MinerHtmlThread.java 爬取页面线程

MinerHtmlThread.java 爬取页面线程

package com.iteye.injavawetrust.miner;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.jsoup.Connection;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document; /**
* 爬取页面线程
* @author InJavaWetrust
*
*/
public class MinerHtmlThread extends Thread { private static final Log LOG = LogFactory.getLog(MinerHtmlThread.class); private MinerConfig config = null; public MinerHtmlThread(MinerConfig config) {
this.config = config;
} @Override
public void run() {
while (!MinerMonitorThread.done) {
minerHtml();
}
} public synchronized void minerHtml() {
MinerUrl minerUrl = MinerQueue.unVisitedPoll(); // 待访问出队列。
try {
//判断当前页面爬取深度
if(null == minerUrl || MinerUtil.isBlank(minerUrl.getUrl()) || minerUrl.getDepth() > config.getMaxDepth()) {
return;
}
//判断爬取页面URL是否包含http
if("http".contains(minerUrl.getUrl())) {
LOG.info("MinerHtmlThread当前爬取URL[" + minerUrl.getUrl() + "]没有http");
return;
}
LOG.info("MinerHtmlThread当前爬取页面[" + minerUrl.getUrl() + "]爬取深度[" + minerUrl.getDepth() + "] 当前线程 [" + Thread.currentThread().getName() + "]");
Connection conn = Jsoup.connect(minerUrl.getUrl());
conn.header("User-Agent", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13");//配置模拟浏览器
Document doc = conn.get();
String page = doc.html();
Html html = new Html();
html.setUrl(minerUrl.getUrl());
html.setHtml(page);
html.setDepth(minerUrl.getDepth()); // 添加到存储队列
MinerQueue.addStore(html); // 已经爬取的页面 添加到等待提取URL的分析页面队列
MinerQueue.addWaitingMisering(html); } catch(Exception e) {
LOG.info("MinerHtmlThread爬取页面失败 URL [" + minerUrl.getUrl() + "]");
LOG.info("MinerHtmlThreadError info [" + e.getMessage() + "]");
} } }

返回列表

上一篇:20145201 《Java程序设计》第二周学习总结


下一篇:理解WebKit和Chromium:Chromium资源磁盘缓存