主要目的是 HttpClient 和 Jsoup 的学习
首先访问京东,搜索手机,分析页面,我们抓取以下商品数据: 商品图片、价格、标题、商品详情页
CREATE TABLE `jd_item` (
`id` BIGINT(10) NOT NULL AUTO_INCREMENT COMMENT '主键 id',
`spu` BIGINT(15) DEFAULT NULL COMMENT '商品集合 id',
`sku` BIGINT(15) DEFAULT NULL COMMENT '商品最小品类单元 id',
`title` VARCHAR(100) DEFAULT NULL COMMENT '商品标题',
`price` BIGINT(10) DEFAULT NULL COMMENT '商品价格',
`pic` VARCHAR(200) DEFAULT NULL COMMENT '商品图片',
`url` VARCHAR(200) DEFAULT NULL COMMENT '商品详情地址',
`created` DATETIME DEFAULT NULL COMMENT '创建时间',
`updated` DATETIME DEFAULT NULL COMMENT '更新时间',
PRIMARY KEY (`id`),
KEY `sku` (`sku`) USING BTREE )
ENGINE=INNODB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8 COMMENT='京东商品表';
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0modelVersion>
<parent>
<groupId>org.springframework.bootgroupId>
<artifactId>spring-boot-starter-parentartifactId>
<version>2.0.2.RELEASEversion>
parent>
<groupId>com.rhoningroupId>
<artifactId>crawlerTest_jdartifactId>
<version>1.0-SNAPSHOTversion>
<dependencies>
<dependency>
<groupId>org.springframework.bootgroupId>
<artifactId>spring-boot-starter-webartifactId>
dependency>
<dependency>
<groupId>org.springframework.bootgroupId>
<artifactId>spring-boot-starter-data-jpaartifactId>
dependency>
<dependency>
<groupId>mysqlgroupId>
<artifactId>mysql-connector-javaartifactId>
dependency>
<dependency>
<groupId>org.apache.httpcomponentsgroupId>
<artifactId>httpclientartifactId>
dependency>
<dependency>
<groupId>org.jsoupgroupId>
<artifactId>jsoupartifactId>
<version>1.10.3version>
dependency>
<dependency>
<groupId>org.apache.commonsgroupId>
<artifactId>commons-lang3artifactId>
dependency>
dependencies>
project>
#DB Configuration:
spring.datasource.driverClassName=com.mysql.jdbc.Driver
spring.datasource.url=jdbc:mysql://127.0.0.1:3306/test
spring.datasource.username=root
spring.datasource.password=root
#JPA Configuration:
spring.jpa.database=MySQL
spring.jpa.show-sql=true
package com.rhonin.jd.pojo;
import javax.persistence.*;
import java.util.Date;
@Entity
@Table(name = "jd_item")
public class Item {
//主键
@Id
@GeneratedValue(strategy = GenerationType.IDENTITY)
//标准产品单位(商品集合)
private Long spu;
// 库存量单位(最小品类单元)
private Long sku;
// 商品标题
private String title;
// 商品价格
private Double price;
// 商品图片
private String pic;
// 商品详情地址
private String url;
// 创建时间
private Date created;
// 更新时间
private Date updated;
//get set方法略
}
public interface ItemDao extends JpaRepository<Item,Long> {
}
public interface ItemService {
/**
* 保存商品
* @param item
*/
public void save(Item item);
/**
* 根据条件查询商品
* @param item
* @return
*/
public List<Item> findAll(Item item);
}
public class ItemServiceImpl implements ItemService {
@Autowired
private ItemDao itemDao;
@Override
public void save(Item item) {
this.itemDao.save(item);
}
@Override
public List<Item> findAll(Item item) {
//声明查询条件
Example<Item> example = Example.of(item);
//根据查询条件进行查询数据
List<Item> list = this.itemDao.findAll(example);
return list;
}
}
@SpringBootApplication
@EnableScheduling
public class application {
public static void main(String[] args) {
SpringApplication.run(application.class, args);
}
}
@Component
public class HttpUtils {
private PoolingHttpClientConnectionManager cm;
public HttpUtils() {
this.cm = new PoolingHttpClientConnectionManager();
//设置最大连接数
this.cm.setMaxTotal(100);
//设置每个主机的最大连接数
this.cm.setDefaultMaxPerRoute(10);
}
/**
* 根据请求地址下载页面数据
*
* @param url
* @return 页面数据
*/
public String doGetHtml(String url) {
//获取HttpClient对象
CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(this.cm).build();
//创建httpGet请求对象,设置url地址
HttpGet httpGet = new HttpGet(url);
//设置请求信息
httpGet.setConfig(this.getConfig());
CloseableHttpResponse response = null;
try {
//使用HttpClient发起请求,获取响应
response = httpClient.execute(httpGet);
