java爬虫爬新浪微博里某个明星的微博，Starting ChromeDriver (v2.7.236900) on port 27871，就自动报错

baidu_35198066 2016-11-21 10:26:41

/**

 * 

 */

package 新浪微博爬虫;



import java.io.File;

import java.io.IOException;

import java.util.List;

import java.util.Random;



import org.openqa.selenium.By;

import org.openqa.selenium.WebDriver;

import org.openqa.selenium.WebElement;

import org.openqa.selenium.chrome.ChromeDriverService;

import org.openqa.selenium.remote.DesiredCapabilities;

import org.openqa.selenium.remote.RemoteWebDriver;

/*

from selenium import webdriver

options = webdriver.ChromeOptions()

options.add_experimental_option("excludeSwitches",["ignore-certificate-errors"])

driver = webdriver.Chrome(chrome_options=options)

/

/**

 * @author Administrator

 *

 */

public class Spider {



	/**

	 * @param args

	 * @throws IOException 

	 * @throws InterruptedException 

	 */

	public static void main(String[] args) throws IOException, InterruptedException {

		long waitLoadBaseTime = 10000;

		int waitLoadRandomTime = 3000;

		Random random = new Random(System.currentTimeMillis());

		// 设置 chrome 的路径

		System.setProperty(

		"webdriver.chrome.driver",

		"C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe");

		// 创建一个 ChromeDriver 的接口，用于连接 Chrome

		@SuppressWarnings("deprecation")

		ChromeDriverService service = new ChromeDriverService.Builder()

		.usingDriverExecutable(

		new File(

		"C:\\Program Files (x86)\\Google\\Chrome\\Application\\chromedriver.exe"))

		.usingAnyFreePort().build();

		service.start();

		// 创建一个 Chrome 的浏览器实例

		WebDriver driver = new RemoteWebDriver(service.getUrl(),

		DesiredCapabilities.chrome());

		// 让浏览器访问微博主页

		driver.get("http://weibo.com/u/6033327972");

		//等待页面动态加载完毕

		Thread.sleep(waitLoadBaseTime+random.nextInt(waitLoadRandomTime));

		//选择每条微博的整体子模块

		List<WebElement> elements = driver.findElements(By.cssSelector("div[action-type=feed_list_item]"));

		//选择每条微博的文本内容模块

		List<WebElement> elements2 = driver.findElements(By.cssSelector("div[node-type=feed_list_reason],div[node-type=feed_list_content]"));

		System.out.println(elements.size());

		for (int i = 0; i < elements.size(); i++) {

		//展开评论

		elements.get(i).findElement(By.cssSelector("a[action-type=fl_comment]")).click();;

		Thread.sleep(1000);

		}

		//评论列表

		List<WebElement> elements3 = driver.findElements(By.cssSelector("div[node-type=feed_list_commentList]"));

		System.out.println(elements3.size());

		int a = 0;

		for (int i =0;i<elements2.size()&&a<elements3.size();i++) {

		//抓取内容

		String content = elements2.get(i).getText();

		if (!content.contains("转发微博")) {

		System.out.println("content:"+content);

		//抓取评论

		if (elements3.get(a).getText().isEmpty()) {

		System.out.println("comment:no comment");

		}else{

		System.out.println("comment:"+elements3.get(a).getText());

		}

		a++;

		}

		}

		driver.quit();

		// 关闭 ChromeDriver 接口

		service.stop();

	}



}

程序已启动，弹出chromediver.exe已停止工作
结束进程
弹出错误

Starting ChromeDriver (v2.7.236900) on port 15302

Exception in thread "main" org.openqa.selenium.remote.UnreachableBrowserException: Error communicating with the remote browser. It may have died.

Build info: version: '2.42.2', revision: '6a6995d', time: '2014-06-03 17:42:30'

System info: host: 'MS-20160515FWNU', ip: '192.168.1.190', os.name: 'Windows 7', os.arch: 'amd64', os.version: '6.1', java.version: '1.8.0_92'

Driver info: driver.version: RemoteWebDriver

	at org.openqa.selenium.remote.RemoteWebDriver.execute(RemoteWebDriver.java:593)

	at org.openqa.selenium.remote.RemoteWebDriver.get(RemoteWebDriver.java:304)

	at 新浪微博爬虫.Spider.main(Spider.java:54)

Caused by: java.net.SocketException: Connection reset

	at java.net.SocketInputStream.read(SocketInputStream.java:209)

	at java.net.SocketInputStream.read(SocketInputStream.java:141)

	at org.apache.http.impl.io.SessionInputBufferImpl.streamRead(SessionInputBufferImpl.java:136)

	at org.apache.http.impl.io.SessionInputBufferImpl.fillBuffer(SessionInputBufferImpl.java:152)

	at org.apache.http.impl.io.SessionInputBufferImpl.readLine(SessionInputBufferImpl.java:270)

	at org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:140)

	at org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:57)

	at org.apache.http.impl.io.AbstractMessageParser.parse(AbstractMessageParser.java:260)

	at org.apache.http.impl.DefaultBHttpClientConnection.receiveResponseHeader(DefaultBHttpClientConnection.java:161)

	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)

	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)

	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)

	at java.lang.reflect.Method.invoke(Method.java:498)

	at org.apache.http.impl.conn.CPoolProxy.invoke(CPoolProxy.java:138)

	at com.sun.proxy.$Proxy0.receiveResponseHeader(Unknown Source)

	at org.apache.http.protocol.HttpRequestExecutor.doReceiveResponse(HttpRequestExecutor.java:271)

	at org.apache.http.protocol.HttpRequestExecutor.execute(HttpRequestExecutor.java:123)

	at org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:254)

	at org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:195)

	at org.apache.http.impl.execchain.RetryExec.execute(RetryExec.java:85)

	at org.apache.http.impl.execchain.RedirectExec.execute(RedirectExec.java:108)

	at org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:186)

	at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:72)

	at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:57)

	at org.openqa.selenium.remote.HttpCommandExecutor.fallBackExecute(HttpCommandExecutor.java:204)

	at org.openqa.selenium.remote.HttpCommandExecutor.execute(HttpCommandExecutor.java:173)

	at org.openqa.selenium.remote.RemoteWebDriver.execute(RemoteWebDriver.java:572)

	... 2 more