Webmagic+Selenium+PhantomJS實戰

仍是直接貼代碼說明比較實在。
感受webmagic-selenium這個模塊有點雞肋，但仍是有可借鑑之處。借鑑它寫了一個SeleniumDownloader,以下：

import org.openqa.selenium.By;
import org.openqa.selenium.Cookie;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Request;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Task;
import us.codecraft.webmagic.downloader.Downloader;
import us.codecraft.webmagic.selector.Html;
import us.codecraft.webmagic.selector.PlainText;
import us.codecraft.webmagic.utils.UrlUtils;

import java.util.Map;

/**
 * @author taojw
 *
 */
public class SeleniumDownloader  implements Downloader{
    private static final Logger log=LoggerFactory.getLogger(SeleniumDownloader.class);
    private int sleepTime=3000;//3s
    private SeleniumAction action=null;
    private WebDriverPool webDriverPool=new WebDriverPool();
    public SeleniumDownloader(){
    }
    public SeleniumDownloader(int sleepTime,WebDriverPool pool){
        this(sleepTime,pool,null);
    }
    public SeleniumDownloader(int sleepTime,WebDriverPool pool,SeleniumAction action){
        this.sleepTime=sleepTime;
        this.action=action;
        if(pool!=null){
            webDriverPool=pool;
        }
    }
    public SeleniumDownloader setSleepTime(int sleepTime) {
        this.sleepTime = sleepTime;
        return this;
    }
    public void setOperator(SeleniumAction action){
        this.action=action;
    }
    @Override
    public Page download(Request request, Task task) {
        WebDriver webDriver;
        try {
            webDriver = webDriverPool.get();
        } catch (InterruptedException e) {
            log.warn("interrupted", e);
            return null;
        }
        log.info("downloading page " + request.getUrl());
        Page page = new Page();
        try {
            webDriver.get(request.getUrl());
            Thread.sleep(sleepTime);
        } catch (InterruptedException e) {
            e.printStackTrace();
        } catch (Exception e) {
            webDriverPool.close(webDriver);
            page.setSkip(true);
            return page;
        }
//        WindowUtil.changeWindow(webDriver);
        WebDriver.Options manage = webDriver.manage();
        Site site = task.getSite();
        if (site.getCookies() != null) {
            for (Map.Entry<String, String> cookieEntry : site.getCookies()
                    .entrySet()) {
                Cookie cookie = new Cookie(cookieEntry.getKey(),
                        cookieEntry.getValue());
                manage.addCookie(cookie);
            }
        }
        manage.window().maximize();
        if(action!=null){
            action.execute(webDriver);
        }
        SeleniumAction reqAction=(SeleniumAction) request.getExtra("action");
        if(reqAction!=null){
            reqAction.execute(webDriver);
        }

        WebElement webElement = webDriver.findElement(By.xpath("/html"));
        String content = webElement.getAttribute("outerHTML");
        
        page.setRawText(content);
        page.setHtml(new Html(UrlUtils.fixAllRelativeHrefs(content,
                webDriver.getCurrentUrl())));
        page.setUrl(new PlainText(webDriver.getCurrentUrl()));
        page.setRequest(request);
        webDriverPool.returnToPool(webDriver);
        return page;
    }

    @Override
    public void setThread(int thread) {
        
    }

}

功能：
支持在Spider.setDownloader的時候添加鉤子SeleniumAction來實現自定義selenium的通用操做。增強了靈活性
支持對每一個請求添加action參數，參數值爲SeleniumAction對象，進而能夠對每一個請求實現自定義selenium操做.增強了靈活性

import org.openqa.selenium.WebDriver;

/**
 * @author taojw
 *
 */
public interface SeleniumAction {
    void execute(WebDriver driver);
}

WebDriverPool實現：注意對WebDriver的池化來保證性能
也是參考webmagic-selenium做了些修改。

import com.fh.util.FileUtil;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.phantomjs.PhantomJSDriver;
import org.openqa.selenium.phantomjs.PhantomJSDriverService;
import org.openqa.selenium.remote.DesiredCapabilities;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.concurrent.BlockingDeque;
import java.util.concurrent.LinkedBlockingDeque;
import java.util.concurrent.atomic.AtomicInteger;

