java+phantomjs实现动态网页抓取

1.下载地址:http://phantomjs.org/download.html

2.java代码

public     void   getHtml(String url)
{
	 HTML="";
    String jsPath = "C:\\phantomjs\\examples\\myjs.js";
    String exePath = "C:\\phantomjs\\bin\\phantomjs.exe";
    System.out.println(jsPath);
    System.out.println(exePath);
    Runtime rt = Runtime.getRuntime();
	Process p;
	try {
		p = rt.exec(exePath + " " + jsPath + " " + url);

	InputStream is = p.getInputStream();
	BufferedReader br = new BufferedReader(new InputStreamReader(is));
	StringBuffer sbf = new StringBuffer();
	String tmp = "";
	while ((tmp = br.readLine()) != null)
	{
		sbf.append(tmp);
	}
	HTML=sbf.toString();
 
  is.close();
  br.close();
  sbf=null;
  is=null;
  br=null;
	} catch (IOException e) {
	 
		e.printStackTrace();
	}
 
}

　3.js

   

var page = require('webpage').create(),
  system = require('system'),
  t, address;

page.settings.loadImages = false;  //为了提升加载速度，不加载图片
page.settings.resourceTimeout = 10000;//超过10秒放弃加载
//此处是用来设置截图的参数。不截图没啥用
page.viewportSize = {
  width: 1280,
  height: 800
};
block_urls = ['baidu.com'];//为了提升速度，屏蔽一些需要时间长的。比如百度广告
page.onResourceRequested = function(requestData, request){
    for(url in block_urls) {
        if(requestData.url.indexOf(block_urls[url]) !== -1) {
            request.abort();
           return;
        }
    }            
}
 
address = system.args[1];
page.open(address, function(status) {
  if (status !== 'success') {
    console.log('FAIL to load the address');
  } else {
 
    console.log(page.content);
    setTimeout(function(){ phantom.exit(); }, 6000);
  }
  phantom.exit();
});