JAVA 抓取当当图书文字并保存本地TXT文档

package com.xuexue.crawler.executor;


import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.List;
import java.util.concurrent.TimeUnit;


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


import com.xuexue.crawler.utils.FileUtils;


public class fond {


public static void main(String[] args) throws InterruptedException, IOException {
//writeFilePath ls = new writeFilePath();
List<String> keys = FileUtils.loadFile("E:\\yan.txt");
String writeFilePath = "E:\\productInfos";
String url = "http://www.dangdang.com";
System.setProperty("webdriver.chrome.driver","C:\\chromedriver.exe");
WebDriver driver = new ChromeDriver();
driver.manage().timeouts().pageLoadTimeout(3600, TimeUnit.SECONDS);
File file =new File(writeFilePath);
if(!file.exists()){
    file.mkdirs();
   }
 
for(String key : keys){
driver.get(url);
String fileName = key+".txt";
WebElement input = driver.findElement(By.xpath("//input[@id='key_S']"));
List<WebElement> buttons = driver.findElements(By.xpath("//input[@dd_name='搜索按钮']"));
input.sendKeys(key);
buttons.get(buttons.size()-1).click();
Thread.sleep(3000L);
WebElement li =  driver.findElement(By.id("p23917371"));
WebElement p =  li.findElement(By.tagName("p"));
WebElement a1 =  p.findElement(By.tagName("a"));
String nextUrl = a1.getAttribute("href");
FileWriter fileWritter = new FileWriter(writeFilePath+"\\"+fileName,true);
driver.get(nextUrl);

List<WebElement> textElements = driver.findElements(By.xpath("//div[@class='group_buy']"));
for(WebElement te : textElements){
System.out.println(te.getText());

fileWritter.write(te.getText()+"\r\n");

}

fileWritter.flush();
fileWritter.close();
}

driver.close();
}
}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值