2）JS动态生成HTML元素的爬取

2）JS动态生成HTML元素的爬取

import java.util.List;

import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;

import cn.edu.hfut.dmic.webcollector.crawler.DeepCrawler;
import cn.edu.hfut.dmic.webcollector.model.Links;
import cn.edu.hfut.dmic.webcollector.model.Page;

/*
 * JS爬取
 * Refer: http://blog.csdn.net/smilings/article/details/7395509
 */
public class WebCollector3 extends DeepCrawler {

	public WebCollector3(String crawlPath) {
		super(crawlPath);
		// TODO Auto-generated constructor stub
	}

	@Override
	public Links visitAndGetNextLinks(Page page) {
		/*HtmlUnitDriver可以抽取JS生成的数据*/
//		HtmlUnitDriver driver=PageUtils.getDriver(page,BrowserVersion.CHROME);
//		String content = PageUtils.getPhantomJSDriver(page);
        WebDriver driver = PageUtils.getWebDriver(page);
//        List<WebElement> divInfos=driver.findElementsByCssSelector("#feed_content");
        List<WebElement> divInfos=driver.findElements(By.cssSelector("#feed_content span"));
        for(WebElement divInfo:divInfos){
            System.out.println("Text是：" + divInfo.getText());
        }
        return null;
	}
	
	public static void main(String[] args) {
		WebCollector3 crawler=new WebCollector3("/home/hu/data/wb");
        for(int page=1;page<=5;page++)
//        crawler.addSeed("http://www.sogou.com/web?query="+URLEncoder.encode("编程")+"&page="+page);
        crawler.addSeed("http://cq.qq.com/baoliao/detail.htm?294064");
        try {
			crawler.start(1);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

}

PageUtils.java

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;

import org.openqa.selenium.JavascriptExecutor;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.htmlunit.HtmlUnitDriver;
import org.openqa.selenium.ie.InternetExplorerDriver;
import org.openqa.selenium.phantomjs.PhantomJSDriver;

import com.gargoylesoftware.htmlunit.BrowserVersion;

import cn.edu.hfut.dmic.webcollector.model.Page;

public class PageUtils {
	public static HtmlUnitDriver getDriver(Page page) {
        HtmlUnitDriver driver = new HtmlUnitDriver();
        driver.setJavascriptEnabled(true);
        driver.get(page.getUrl());
        return driver;
    }

    public static HtmlUnitDriver getDriver(Page page, BrowserVersion browserVersion) {
        HtmlUnitDriver driver = new HtmlUnitDriver(browserVersion);
        driver.setJavascriptEnabled(true);
        driver.get(page.getUrl());
    	return driver;
    }
    
    public static WebDriver getWebDriver(Page page) {
//    	WebDriver driver = new HtmlUnitDriver(true);
    	
//    	System.setProperty("webdriver.chrome.driver", "D:\Installs\Develop\crawling\chromedriver.exe");
//    	WebDriver driver = new ChromeDriver();
    	
    	System.setProperty("phantomjs.binary.path", "D:\Installs\Develop\crawling\phantomjs-2.0.0-windows\bin\phantomjs.exe");
    	WebDriver driver = new PhantomJSDriver();
    	driver.get(page.getUrl());
    	
//    	JavascriptExecutor js = (JavascriptExecutor) driver;
//    	js.executeScript("function(){}");
    	return driver;
    }
    
    public static String getPhantomJSDriver(Page page) {
    	Runtime rt = Runtime.getRuntime();
    	Process process = null;
    	try {
			process = rt.exec("D:\Installs\Develop\crawling\phantomjs-2.0.0-windows\bin\phantomjs.exe " + 
			"D:\workspace\crawlTest1\src\crawlTest1\parser.js " +
			page.getUrl().trim());
			InputStream in = process.getInputStream();
			InputStreamReader reader = new InputStreamReader(
					in, "UTF-8");
			BufferedReader br = new BufferedReader(reader);
			StringBuffer sbf = new StringBuffer();
			String tmp = "";
			while((tmp = br.readLine())!=null){    
                sbf.append(tmp);    
            }
			return sbf.toString();
		} catch (IOException e) {
			e.printStackTrace();
		}
    	
    	return null;
    }
}

2.1）HtmlUnitDriver getDriver是selenium 1.x的作法，已经outdate了，现在用WebDriver getWebDriver

2.2）这里用了几种方法：HtmlUnitDriver, ChromeDriver, PhantomJSDriver, PhantomJS，参考 http://blog.csdn.net/five3/article/details/19085303，各自之间的优缺 点如下：

driver类型	优点	缺点	应用
真实浏览器driver	真实模拟用户行为	效率、稳定性低	兼容性测试
HtmlUnit	速度快	js引擎不是主流的浏览器支持的	包含少量js的页面测试
PhantomJS	速度中等、模拟行为接近真实	不能模拟不同/特定浏览器的行为	非GUI的功能性测试

* 真实浏览器driver 包括 Firefox, Chrome, IE

2.3）用PhantomJSDriver的时候，遇上错 误：ClassNotFoundException: org.openqa.selenium.browserlaunchers.Proxies，原 因竟然是selenium 2.44 的bug，后来通过maven找到phantomjsdriver-1.2.1.jar 才解决了。

2.4）另外，我还试了PhantomJS 原生调用（也就是不用selenium，直接调用PhantomJS，见上面的方法），原生要调用JS，这里的parser.js代码如下：

system = require('system')   
address = system.args[1];//获得命令行第二个参数 接下来会用到   
//console.log('Loading a web page');   
var page = require('webpage').create();   
var url = address;   
//console.log(url);   
page.open(url, function (status) {   
    //Page is loaded!   
    if (status !== 'success') {   
        console.log('Unable to post!');   
    } else {    
    //此处的打印，是将结果一流的形式output到java中，java通过InputStream可以获取该输出内容
        console.log(page.content);   
    }      
    phantom.exit();   
});

3）后话

3.1）HtmlUnitDriver + PhantomJSDriver是当前最可靠的动态抓取方案。

3.2）这过程中用到很多包、exe，遇到很多的墙~，有需要的朋友可以找我要。

Reference

http://www.ibm.com/developerworks/cn/web/1309_fengyq_seleniumvswebdriver/
http://blog.csdn.net/smilings/article/details/7395509
http://phantomjs.org/download.html
http://blog.csdn.net/five3/article/details/19085303
http://phantomjs.org/quick-start.html

... ...

动态网页爬取例子（WebCollector+selenium+phantomjs）