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
54904851
Commit
54904851
authored
Jul 26, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add list output support
parent
2bb6f847
Changes
3
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
74 additions
and
6 deletions
+74
-6
ConsolePipeline.java
.../java/us/codecraft/webmagic/pipeline/ConsolePipeline.java
+9
-0
FilePipeline.java
...ain/java/us/codecraft/webmagic/pipeline/FilePipeline.java
+16
-6
InfoQMiniBookProcessor.java
...us/codecraft/webmagic/samples/InfoQMiniBookProcessor.java
+49
-0
No files found.
webmagic-core/src/main/java/us/codecraft/webmagic/pipeline/ConsolePipeline.java
View file @
54904851
...
@@ -20,6 +20,15 @@ public class ConsolePipeline implements Pipeline{
...
@@ -20,6 +20,15 @@ public class ConsolePipeline implements Pipeline{
}
}
System
.
out
.
println
(
"get page: "
+
resultItems
.
getRequest
().
getUrl
());
System
.
out
.
println
(
"get page: "
+
resultItems
.
getRequest
().
getUrl
());
for
(
Map
.
Entry
<
String
,
Object
>
entry
:
resultItems
.
getAll
().
entrySet
())
{
for
(
Map
.
Entry
<
String
,
Object
>
entry
:
resultItems
.
getAll
().
entrySet
())
{
if
(
entry
.
getValue
()
instanceof
Iterable
)
{
Iterable
value
=
(
Iterable
)
entry
.
getValue
();
System
.
out
.
println
(
entry
.
getKey
()
+
":"
);
for
(
Object
o
:
value
)
{
System
.
out
.
println
(
o
);
}
}
else
{
System
.
out
.
println
(
entry
.
getKey
()
+
":\t"
+
entry
.
getValue
());
}
System
.
out
.
println
(
entry
.
getKey
()+
":\t"
+
entry
.
getValue
());
System
.
out
.
println
(
entry
.
getKey
()+
":\t"
+
entry
.
getValue
());
}
}
}
}
...
...
webmagic-core/src/main/java/us/codecraft/webmagic/pipeline/FilePipeline.java
View file @
54904851
...
@@ -13,6 +13,7 @@ import java.util.Map;
...
@@ -13,6 +13,7 @@ import java.util.Map;
/**
/**
* 持久化到文件的接口。
* 持久化到文件的接口。
*
* @author code4crafter@gmail.com <br>
* @author code4crafter@gmail.com <br>
* Date: 13-4-21
* Date: 13-4-21
* Time: 下午6:28
* Time: 下午6:28
...
@@ -32,6 +33,7 @@ public class FilePipeline implements Pipeline {
...
@@ -32,6 +33,7 @@ public class FilePipeline implements Pipeline {
/**
/**
* 新建一个FilePipeline
* 新建一个FilePipeline
*
* @param path 文件保存路径
* @param path 文件保存路径
*/
*/
public
FilePipeline
(
String
path
)
{
public
FilePipeline
(
String
path
)
{
...
@@ -45,18 +47,26 @@ public class FilePipeline implements Pipeline {
...
@@ -45,18 +47,26 @@ public class FilePipeline implements Pipeline {
if
(!
file
.
exists
())
{
if
(!
file
.
exists
())
{
file
.
mkdirs
();
file
.
mkdirs
();
}
}
if
(
resultItems
.
isSkip
()){
if
(
resultItems
.
isSkip
())
{
return
;
return
;
}
}
try
{
try
{
PrintWriter
printWriter
=
new
PrintWriter
(
new
FileWriter
(
path
+
DigestUtils
.
md5Hex
(
resultItems
.
getRequest
().
getUrl
())
+
".html"
));
PrintWriter
printWriter
=
new
PrintWriter
(
new
FileWriter
(
path
+
DigestUtils
.
md5Hex
(
resultItems
.
getRequest
().
getUrl
())
+
".html"
));
printWriter
.
println
(
"url:\t"
+
resultItems
.
getRequest
().
getUrl
());
printWriter
.
println
(
"url:\t"
+
resultItems
.
getRequest
().
getUrl
());
for
(
Map
.
Entry
<
String
,
Object
>
entry
:
resultItems
.
getAll
().
entrySet
())
{
for
(
Map
.
Entry
<
String
,
Object
>
entry
:
resultItems
.
getAll
().
entrySet
())
{
printWriter
.
println
(
entry
.
getKey
()+
":\t"
+
entry
.
getValue
());
if
(
entry
.
getValue
()
instanceof
Iterable
)
{
Iterable
value
=
(
Iterable
)
entry
.
getValue
();
printWriter
.
println
(
entry
.
getKey
()
+
":"
);
for
(
Object
o
:
value
)
{
printWriter
.
println
(
o
);
}
}
else
{
printWriter
.
println
(
entry
.
getKey
()
+
":\t"
+
entry
.
getValue
());
}
}
}
printWriter
.
close
();
printWriter
.
close
();
}
catch
(
IOException
e
)
{
}
catch
(
IOException
e
)
{
logger
.
warn
(
"write file error"
,
e
);
logger
.
warn
(
"write file error"
,
e
);
}
}
}
}
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/InfoQMiniBookProcessor.java
0 → 100644
View file @
54904851
package
us
.
codecraft
.
webmagic
.
samples
;
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
;
/**
* @author code4crafter@gmail.com <br>
* Date: 13-4-21
* Time: 下午8:08
*/
public
class
InfoQMiniBookProcessor
implements
PageProcessor
{
private
Site
site
;
@Override
public
void
process
(
Page
page
)
{
page
.
addTargetRequests
(
page
.
getHtml
().
links
().
regex
(
"http://www\\.infoq\\.com/cn/minibooks/.*"
).
all
());
List
<
String
>
all
=
page
.
getHtml
().
links
().
regex
(
".*\\.pdf"
).
all
();
if
(
CollectionUtils
.
isNotEmpty
(
all
))
{
page
.
putField
(
"pdf"
,
all
);
}
else
{
page
.
getResultItems
().
setSkip
(
true
);
}
}
@Override
public
Site
getSite
()
{
if
(
site
==
null
)
{
site
=
Site
.
me
().
setDomain
(
"www.infoq.com"
).
addStartUrl
(
"http://www.infoq.com/cn/minibooks"
).
addCookie
(
"RegisteredUserCookie"
,
"sDDDc8dIAgZSq67uJSXhtpQaHEi1XDOH"
).
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"
);
}
return
site
;
}
public
static
void
main
(
String
[]
args
)
{
Spider
.
create
(
new
InfoQMiniBookProcessor
())
.
scheduler
(
new
RedisScheduler
(
"localhost"
))
.
pipeline
(
new
FilePipeline
(
"/data/temp/webmagic/"
))
.
thread
(
5
)
.
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