Commit c2142f87 authored by yihua.huang's avatar yihua.huang

add iteye sample

parent 2a19d803
...@@ -18,23 +18,24 @@ import java.util.concurrent.atomic.AtomicInteger; ...@@ -18,23 +18,24 @@ import java.util.concurrent.atomic.AtomicInteger;
/** /**
* <pre> * <pre>
*webmagic爬虫的入口类。 * webmagic爬虫的入口类。
* *
*示例: * 示例:
*定义一个最简单的爬虫: * 定义一个最简单的爬虫:
* Spider.create(new SimplePageProcessor("http://my.oschina.net/", "http://my.oschina.net/*blog/*")).run(); * Spider.create(new SimplePageProcessor("http://my.oschina.net/", "http://my.oschina.net/*blog/*")).run();
* *
*使用FilePipeline保存结果到文件: * 使用FilePipeline保存结果到文件:
* Spider.create(new SimplePageProcessor("http://my.oschina.net/", "http://my.oschina.net/*blog/*")) * Spider.create(new SimplePageProcessor("http://my.oschina.net/", "http://my.oschina.net/*blog/*"))
* .pipeline(new FilePipeline("/data/temp/webmagic/")).run(); * .pipeline(new FilePipeline("/data/temp/webmagic/")).run();
* *
*使用FileCacheQueueScheduler缓存URL,关闭爬虫后下次自动从停止的页面继续抓取: * 使用FileCacheQueueScheduler缓存URL,关闭爬虫后下次自动从停止的页面继续抓取:
* Spider.create(new SimplePageProcessor("http://my.oschina.net/", "http://my.oschina.net/*blog/*")) * Spider.create(new SimplePageProcessor("http://my.oschina.net/", "http://my.oschina.net/*blog/*"))
* .scheduler(new FileCacheQueueScheduler("/data/temp/webmagic/cache/")).run(); * .scheduler(new FileCacheQueueScheduler("/data/temp/webmagic/cache/")).run();
* </pre> * </pre>
*
* @author code4crafter@gmail.com <br> * @author code4crafter@gmail.com <br>
* Date: 13-4-21 * Date: 13-4-21
* Time: 上午6:53 * Time: 上午6:53
*/ */
public class Spider implements Runnable, Task { public class Spider implements Runnable, Task {
...@@ -66,6 +67,7 @@ public class Spider implements Runnable, Task { ...@@ -66,6 +67,7 @@ public class Spider implements Runnable, Task {
/** /**
* 使用已定义的抽取规则新建一个Spider。 * 使用已定义的抽取规则新建一个Spider。
*
* @param pageProcessor 已定义的抽取规则 * @param pageProcessor 已定义的抽取规则
*/ */
public Spider(PageProcessor pageProcessor) { public Spider(PageProcessor pageProcessor) {
...@@ -76,6 +78,7 @@ public class Spider implements Runnable, Task { ...@@ -76,6 +78,7 @@ public class Spider implements Runnable, Task {
/** /**
* 使用已定义的抽取规则新建一个Spider。 * 使用已定义的抽取规则新建一个Spider。
*
* @param pageProcessor 已定义的抽取规则 * @param pageProcessor 已定义的抽取规则
* @return 新建的Spider * @return 新建的Spider
*/ */
...@@ -85,6 +88,7 @@ public class Spider implements Runnable, Task { ...@@ -85,6 +88,7 @@ public class Spider implements Runnable, Task {
/** /**
* 重新设置startUrls,会覆盖Site本身的startUrls。 * 重新设置startUrls,会覆盖Site本身的startUrls。
*
* @param startUrls * @param startUrls
* @return this * @return this
*/ */
...@@ -96,6 +100,7 @@ public class Spider implements Runnable, Task { ...@@ -96,6 +100,7 @@ public class Spider implements Runnable, Task {
/** /**
* 为爬虫设置一个唯一ID,用于标志任务,默认情况下使用domain作为uuid,对于单domain多任务的情况,请为重复任务设置不同的ID。 * 为爬虫设置一个唯一ID,用于标志任务,默认情况下使用domain作为uuid,对于单domain多任务的情况,请为重复任务设置不同的ID。
*
* @param uuid 唯一ID * @param uuid 唯一ID
* @return this * @return this
*/ */
...@@ -106,6 +111,7 @@ public class Spider implements Runnable, Task { ...@@ -106,6 +111,7 @@ public class Spider implements Runnable, Task {
/** /**
* 设置调度器。调度器用于保存待抓取URL,并可以进行去重、同步、持久化等工作。默认情况下使用内存中的阻塞队列进行调度。 * 设置调度器。调度器用于保存待抓取URL,并可以进行去重、同步、持久化等工作。默认情况下使用内存中的阻塞队列进行调度。
*
* @param scheduler 调度器 * @param scheduler 调度器
* @return this * @return this
*/ */
...@@ -117,6 +123,7 @@ public class Spider implements Runnable, Task { ...@@ -117,6 +123,7 @@ public class Spider implements Runnable, Task {
/** /**
* 设置处理管道。处理管道用于最终抽取结果的后处理,例如:保存到文件、保存到数据库等。默认情况下会输出到控制台。 * 设置处理管道。处理管道用于最终抽取结果的后处理,例如:保存到文件、保存到数据库等。默认情况下会输出到控制台。
*
* @param pipeline 处理管道 * @param pipeline 处理管道
