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
3d4ad02b
Commit
3d4ad02b
authored
Jun 10, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fix freemarker dir error
parent
412abeb8
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
49 additions
and
6 deletions
+49
-6
FreemarkerPipeline.java
...va/us/codecraft/webmagic/pipeline/FreemarkerPipeline.java
+4
-0
SinaBlogProcesser.java
...java/us/codecraft/webmagic/samples/SinaBlogProcesser.java
+11
-6
SinablogProcessorTest.java
...s/codecraft/webmagic/processor/SinablogProcessorTest.java
+34
-0
No files found.
webmagic-plugin/src/main/java/us/codecraft/webmagic/pipeline/FreemarkerPipeline.java
View file @
3d4ad02b
...
...
@@ -44,6 +44,10 @@ public class FreemarkerPipeline implements Pipeline {
String
domain
=
site
.
getDomain
();
domain
=
UrlUtils
.
getDomain
(
domain
);
String
path
=
this
.
path
+
""
+
domain
+
"/"
;
File
file
=
new
File
(
path
);
if
(!
file
.
exists
())
{
file
.
mkdir
();
}
try
{
PrintWriter
printWriter
=
new
PrintWriter
(
new
FileWriter
(
path
+
DigestUtils
.
md5Hex
(
page
.
getUrl
().
toString
())
+
".html"
));
template
.
process
(
page
.
getFields
(),
printWriter
);
...
...
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/SinaBlogProcesser.java
View file @
3d4ad02b
...
...
@@ -11,19 +11,24 @@ import us.codecraft.webmagic.processor.PageProcessor;
*/
public
class
SinaBlogProcesser
implements
PageProcessor
{
private
Site
site
;
@Override
public
void
process
(
Page
page
)
{
page
.
addTargetRequests
(
page
.
getHtml
().
rs
(
"<a[^<>]*href=[\"']{1}(http://blog\\.sina\\.com\\.cn/s/blog_.*?)[\"']{1}
"
).
toStrings
());
page
.
addTargetRequests
(
page
.
getHtml
().
as
().
rs
(
"(http://blog\\.sina\\.com\\.cn/s/blog_.*)
"
).
toStrings
());
page
.
putField
(
"title"
,
page
.
getHtml
().
x
(
"//div[@class='articalTitle']/h2"
));
page
.
putField
(
"
body"
,
page
.
getHtml
().
sc
(
));
//x("//dd[@class='w133']")
page
.
putField
(
"
content"
,
page
.
getHtml
().
x
(
"//div[@id='articlebody']//div[@class='articalContent']"
));
page
.
putField
(
"id"
,
page
.
getUrl
().
r
(
"http://blog\\.sina\\.com\\.cn/s/blog_(\\w+)"
));
page
.
putField
(
"date"
,
page
.
getHtml
().
x
(
"//div[@id='articlebody']//span[@class='time SG_txtc']"
).
r
(
"\\((.*)\\)"
));
page
.
putField
(
"tags"
,
page
.
getHtml
().
xs
(
"//td[@class='blog_tag']/h3/a"
));
//
page.putField("tags",page.getHtml().xs("//td[@class='blog_tag']/h3/a"));
}
@Override
public
Site
getSite
()
{
return
Site
.
me
().
setDomain
(
"blog.sina.com.cn"
).
setStartUrl
(
"http://blog.sina.com.cn/"
).
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"
);
if
(
site
==
null
){
site
=
Site
.
me
().
setDomain
(
"blog.sina.com.cn"
).
setStartUrl
(
"http://blog.sina.com.cn/flashsword20"
).
setSleepTime
(
3000
).
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
;
}
}
webmagic-samples/src/test/java/us/codecraft/webmagic/processor/SinablogProcessorTest.java
0 → 100644
View file @
3d4ad02b
package
us
.
codecraft
.
webmagic
.
processor
;
import
org.junit.Test
;
import
us.codecraft.webmagic.Spider
;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.pipeline.FreemarkerPipeline
;
import
us.codecraft.webmagic.samples.SinaBlogProcesser
;
import
us.codecraft.webmagic.schedular.FileCacheQueueSchedular
;
import
java.io.IOException
;
/**
* User: cairne
* Date: 13-6-9
* Time: 上午8:02
*/
public
class
SinablogProcessorTest
{
@Test
public
void
test
()
throws
IOException
{
SinaBlogProcesser
sinaBlogProcesser
=
new
SinaBlogProcesser
();
//pipeline是抓取结束后的处理
//ftl文件放到classpath:ftl/文件夹下
//默认放到/data/temp/webmagic/ftl/[domain]目录下
FreemarkerPipeline
pipeline
=
new
FreemarkerPipeline
(
"wordpress.ftl"
);
//Spider.me()是简化写法,其实就是new一个啦
//Spider.pipeline()设定一个pipeline,支持链式调用
//ConsolePipeline输出结果到控制台
//FileCacheQueueSchedular保存url,支持断点续传,临时文件输出到/data/temp/webmagic/cache目录
//Spider.run()执行
Spider
.
me
().
pipeline
(
new
FilePipeline
()).
pipeline
(
pipeline
).
schedular
(
new
FileCacheQueueSchedular
(
sinaBlogProcesser
.
getSite
(),
"/data/temp/webmagic/cache/"
)).
processor
(
sinaBlogProcesser
).
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