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
8b7e6a35
Commit
8b7e6a35
authored
Aug 06, 2013
by
yihua.huang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add test case back
parent
ac917039
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
134 additions
and
1 deletion
+134
-1
SeleniumTest.java
...t/java/us/codecraft/webmagic/downloader/SeleniumTest.java
+41
-0
SeleniumDownloaderTest.java
.../webmagic/downloader/selenium/SeleniumDownloaderTest.java
+61
-0
WebDriverPoolTest.java
...craft/webmagic/downloader/selenium/WebDriverPoolTest.java
+31
-0
HuabanProcessor.java
...n/java/us/codecraft/webmagic/samples/HuabanProcessor.java
+1
-1
No files found.
webmagic-plugin/webmagic-misc/src/test/java/us/codecraft/webmagic/downloader/SeleniumTest.java
0 → 100644
View file @
8b7e6a35
package
us
.
codecraft
.
webmagic
.
downloader
;
import
org.junit.Ignore
;
import
org.junit.Test
;
import
org.openqa.selenium.By
;
import
org.openqa.selenium.WebDriver
;
import
org.openqa.selenium.WebElement
;
import
org.openqa.selenium.chrome.ChromeDriver
;
import
org.openqa.selenium.remote.DesiredCapabilities
;
import
java.util.Arrays
;
import
java.util.HashMap
;
import
java.util.Map
;
/**
* @author code4crafter@gmail.com <br>
* @date: 13-7-26 <br>
* Time: 下午12:27 <br>
*/
public
class
SeleniumTest
{
@Ignore
(
"need chrome driver"
)
@Test
public
void
testSelenium
()
{
System
.
getProperties
().
setProperty
(
"webdriver.chrome.driver"
,
"/Users/yihua/Downloads/chromedriver"
);
Map
<
String
,
Object
>
contentSettings
=
new
HashMap
<
String
,
Object
>();
contentSettings
.
put
(
"images"
,
2
);
Map
<
String
,
Object
>
preferences
=
new
HashMap
<
String
,
Object
>();
preferences
.
put
(
"profile.default_content_settings"
,
contentSettings
);
DesiredCapabilities
caps
=
DesiredCapabilities
.
chrome
();
caps
.
setCapability
(
"chrome.prefs"
,
preferences
);
caps
.
setCapability
(
"chrome.switches"
,
Arrays
.
asList
(
"--user-data-dir=/Users/yihua/temp/chrome"
));
WebDriver
webDriver
=
new
ChromeDriver
(
caps
);
webDriver
.
get
(
"http://huaban.com/"
);
WebElement
webElement
=
webDriver
.
findElement
(
By
.
xpath
(
"/html"
));
System
.
out
.
println
(
webElement
.
getAttribute
(
"outerHTML"
));
webDriver
.
close
();
}
}
webmagic-plugin/webmagic-misc/src/test/java/us/codecraft/webmagic/downloader/selenium/SeleniumDownloaderTest.java
0 → 100644
View file @
8b7e6a35
package
us
.
codecraft
.
webmagic
.
downloader
.
selenium
;
import
org.junit.Ignore
;
import
org.junit.Test
;
import
us.codecraft.webmagic.Page
;
import
us.codecraft.webmagic.Request
;
import
us.codecraft.webmagic.Site
;
import
us.codecraft.webmagic.Task
;
/**
* @author code4crafter@gmail.com <br>
* @date: 13-7-26 <br>
* Time: 下午2:46 <br>
*/
public
class
SeleniumDownloaderTest
{
private
String
chromeDriverPath
=
"/Users/yihua/Downloads/chromedriver"
;
@Ignore
(
"need chrome driver"
)
@Test
public
void
test
()
{
SeleniumDownloader
seleniumDownloader
=
new
SeleniumDownloader
(
chromeDriverPath
);
long
time1
=
System
.
currentTimeMillis
();
for
(
int
i
=
0
;
i
<
100
;
i
++)
{
Page
page
=
seleniumDownloader
.
download
(
new
Request
(
"http://huaban.com/"
),
new
Task
()
{
@Override
public
String
getUUID
()
{
return
"huaban.com"
;
}
@Override
public
Site
getSite
()
{
return
Site
.
me
();
}
});
System
.
out
.
println
(
page
.
getHtml
().
$
(
"#waterfall"
).
links
().
regex
(
".*pins.*"
).
all
());
}
System
.
out
.
println
(
System
.
currentTimeMillis
()
-
time1
);
}
@Ignore
@Test
public
void
testBaiduWenku
()
{
SeleniumDownloader
seleniumDownloader
=
new
SeleniumDownloader
(
chromeDriverPath
);
seleniumDownloader
.
setSleepTime
(
10000
);
long
time1
=
System
.
currentTimeMillis
();
Page
page
=
seleniumDownloader
.
download
(
new
Request
(
"http://wenku.baidu.com/view/462933ff04a1b0717fd5ddc2.html"
),
new
Task
()
{
@Override
public
String
getUUID
()
{
return
"huaban.com"
;
}
@Override
public
Site
getSite
()
{
return
Site
.
me
();
}
});
System
.
out
.
println
(
page
.
getHtml
().
$
(
"div.inner"
).
replace
(
"<[^<>]+>"
,
""
).
replace
(
"&nsbp;"
,
""
).
all
());
}
}
webmagic-plugin/webmagic-misc/src/test/java/us/codecraft/webmagic/downloader/selenium/WebDriverPoolTest.java
0 → 100644
View file @
8b7e6a35
package
us
.
codecraft
.
webmagic
.
downloader
.
selenium
;
import
org.junit.Ignore
;
import
org.junit.Test
;
import
org.openqa.selenium.WebDriver
;
/**
* @author code4crafter@gmail.com <br>
* @date: 13-7-26 <br>
* Time: 下午2:12 <br>
*/
public
class
WebDriverPoolTest
{
private
String
chromeDriverPath
=
"/Users/yihua/Downloads/chromedriver"
;
@Ignore
(
"need chrome driver"
)
@Test
public
void
test
()
{
System
.
getProperties
().
setProperty
(
"webdriver.chrome.driver"
,
chromeDriverPath
);
WebDriverPool
webDriverPool
=
new
WebDriverPool
(
5
);
for
(
int
i
=
0
;
i
<
5
;
i
++)
{
try
{
WebDriver
webDriver
=
webDriverPool
.
get
();
System
.
out
.
println
(
i
);
}
catch
(
InterruptedException
e
)
{
e
.
printStackTrace
();
}
}
webDriverPool
.
closeAll
();
}
}
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/HuabanProcessor.java
View file @
8b7e6a35
...
@@ -6,7 +6,7 @@ import us.codecraft.webmagic.Spider;
...
@@ -6,7 +6,7 @@ import us.codecraft.webmagic.Spider;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.pipeline.FilePipeline
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
us.codecraft.webmagic.processor.PageProcessor
;
import
us.codecraft.webmagic.scheduler.RedisScheduler
;
import
us.codecraft.webmagic.scheduler.RedisScheduler
;
import
us.codecraft.webmagic.
selenium
.downloader.SeleniumDownloader
;
import
us.codecraft.webmagic.
downloader
.downloader.SeleniumDownloader
;
/**
/**
* 花瓣网抽取器。<br>
* 花瓣网抽取器。<br>
...
...
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