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
f1d5e297
Commit
f1d5e297
authored
Nov 12, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add scripts
parent
4cd3e1d8
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
16 additions
and
3 deletions
+16
-3
ScriptProcessor.java
...n/java/us/codecraft/webmagic/scripts/ScriptProcessor.java
+15
-0
oschina.rb
webmagic-scripts/src/main/resources/ruby/oschina.rb
+1
-3
No files found.
webmagic-scripts/src/main/java/us/codecraft/webmagic/scripts/ScriptProcessor.java
View file @
f1d5e297
package
us
.
codecraft
.
webmagic
.
scripts
;
import
org.apache.commons.io.IOUtils
;
import
sun.org.mozilla.javascript.internal.NativeObject
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.processor.PageProcessor
;
...
...
@@ -11,6 +12,7 @@ import javax.script.ScriptEngineManager;
import
javax.script.ScriptException
;
import
java.io.IOException
;
import
java.io.InputStream
;
import
java.util.Map
;
/**
* @author code4crafter@gmail.com
...
...
@@ -51,6 +53,19 @@ public class ScriptProcessor implements PageProcessor {
context
.
setAttribute
(
"config"
,
site
,
ScriptContext
.
ENGINE_SCOPE
);
try
{
engine
.
eval
(
defines
+
"\n"
+
script
,
context
);
switch
(
language
)
{
case
JavaScript:
NativeObject
o
=
(
NativeObject
)
engine
.
get
(
"result"
);
if
(
o
!=
null
)
{
for
(
Map
.
Entry
<
Object
,
Object
>
objectObjectEntry
:
o
.
entrySet
())
{
page
.
getResultItems
().
put
(
objectObjectEntry
.
getKey
().
toString
(),
objectObjectEntry
.
getValue
());
}
}
break
;
case
JRuby:
Object
o1
=
engine
.
get
(
"result"
);
break
;
}
}
catch
(
ScriptException
e
)
{
e
.
printStackTrace
();
}
...
...
webmagic-scripts/src/main/resources/ruby/oschina.rb
View file @
f1d5e297
title
=
css
"div.BlogTitle h1"
content
=
css
"div.BlogContent"
urls
"http://my
\\
.oschina
\\
.net/flashsword/blog/
\\
d+"
puts
title
puts
content
\ No newline at end of file
urls
"http://my
\\
.oschina
\\
.net/flashsword/blog/
\\
d+"
\ No newline at end of file
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