/**
 * @author taojw
 */
public class WebDriverPool {
    private Logger logger = LoggerFactory.getLogger(getClass());

    private int CAPACITY = 5;
    private AtomicInteger refCount = new AtomicInteger(0);
    private static final String DRIVER_PHANTOMJS = "phantomjs";

    /**
     * store webDrivers available
     */
    private BlockingDeque<WebDriver> innerQueue = new LinkedBlockingDeque<WebDriver>(
            CAPACITY);

    private static String PHANTOMJS_PATH;
    private static DesiredCapabilities caps = DesiredCapabilities.phantomjs();
    static {
        PHANTOMJS_PATH = FileUtil.getCommonProp("phantomjs.path");
        caps.setJavascriptEnabled(true);
        caps.setCapability(
                PhantomJSDriverService.PHANTOMJS_EXECUTABLE_PATH_PROPERTY,
                PHANTOMJS_PATH);
        caps.setCapability("takesScreenshot", true);
        caps.setCapability(
                PhantomJSDriverService.PHANTOMJS_PAGE_CUSTOMHEADERS_PREFIX
                        + "User-Agent",
                "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36");
        caps.setCapability(PhantomJSDriverService.PHANTOMJS_CLI_ARGS,
                "--load-images=no");

    }

    public WebDriverPool() {
    }

    public WebDriverPool(int poolsize) {
        this.CAPACITY = poolsize;
        innerQueue = new LinkedBlockingDeque<WebDriver>(poolsize);
    }

    public WebDriver get() throws InterruptedException {
        WebDriver poll = innerQueue.poll();
        if (poll != null) {
            return poll;
        }
        if (refCount.get() < CAPACITY) {
            synchronized (innerQueue) {
                if (refCount.get() < CAPACITY) {

                    WebDriver mDriver = new PhantomJSDriver(caps);
                    // 嘗試性解決：https://github.com/ariya/phantomjs/issues/11526問題
                    mDriver.manage().timeouts()
                            .pageLoadTimeout(60, TimeUnit.SECONDS);
                    // mDriver.manage().window().setSize(new Dimension(1366,
                    // 768));
                    innerQueue.add(mDriver);
                    refCount.incrementAndGet();
                }
            }
        }
        return innerQueue.take();
    }

    public void returnToPool(WebDriver webDriver) {
        // webDriver.quit();
        // webDriver=null;
        innerQueue.add(webDriver);
    }

    public void close(WebDriver webDriver) {
        refCount.decrementAndGet();
        webDriver.close();
        webDriver.quit();
        webDriver = null;
    }

    public void shutdown() {
        try {
            for (WebDriver driver : innerQueue) {
                close(driver);
            }
            innerQueue.clear();
        } catch (Exception e) {
//            e.printStackTrace();
            logger.warn("webdriverpool關閉失敗",e);
        }
    }
}

修改後：
僅支持PhantomJS做爲瀏覽器驅動。
增長phantomjs相關配置
修改隊列大小控制邏輯

WindowUtil
注意這個loadAll方法的實現很巧妙哦，因爲涉及滾動加載頁面的時候，若是一會兒滾到底部可能會形成中間部分沒有加載出來，這樣就不得不針對每一個頁面進行滿滿滾動。而loadAll採起的思路是直接獲取頁面可滾動大小，而後將瀏覽器窗口調成對應大小，刷新以後全部內容便加載出來了。

import org.apache.commons.io.FileUtils;
import org.openqa.selenium.*;

import java.io.File;
import java.io.IOException;

/**
 * @author taojw
 *
 */
public class WindowUtil {
    
    /**
     * 滾動窗口。
     * @param driver
     * @param height
     */
    public static void scroll(WebDriver driver,int height){
        ((JavascriptExecutor)driver).executeScript("window.scrollTo(0,"+height+" );");    
    }
    /**
     * 從新調整窗口大小，以適應頁面，須要耗費必定時間。建議等待合理的時間。
     * @param driver
     */
    public static void loadAll(WebDriver driver){
        Dimension od=driver.manage().window().getSize();
        int width=driver.manage().window().getSize().width;
        //嘗試性解決：https://github.com/ariya/phantomjs/issues/11526問題
        driver.manage().timeouts().pageLoadTimeout(60, TimeUnit.SECONDS); 
        long height=(Long)((JavascriptExecutor)driver).executeScript("return document.body.scrollHeight;");
        driver.manage().window().setSize(new Dimension(width, (int)height));
        driver.navigate().refresh();
    }
    public static void taskScreenShot(WebDriver driver,File saveFile){
        File src=((TakesScreenshot)driver).getScreenshotAs(OutputType.FILE);
        try {
            FileUtils.copyFile(src, saveFile);
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    public static void changeWindow(WebDriver driver){
        // 獲取當前頁面句柄
        String handle = driver.getWindowHandle();
        // 獲取全部頁面的句柄，並循環判斷不是當前的句柄，就作選取switchTo()
        for (String handles : driver.getWindowHandles()) {
            if (handles.equals(handle))
                continue;
            driver.switchTo().window(handles);
        }
    }
}

至此對爬蟲框架的擴展高一段落。

實戰部分

抓取淘寶店鋪信息

/**
 * 店鋪銷售信息
 *
 * @author taojw
 */
@Scope("prototype")
@Component
public class TaoBaoShopInfoProcessor implements PageProcessor {
    private static final Logger log = LoggerFactory
            .getLogger(TaoBaoShopInfoProcessor.class);

    @Autowired
    private TaoBaoShopInfoService service;

    private Site site = Site
            .me()
            .setCharset("UTF-8")
            .setCycleRetryTimes(3)
            .setSleepTime(3 * 1000)
            .addHeader("Connection", "keep-alive")
            .addHeader("Cache-Control", "max-age=0")
            .addHeader("User-Agent",
                    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:50.0) Gecko/20100101 Firefox/50.0");

    private AtomicBoolean isPageAdd = new AtomicBoolean(false);
    private static AtomicBoolean running = new AtomicBoolean(false);
    private WebDriverPool pool=new WebDriverPool();
    @Override
    public Site getSite() {
        return this.site;
    }

    @Override
    public void process(Page page) {
        if (islistPage(page)) {
            List<String> urls = page.getHtml()
                    .$("dl.item a.J_TGoldData", "href").all();
            List<String> targetUrls = new ArrayList<String>();
            for (String url : urls) {
                targetUrls.add(url.trim());
            }
            page.addTargetRequests(targetUrls);
            if (isPageAdd.compareAndSet(false, true)) {
                // 分頁處理
                String pageinfo = page.getHtml()
                        .$(".pagination .page-info", "text").get();
                int pageCount = Integer.valueOf(pageinfo.split("/")[1]);
                String cururl = page.getUrl().get();
                //只抓前5頁
                if(pageCount>5){
                    pageCount=5;
                }
                for (int i = 1; i < pageCount; i++) {
                    String tmp = cururl + "&pageNo=" + (i + 1);
                    page.addTargetRequest(tmp);
                }
            }
            return;
        }

        // 商品頁面
        String curUrl = page.getUrl().get();
        boolean isTaoBao=curUrl.startsWith("https://item.taobao.com");
        boolean isTmall=curUrl.startsWith("https://detail.tmall.com");
        
        String tmpspm = curUrl.split("\\?")[1].split("&")[0];
        // spm碼
        String spm = tmpspm.split("=")[1];
        // 網店地址
        String shopUrl="";
     // 商品名稱
        String name="";
     // 價格
        double price =0; 
     // 30天交易總數
        int sellCount=0;
     // 交易總價
        double allPrice=0;
        if(isTaoBao){
            shopUrl= page.getHtml()
                    .xpath("//div[@class='tb-shop-name']/dl/dd/strong/a/@href")
                    .get();
            shopUrl = shopUrl.split("\\?")[0];
            
            name = page.getHtml().xpath("//*[@id='J_Title']/h3/text()")
                    .get();
            try{
                price=Double.valueOf(page.getHtml()
                        .$("#J_PromoPriceNum", "text").get().split("-")[0].trim());
                }catch(Exception e){
                    