* @return this * @return this
*/ */
...@@ -148,7 +155,7 @@ public class Spider implements Runnable, Task { ...@@ -148,7 +155,7 @@ public class Spider implements Runnable, Task {
pipelines.add(new ConsolePipeline()); pipelines.add(new ConsolePipeline());
} }
//singel thread //singel thread
if (executorService==null){ if (executorService == null) {
while (request != null) { while (request != null) {
processRequest(request); processRequest(request);
request = scheduler.poll(this); request = scheduler.poll(this);
...@@ -217,13 +224,13 @@ public class Spider implements Runnable, Task { ...@@ -217,13 +224,13 @@ public class Spider implements Runnable, Task {
} }
} }
private void checkIfNotRunning(){ private void checkIfNotRunning() {
if (!stat.compareAndSet(STAT_INIT,STAT_INIT)){ if (!stat.compareAndSet(STAT_INIT, STAT_INIT)) {
throw new IllegalStateException("Spider is already running!"); throw new IllegalStateException("Spider is already running!");
} }
} }
public void runAsync(){ public void runAsync() {
Thread thread = new Thread(this); Thread thread = new Thread(this);
thread.setDaemon(false); thread.setDaemon(false);
thread.start(); thread.start();
...@@ -231,15 +238,19 @@ public class Spider implements Runnable, Task { ...@@ -231,15 +238,19 @@ public class Spider implements Runnable, Task {
/** /**
* 建立多个线程下载 * 建立多个线程下载
*
* @param threadNum 线程数 * @param threadNum 线程数
* @return this * @return this
*/ */
public Spider thread(int threadNum) { public Spider thread(int threadNum) {
checkIfNotRunning(); checkIfNotRunning();
if (threadNum <= 1) { if (threadNum <= 0) {
throw new IllegalArgumentException("threadNum should be more than one!"); throw new IllegalArgumentException("threadNum should be more than one!");
} }
synchronized (this){ if (threadNum == 1) {
return this;
}
synchronized (this) {
this.executorService = ThreadUtils.newFixedThreadPool(threadNum); this.executorService = ThreadUtils.newFixedThreadPool(threadNum);
} }
return this; return this;
......
...@@ -46,7 +46,7 @@ public class FilePipeline implements Pipeline { ...@@ -46,7 +46,7 @@ public class FilePipeline implements Pipeline {
file.mkdirs(); file.mkdirs();
} }
try { try {
PrintWriter printWriter = new PrintWriter(new FileWriter(path + DigestUtils.md5Hex(resultItems.getRequest().getUrl()))); 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()); printWriter.println(entry.getKey()+":\t"+entry.getValue());
......
package us.codecraft.webmagic.samples;
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;
/**
* @author yihua.huang@dianping.com <br>
* @date: 13-7-26 <br>
* Time: 上午7:31 <br>
*/
public class IteyeBlogProcessor implements PageProcessor {
private Site site;
@Override
public void process(Page page) {
page.addTargetRequests(page.getHtml().links().regex(".*yanghaoli\\.iteye\\.com/blog/\\d+").all());
page.putField("title",page.getHtml().xpath("//title").toString());
page.putField("content",page.getHtml().smartContent().toString());
}
@Override
public Site getSite() {
if (site == null) {
site = Site.me().setDomain("yanghaoli.iteye.com").addStartUrl("http://yanghaoli.iteye.com/").
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")
.setSleepTime(100).setRetryTimes(3);
}
return site;
}
public static void main(String[] args) {
Spider.create(new IteyeBlogProcessor()).thread(5).pipeline(new FilePipeline()).run();
}
}
<?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="net.sf.ehcache" additivity="false">
<level value="warn" />
<appender-ref ref="stdout" />
</logger>
<root>
<level value="info" />
<appender-ref ref="stdout" />
</root>
</log4j:configuration>
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment