add example
parent
95ab4edec3
commit
b131878123
@ -0,0 +1,36 @@
|
||||
package us.codecraft.webmagic.processor.example;
|
||||
|
||||
import us.codecraft.webmagic.Page;
|
||||
import us.codecraft.webmagic.Site;
|
||||
import us.codecraft.webmagic.Spider;
|
||||
import us.codecraft.webmagic.processor.PageProcessor;
|
||||
|
||||
/**
|
||||
* @author code4crafter@gmail.com <br>
|
||||
* @since 0.3.2
|
||||
*/
|
||||
public class GithubRepoPageProcesser implements PageProcessor {
|
||||
|
||||
private Site site = Site.me().addStartUrl("https://github.com/code4craft").setRetryTimes(3).setSleepTime(100);
|
||||
|
||||
@Override
|
||||
public void process(Page page) {
|
||||
page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/\\w+/\\w+)").all());
|
||||
page.putField("author", page.getUrl().regex("https://github\\.com/(\\w+)/.*").toString());
|
||||
page.putField("name", page.getHtml().xpath("//h1[@class='entry-title public']/strong/a/text()").toString());
|
||||
if (page.getResultItems().get("name")==null){
|
||||
//skip this page
|
||||
page.setSkip(true);
|
||||
}
|
||||
page.putField("readme", page.getHtml().xpath("//div[@id='readme']/tidyText()"));
|
||||
}
|
||||
|
||||
@Override
|
||||
public Site getSite() {
|
||||
return site;
|
||||
}
|
||||
|
||||
public static void main(String[] args) {
|
||||
Spider.create(new GithubRepoPageProcesser()).thread(5).run();
|
||||
}
|
||||
}
|
@ -0,0 +1,39 @@
|
||||
package us.codecraft.webmagic.processor.example;
|
||||
|
||||
import us.codecraft.webmagic.Page;
|
||||
import us.codecraft.webmagic.Site;
|
||||
import us.codecraft.webmagic.Spider;
|
||||
import us.codecraft.webmagic.processor.PageProcessor;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* @author code4crafter@gmail.com <br>
|
||||
*/
|
||||
public class OschinaBlogPageProcesser implements PageProcessor {
|
||||
|
||||
private Site site = Site.me().setDomain("my.oschina.net").addStartUrl("http://my.oschina.net/flashsword/blog");
|
||||
|
||||
@Override
|
||||
public void process(Page page) {
|
||||
List<String> links = page.getHtml().links().regex("http://my\\.oschina\\.net/flashsword/blog/\\d+").all();
|
||||
page.addTargetRequests(links);
|
||||
page.putField("title", page.getHtml().xpath("//div[@class='BlogEntity']/div[@class='BlogTitle']/h1/text()").toString());
|
||||
if (page.getResultItems().get("title") == null) {
|
||||
//skip this page
|
||||
page.setSkip(true);
|
||||
}
|
||||
page.putField("content", page.getHtml().xpath("//div[@class='BlogContent']/tidyText()").toString());
|
||||
page.putField("tags", page.getHtml().xpath("//div[@class='BlogTags']/a/text()").all());
|
||||
}
|
||||
|
||||
@Override
|
||||
public Site getSite() {
|
||||
return site;
|
||||
|
||||
}
|
||||
|
||||
public static void main(String[] args) {
|
||||
Spider.create(new OschinaBlogPageProcesser()).thread(2).run();
|
||||
}
|
||||
}
|
@ -0,0 +1,20 @@
|
||||
package us.codecraft.webmagic.formatter;
|
||||
|
||||
import org.junit.Test;
|
||||
import us.codecraft.webmagic.model.formatter.DateFormatter;
|
||||
|
||||
import java.util.Date;
|
||||
|
||||
/**
|
||||
* @author code4crafter@gmail.com
|
||||
*/
|
||||
public class DateFormatterTest {
|
||||
|
||||
@Test
|
||||
public void testDateFormatter() throws Exception {
|
||||
DateFormatter dateFormatter = new DateFormatter();
|
||||
dateFormatter.initParam(new String[]{"yyyy-MM-dd HH:mm"});
|
||||
Date format = dateFormatter.format("2013-09-10 22:11");
|
||||
System.out.println(format);
|
||||
}
|
||||
}
|
@ -0,0 +1,31 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE log4j:configuration SYSTEM "log4j.dtd">
|
||||
<log4j:configuration xmlns:log4j="http://jakarta.apache.org/log4j/">
|
||||
|
||||
<appender name="stdout" class="org.apache.log4j.ConsoleAppender">
|
||||
<layout class="org.apache.log4j.PatternLayout">
|
||||
<param name="ConversionPattern" value="%d{yy-MM-dd HH:mm:ss,SSS} %-5p %c(%F:%L) ## %m%n" />
|
||||
</layout>
|
||||
</appender>
|
||||
|
||||
<logger name="org.springframework" additivity="false">
|
||||
<level value="warn" />
|
||||
<appender-ref ref="stdout" />
|
||||
</logger>
|
||||
|
||||
<logger name="org.apache" additivity="false">
|
||||
<level value="warn" />
|
||||
<appender-ref ref="stdout" />
|
||||
</logger>
|
||||
|
||||
<logger name="net.sf.ehcache" additivity="false">
|
||||
<level value="warn" />
|
||||
<appender-ref ref="stdout" />
|
||||
</logger>
|
||||
|
||||
<root>
|
||||
<level value="debug" />
|
||||
<appender-ref ref="stdout" />
|
||||
</root>
|
||||
|
||||
</log4j:configuration>
|
Loading…
Reference in New Issue