                    price=Double.valueOf(page.getHtml()
                            .$("#J_StrPrice .tb-rmb-num", "text").get().split("-")[0].trim());
                }
            sellCount = Integer.valueOf(page.getHtml()
                    .$("#J_SellCounter", "text").get());
            allPrice = Double.valueOf(price) * Double.valueOf(sellCount);
        }else if(isTmall){
            shopUrl= page.getHtml()
                    .xpath("//*[@id='side-shop-info']/div/h3/div/a/@href")
                    .get();
            shopUrl = shopUrl.split("\\?")[0];
            
            name = page.getHtml().$(".tb-detail-hd h1","text")
                    .get().trim();
        
            price=Double.valueOf(page.getHtml()
                        .$(".tm-price", "text").get().split("-")[0].trim());
                
            sellCount = Integer.valueOf(page.getHtml()
                    .$(".tm-count", "text").get().trim());
            allPrice = Double.valueOf(price) * Double.valueOf(sellCount);
        }

        // 採集日期
        // Timestamp recordDate=new Timestamp(new Date().getTime());
        String recordDate = DateUtil.formatDate(new Date(), "yyyy-MM-dd");

        log.debug(shopUrl + ":" + spm + ":" + name + ":" + price + ":"
                + sellCount + ":" + allPrice + ":" + recordDate);

        PageData pd = new PageData();
        pd.put("id", UUID.randomUUID().toString());
        pd.put("shopUrl", shopUrl);
        pd.put("spm", spm);
        pd.put("name", name);
        pd.put("price", price);
        pd.put("sellCount", sellCount);
        pd.put("allPrice", allPrice);
        pd.put("recordDate", recordDate);
        service.saveData(pd);
    }

    private boolean islistPage(Page page) {
        String tmp = page.getHtml().$("#J_PromoPrice").get();
        if (StringUtils.isBlank(tmp)) {
            return true;
        }
        return false;
    }

    public void start() {
        if (running.compareAndSet(false, true)) {
            try {
                service.emptyTable();
                List<String> urls = service.getShopUrl();
                if (urls == null) {
                    log.error("店鋪url獲取異常,終止抓取");
                }
                String[] urlStrs=null;
                int size=50;
//                int size=urls.size();
                if(urls.size()<size){
                    urlStrs=new String[urls.size()];
                    urlStrs=urls.toArray(urlStrs);
                    
                }else{
                    urlStrs=new String[size];
                    for(int i=0;i<size;i++){
                        urlStrs[i]=urls.get(i).trim();
                    }
                }
                log.info("準備抓取,須要抓取的店鋪數爲{}", urls.size());
               // String[] urlStrs = new String[urls.size()];
              //  "https://zhuzhuwo.taobao.com" urls.toArray(urlStrs)
                Spider spider = Spider.create(this)
                        .setDownloader(new SeleniumDownloader(5000, pool, new TestAction()))
                        .addUrl(urlStrs);
                      //  .addUrl("https://zhuzhuwo.taobao.com");

                spider.thread(5).run();
                log.info("淘寶店鋪銷售信息數據正常抓取完畢");
            } finally {
                log.info("淘寶店鋪銷售信息數據抓取完畢,準備關閉webdriverpool");
                pool.shutdown();
                log.info("webdriverpool關閉完畢");
                running.set(false);
            }
        }
    }

    public static void main(String[] args) {
        new TaoBaoShopInfoProcessor().start();
    }

