Code
public class CrawlJobHandler implements CrawlStatusListener {

public void startCrawler() {
        running = true;
        if (pendingCrawlJobs.size() > 0 && isCrawling() == false) {
            // Ok, can just start the next job
            startNextJob();
        }
    }

protected final void startNextJob() {
        synchronized (this) {
            if(startingNextJob != null) {
                try {
                    startingNextJob.join();
                } catch (InterruptedException e) {
                    e.printStackTrace();
                    return;
                }
            }
            startingNextJob = new Thread(new Runnable() {
                public void run() {
                    startNextJobInternal();
                }
            }, "StartNextJob");
            //当前任务线程开始执行
            startingNextJob.start();
        }
    }

protected void startNextJobInternal() {
        if (pendingCrawlJobs.size() == 0 || isCrawling()) {
            // No job ready or already crawling.
            return;
        }
    //从待处理的任务列表取出一个任务
        this.currentJob = (CrawlJob)pendingCrawlJobs.first();
        assert pendingCrawlJobs.contains(currentJob) :
            "pendingCrawlJobs is in an illegal state";
    //从待处理列表中删除
        pendingCrawlJobs.remove(currentJob);
        try {
            this.currentJob.setupForCrawlStart();
            // This is ugly but needed so I can clear the currentJob
            // reference in the crawlEnding and update the list of completed
            // jobs.  Also, crawlEnded can startup next job.
            this.currentJob.getController().addCrawlStatusListener(this);
            // now, actually start
        //控制器真正开始执行的地方
            this.currentJob.getController().requestCrawlStart();
        } catch (InitializationException e) {
            loadJob(getStateJobFile(this.currentJob.getDirectory()));
            this.currentJob = null;
            startNextJobInternal(); // Load the next job if there is one.
        }
    }
}

Code
package org.archive.crawler.framework;

public class CrawlController implements Serializable, Reporter {
     
    // key subcomponents which define and implement a crawl in progress
    private transient CrawlOrder order;
    private transient CrawlScope scope;
    private transient ProcessorChainList processorChains;
    
    private transient Frontier frontier;

private transient ToePool toePool;
    
    private transient ServerCache serverCache;
    
    // This gets passed into the initialize method.
    private transient SettingsHandler settingsHandler;

 
}

Code
public void initialize(SettingsHandler sH)
    throws InitializationException {
        sendCrawlStateChangeEvent(PREPARING, CrawlJob.STATUS_PREPARING);

this.singleThreadLock = new ReentrantLock();
        this.settingsHandler = sH;

//从XMLSettingsHandler中取出Order
        this.order = settingsHandler.getOrder();

this.order.setController(this);
        this.bigmaps = new Hashtable<String,CachedBdbMap<?,?>>();
        sExit = "";
        this.manifest = new StringBuffer();
        String onFailMessage = "";
        try {
            onFailMessage = "You must set the User-Agent and From HTTP" +
            " header values to acceptable strings. \n" +
            " User-Agent: [software-name](+[info-url])[misc]\n" +
            " From: [email-address]\n";

//检查了用户设定的UserAgent等信息，看是否符合格式
            order.checkUserAgentAndFrom();

onFailMessage = "Unable to setup disk";
            if (disk == null) {
                setupDisk(); //设定了开始抓取后保存文件信息的目录结构
            }

onFailMessage = "Unable to create log file(s)";
            //初始化了日志信息的记录工具
            setupLogs();

onFailMessage = "Unable to test/run checkpoint recover";
            this.checkpointRecover = getCheckpointRecover();
            if (this.checkpointRecover == null) {
                this.checkpointer =
                    new Checkpointer(this, this.checkpointsDisk);
            } else {
                setupCheckpointRecover();
            }
            
            onFailMessage = "Unable to setup bdb environment.";

//初始化使用Berkley DB的一些工具
            setupBdb();
            
            onFailMessage = "Unable to setup statistics";
            setupStatTracking();
            
            onFailMessage = "Unable to setup crawl modules";
        //初始化了Scope、Frontier以及ProcessorChain
            setupCrawlModules();
        } catch (Exception e) {
            String tmp = "On crawl: "
                + settingsHandler.getSettingsObject(null).getName() + " " +
                onFailMessage;
            LOGGER.log(Level.SEVERE, tmp, e);
            throw new InitializationException(tmp, e);
        }

Lookup.getDefaultCache(DClass.IN).setMaxEntries(1);
        //dns.getRecords("localhost", Type.A, DClass.IN);

//实例化线程池
        setupToePool();
        setThresholds();
        
        reserveMemory = new LinkedList<char[]>();
        for(int i = 1; i < RESERVE_BLOCKS; i++) {
            reserveMemory.add(new char[RESERVE_BLOCK_SIZE]);
        }
    }

Code
    public void requestCrawlStart() {
        //初始化处理器链
        runProcessorInitialTasks();

sendCrawlStateChangeEvent(STARTED, CrawlJob.STATUS_PENDING);
        String jobState;
        state = RUNNING;
        jobState = CrawlJob.STATUS_RUNNING;
        sendCrawlStateChangeEvent(this.state, jobState);

// A proper exit will change this value.
        this.sExit = CrawlJob.STATUS_FINISHED_ABNORMAL;
        
        Thread statLogger = new Thread(statistics);
        statLogger.setName("StatLogger");
        //开始日志线程
        statLogger.start();
        //启运Frontier，抓取工作开始
        frontier.start();
    }