//解析响应,返回结果
if (response.getStatusLine().getStatusCode() == 200) {
//判断响应体Entity是否不为空,如果不为空就可以使用EntityUtils
if (response.getEntity() != null) {
String content = EntityUtils.toString(response.getEntity(), "utf8");
return content;
}
}
} catch (IOException e) {
e.printStackTrace();
} finally {
//关闭response
if (response != null) {
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
//返回空串
return "";
}
/**
* 下载图片
*
* @param url
* @return 图片名称
*/
public String doGetImage(String url) {
//获取HttpClient对象
CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(this.cm).build();
//创建httpGet请求对象,设置url地址
HttpGet httpGet = new HttpGet(url);
//设置请求信息
httpGet.setConfig(this.getConfig());
CloseableHttpResponse response = null;
try {
//使用HttpClient发起请求,获取响应
response = httpClient.execute(httpGet);
//解析响应,返回结果
if (response.getStatusLine().getStatusCode() == 200) {
//判断响应体Entity是否不为空
if (response.getEntity() != null) {
//下载图片
//获取图片的后缀
String extName = url.substring(url.lastIndexOf("."));
//创建图片名,重命名图片
String picName = UUID.randomUUID().toString() + extName;
//下载图片
//声明OutPutStream
OutputStream outputStream = new FileOutputStream(new File("C:\\Users\\tree\\Desktop\\images\\" +
picName));
response.getEntity().writeTo(outputStream);
//返回图片名称
return picName;
}
}
} catch (IOException e) {
e.printStackTrace();
} finally {
//关闭response
if (response != null) {
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
//如果下载失败,返回空串
return "";
}
//设置请求信息
private RequestConfig getConfig() {
RequestConfig config = RequestConfig.custom()
.setConnectTimeout(1000) //创建连接的最长时间
.setConnectionRequestTimeout(500) // 获取连接的最长时间
.setSocketTimeout(10000) //数据传输的最长时间
.build();
return config;
}
}
@Component
public class ItemTask {
@Autowired
private HttpUtils httpUtils;
@Autowired
private ItemService itemService;
private static final ObjectMapper MAPPER = new ObjectMapper();
//当下载任务完成后,间隔多长时间进行下一次的任务。
@Scheduled(fixedDelay = 100 * 1000)
public void itemTask() throws Exception {
//声明需要解析的初始地址
String url = "https://search.jd.com/Search?keyword=%E6%89%8B%E6%9C%BA&enc=utf-8&qrst=1&rt=1&stop=1&vt=2&wq" +
"=%E6%89%8B%E6%9C%BA&cid2=653&cid3=655&s=113&click=0&page=";
//按照页面对手机的搜索结果进行遍历解析
for (int i = 1; i < 10; i = i + 2) {
String html = httpUtils.doGetHtml(url + i);
//解析页面,获取商品数据并存储
this.parse(html);
}
System.out.println("手机数据抓取完成!");
}
//解析页面,获取商品数据并存储
private void parse(String html) throws Exception {
//解析html获取Document
Document doc = Jsoup.parse(html);
//获取spu信息
Elements spuEles = doc.select("div#J_goodsList > ul > li");
for (Element spuEle : spuEles) {
//获取spu
long spu = Long.parseLong(spuEle.attr("data-spu"));
//获取sku信息
Elements skuEles = spuEle.select("li.ps-item");
for (Element skuEle : skuEles) {
//获取sku
long sku = Long.parseLong(skuEle.select("[data-sku]").attr("data-sku"));
//根据sku查询商品数据
Item item = new Item();
item.setSku(sku);
List<Item> list = this.itemService.findAll(item);
if(list.size()>0) {
//如果商品存在,就进行下一个循环,该商品不保存,因为已存在
continue;
}
//设置商品的spu
item.setSpu(spu);
//获取商品的详情的url
String itemUrl = "https://item.jd.com/" + sku + ".html";
item.setUrl(itemUrl);
//获取商品的图片
String picUrl ="https:"+ skuEle.select("img[data-sku]").first().attr("data-lazy-img");
picUrl = picUrl.replace("/n9/","/n1/");
String picName = this.httpUtils.doGetImage(picUrl);
item.setPic(picName);
//获取商品的价格
String priceJson = this.httpUtils.doGetHtml("https://p.3.cn/prices/mgets?skuIds=J_" + sku);
double price = MAPPER.readTree(priceJson).get(0).get("p").asDouble();
item.setPrice(price);
//获取商品的标题
String itemInfo = this.httpUtils.doGetHtml(item.getUrl());
String title = Jsoup.parse(itemInfo).select("div.sku-name").text();
item.setTitle(title);
item.setCreated(new Date());
item.setUpdated(item.getCreated());
//保存商品数据到数据库中
this.itemService.save(item);
}
}
}
}