    private class TestAction implements SeleniumAction {

        @Override
        public void execute(WebDriver driver) {
            WebDriverWait wait = new WebDriverWait(driver, 10);
            // 商品頁，避免加載過多無用圖片信息。
            if (driver.getCurrentUrl().startsWith("https://item.taobao.com/")|| driver.getCurrentUrl().startsWith("https://detail.tmall.com")) {
              //  wait.until(ExpectedConditions.presenceOfElementLocated(By
              //          .cssSelector("#J_PromoPriceNum")));
                return;
            }
            // 店鋪首頁，點擊全部分類
            if ((!(driver.getCurrentUrl().startsWith("https://item.taobao.com")))
                    && !(driver.getCurrentUrl().startsWith("https://detail.tmall.com")) && (!driver.getCurrentUrl().contains("search"))) {
                WebElement allcate = driver.findElement(By
                        .cssSelector(".all-cats-trigger a"));
                Actions action = new Actions(driver);
                action.click(allcate).perform();
                try {
                    Thread.sleep(3000);
                } catch (InterruptedException e) {
                    e.printStackTrace();
                }
            }
            String url = driver.getCurrentUrl();
            // 列表頁，加載全部
            WindowUtil.loadAll(driver);
            url = driver.getCurrentUrl();
            try {
                Thread.sleep(3000);
//                WindowUtil.taskScreenShot(driver, new File("d:\\data\\tb\\" + UUID.randomUUID().toString() + ".png"));
                // wait.until(ExpectedConditions.presenceOfElementLocated(By.cssSelector(".pagination .page-info")));
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
        }

    }
}

抓取貓眼票房數據

因爲貓眼票房數據採用加密字體圖標，並且每一個數字對應的加密碼每次都變化。因此這次採用selenium加載頁面，截圖，摳圖(給每一個數字)，考慮到貓眼票房數據的規則性，結合google的 Tesseract-OCR 訓練模型來識別咱們摳出來的數字圖片。

ImageUtil 負責摳圖

import net.coobird.thumbnailator.Thumbnails;
import net.coobird.thumbnailator.geometry.Position;
import net.coobird.thumbnailator.geometry.Size;

/**
 * @author taojw
 *
 */
public class ImageUtil {
    public static void crop(String srcfile,String destfile,ImageRegion region){
        //指定座標  
        try {
            Thumbnails.of(srcfile)  
                    .sourceRegion(region.x, region.y, region.width, region.height)  
                    .size(region.width, region.height).outputQuality(1.0) 
                    //.keepAspectRatio(false)  //不保持比例 
                    .toFile(destfile);
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }  
    }
    public static void main(String[] args) {
        crop("D:\\data\\111.png","D:\\data\\1112.png",new ImageRegion(66, 264, 422, 426));
    }
}

/**
 * @author taojw
 *
 */
public class ImageRegion {
    public int x;
    public int y;
    public int width;
    public int height;
    public ImageRegion(int x,int y,int width,int height){
        this.x=x;
        this.y=y;
        this.width=width;
        this.height=height;
    }
}

TesseractOcrUtil，調用tesseract進程，返回識別結果。

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.UUID;

import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import com.fh.util.FileUtil;

/**
 * @author taojw
 *
 */
public class TesseractOcrUtil {
    private static final Logger log = LoggerFactory
            .getLogger(TesseractOcrUtil.class);
    private static final String tessPath;
    private static final String basePath;
    static {
        tessPath = FileUtil.getCommonProp("tesseract.path");
        basePath = new File(tessPath).getParentFile().getAbsolutePath();
    }

    public static String getByLangNum(String imagePath) {
        return get(imagePath, "num");
    }

    public static String getByLangChi(String imagePath) {
        return get(imagePath, "chi_sim");
    }

    public static String getByLangEng(String imagePath) {
        return get(imagePath, "eng");
    }

    public static String get(String imagePath, String lang) {
        String outName = UUID.randomUUID().toString();
        String outPath = basePath + File.separator
                + outName + ".txt";
//        String cmd = tessPath + " " + imagePath + " " + outName + " -l " + lang;
        ProcessBuilder pb = new ProcessBuilder();
        pb.directory(new File(basePath));
        
        pb.command(tessPath,imagePath,outName,"-l",lang);
        
        pb.redirectErrorStream(true);
        
