23 additions
and
11 deletions
+23
-11
Html.java
...re/src/main/java/us/codecraft/webmagic/selector/Html.java
+1
-1
ExtractorUtils.java
...main/java/us/codecraft/webmagic/utils/ExtractorUtils.java
+3
-6
pom.xml
webmagic-samples/pom.xml
+1
-1
DiaoyuwengProcessor.java
...va/us/codecraft/webmagic/samples/DiaoyuwengProcessor.java
+6
-1
F58PageProcesser.java
.../java/us/codecraft/webmagic/samples/F58PageProcesser.java
+7
-2
HuxiuProcessor.java
...in/java/us/codecraft/webmagic/samples/HuxiuProcessor.java
+5
-0
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/selector/Html.java
View file @
d7cd9e57
...
...
@@ -59,7 +59,7 @@ public class Html extends PlainText {
@Override
public
Selectable
xpath
(
String
xpath
)
{
X
pathSelector
xpathSelector
=
Selectors
.
xpath
(
xpath
);
X
soupSelector
xpathSelector
=
new
XsoupSelector
(
xpath
);
return
selectList
(
xpathSelector
,
strings
);
}
...
...
webmagic-extension/src/main/java/us/codecraft/webmagic/utils/ExtractorUtils.java
View file @
d7cd9e57
package
us
.
codecraft
.
webmagic
.
utils
;
import
us.codecraft.webmagic.model.annotation.ExtractBy
;
import
us.codecraft.webmagic.selector.CssSelector
;
import
us.codecraft.webmagic.selector.RegexSelector
;
import
us.codecraft.webmagic.selector.Selector
;
import
us.codecraft.webmagic.selector.XpathSelector
;
import
us.codecraft.webmagic.selector.*
;
import
java.util.ArrayList
;
import
java.util.List
;
...
...
@@ -27,10 +24,10 @@ public class ExtractorUtils {
selector
=
new
RegexSelector
(
value
);
break
;
case
XPath:
selector
=
new
X
path
Selector
(
value
);
selector
=
new
X
soup
Selector
(
value
);
break
;
default
:
selector
=
new
X
path
Selector
(
value
);
selector
=
new
X
soup
Selector
(
value
);
}
return
selector
;
}
...
...
webmagic-samples/pom.xml
View file @
d7cd9e57
...
...
@@ -5,7 +5,7 @@
<parent>
<artifactId>
webmagic-parent
</artifactId>
<groupId>
us.codecraft
</groupId>
<version>
0.2.
1
</version>
<version>
0.2.
2-SNAPSHOT
</version>
</parent>
<modelVersion>
4.0.0
</modelVersion>
...
...
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/DiaoyuwengProcessor.java
View file @
d7cd9e57
...
...
@@ -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
us.codecraft.webmagic.selector.PlainText
;
...
...
@@ -24,7 +25,7 @@ public class DiaoyuwengProcessor implements PageProcessor {
page
.
addTargetRequests
(
requests
);
if
(
page
.
getUrl
().
toString
().
contains
(
"thread"
)){
page
.
putField
(
"title"
,
page
.
getHtml
().
xpath
(
"//a[@id='thread_subject']"
));
page
.
putField
(
"content"
,
page
.
getHtml
().
xpath
(
"//div[@class='pcb']//tbody"
));
page
.
putField
(
"content"
,
page
.
getHtml
().
xpath
(
"//div[@class='pcb']//tbody
/tidyText()
"
));
page
.
putField
(
"date"
,
page
.
getHtml
().
regex
(
"发表于 (\\d{4}-\\d+-\\d+ \\d+:\\d+:\\d+)"
));
page
.
putField
(
"id"
,
new
PlainText
(
"1000"
+
page
.
getUrl
().
regex
(
"http://www\\.diaoyuweng\\.com/thread-(\\d+)-1-1.html"
).
toString
()));
}
...
...
@@ -38,4 +39,8 @@ public class DiaoyuwengProcessor implements PageProcessor {
}
return
site
;
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
DiaoyuwengProcessor
()).
run
();
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/F58PageProcesser.java
View file @
d7cd9e57
...
...
@@ -2,6 +2,7 @@ package us.codecraft.webmagic.samples;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
java.util.List
;
...
...
@@ -15,14 +16,18 @@ public class F58PageProcesser implements PageProcessor {
@Override
public
void
process
(
Page
page
)
{
List
<
String
>
strings
=
page
.
getHtml
().
regex
(
"<a[^<>]*href=[\"']{1}(/yewu/.*?)[\"']{1}
"
).
all
();
List
<
String
>
strings
=
page
.
getHtml
().
links
().
regex
(
".*/yewu/.*
"
).
all
();
page
.
addTargetRequests
(
strings
);
page
.
putField
(
"title"
,
page
.
getHtml
().
regex
(
"<title>(.*)</title>"
));
page
.
putField
(
"body"
,
page
.
getHtml
().
xpath
(
"//dd
[@class='w133']
"
));
page
.
putField
(
"body"
,
page
.
getHtml
().
xpath
(
"//dd"
));
}
@Override
public
Site
getSite
()
{
return
Site
.
me
().
setDomain
(
"sh.58.com"
).
addStartUrl
(
"http://sh.58.com/"
);
//To change body of implemented methods use File | Settings | File Templates.
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
F58PageProcesser
()).
run
();
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/HuxiuProcessor.java
View file @
d7cd9e57
...
...
@@ -2,6 +2,7 @@ package us.codecraft.webmagic.samples;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
java.util.List
;
...
...
@@ -26,4 +27,8 @@ public class HuxiuProcessor implements PageProcessor {
return
Site
.
me
().
setDomain
(
"www.huxiu.com"
).
addStartUrl
(
"http://www.huxiu.com/"
).
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
HuxiuProcessor
()).
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