        Process process=null;
        String errormsg = "";
        String res = null;
        try {
            process = pb.start();
            // tesseract.exe 1.jpg 1 -l chi_sim
            int excode = process.waitFor();
            
            if (excode == 0) {
                BufferedReader in = new BufferedReader(new InputStreamReader(
                        new FileInputStream(outPath), "UTF-8"));
                res = in.readLine();
                IOUtils.closeQuietly(in);
            } else {
                switch (excode) {
                case 1:
                    errormsg = "Errors accessing files.There may be spaces in your image's filename.";
                    break;
                case 29:
                    errormsg = "Cannot recongnize the image or its selected region.";
                    break;
                case 31:
                    errormsg = "Unsupported image format.";
                    break;
                default:
                    errormsg = "Errors occurred.";
                }
                log.error("when ocr picture " + imagePath
                        + " an error occured. " + errormsg);
            }

        } catch (IOException e) {
            e.printStackTrace();
            log.warn("orc process occurs an io error",e);
        } catch (InterruptedException e) {
            e.printStackTrace();
            log.warn("orc process was interrupt unexpected!",e);
        }finally{
            FileUtils.deleteQuietly(new File(imagePath));
            FileUtils.deleteQuietly(new File(outPath));
        }
        if(res!=null){
            res=res.trim();
        }
        return res;
    }
}

/**
 * @author taojw
 *
 */
public class MaoyanTest implements PageProcessor{
    private static Site site=Site.me().setCharset("UTF-8").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");
    @Override
    public Site getSite() {
        return site;
    }

    @Override
    public void process(Page page) {

    }
    public  void start() {
        
        Spider cnSpider = Spider.create(this).setDownloader(new SeleniumDownloader(5000,null,new TestAction()))
//                .addUrl("https://shop34068488.taobao.com/?spm=a230r.7195193.1997079397.2.JLFlPa")
//                .addUrl("http://piaofang.maoyan.com/company/cinema?date=2017-01-18&webCityId=288&cityTier=0&page=1&cityName=%E6%8F%AD%E9%98%B3");
                .addUrl("http://piaofang.maoyan.com/company/cinema?date=2017-01-18&webCityId=84&cityTier=0&page=1&cityName=%E4%BF%9D%E5%AE%9A");
//                .addPipeline(new JsonFilePipeline("D:\\data\\webmagicfile.json"))
        
        //SpiderMonitor.instance().register(cnSpider);
        cnSpider.run();
    }
    public static void main(String[] args) {
        new MaoyanTest().start();
    }
    
    private class TestAction implements SeleniumAction{

        @Override
        public void execute(WebDriver driver) {
            WindowUtil.loadAll(driver);
            try {
                Thread.sleep(5000);
                //WebDriverWait wait = new WebDriverWait(driver, 10);
                //wait.until(ExpectedConditions.presenceOfElementLocated(By.id("J_PromoPriceNum")));
                
                File src=((TakesScreenshot)driver).getScreenshotAs(OutputType.FILE);
                String srcfile="D:\\data\\"+UUID.randomUUID().toString()+".png";
                FileUtils.copyFile(src, new File(srcfile));
                List<WebElement> movielist=driver.findElements(By.xpath("//*[@id='cinema-tbody']/tr"));
//                movielist.remove(0);
                for(int i=1;i<movielist.size();i++){
                    int index=i+1;
                    String movieName=driver.findElement(By.xpath("//*[@id='cinema-tbody']/tr["+index+"]/td[2]")).getText();
                    
                    String pattern = "//*[@id='cinema-tbody']/tr["+index+"]/td[3]";
                    WebElement tel=driver.findElement(By.xpath(pattern));
                    
                    Point loc=tel.getLocation();
                    Dimension d=tel.getSize();
                    String cop_path="D:\\data\\crop\\current_piaofang_"+movieName+".png";
                    ImageUtil.crop(srcfile, cop_path, new ImageRegion(loc.x, loc.y, d.width+10, d.height));
                    System.out.println(TesseractOcrUtil.getByLangNum(cop_path));
                    FileUtils.deleteQuietly(new File(srcfile));
                }

            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            } catch (InterruptedException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
        }
        
    }
}

可供參考連接：
selenium系列文章：http://www.cnblogs.com/TankXi...
selenium api：http://seleniumhq.github.io/s...
tesseract-ocr樣本訓練: http://blog.csdn.net/firehood...
selenium多窗口切換：http://blog.csdn.net/meyoung0...