Java爬虫爬取 天猫 淘宝 京东 搜索页和 商品详情
先识别商品url,区分平台提取商品编号,再根据平台带着商品编号爬取数据。
1.导包
<!-- 爬虫相关Jar包依赖 -->
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>3.10-FINAL</version>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.3</version>
</dependency>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.11.3</version>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<scope>provided</scope>
</dependency>
2.封装返回类型和常量
引入lombok 注入@Data 来避免写get set toString等重复代码
package java1024.xyz.vo;
import lombok.Data;
/**
- @author xivin
- @email [email protected]
- @description
- @date 2020/1/3br/>*/
@Data
public class UrlData {private int status;
private String platform;
private Long number;
}
package java1024.xyz.vo;
/**
- 常量接口
**/
public interface UrlConst {String taobaoUrlSign = "taobao.com";
String tmallUrlSign = "tmall.com";
String jingdongUrlSign = "jd.com";String TMALL_PRODUCT_DETAIL = "https://detail.tmall.com/item.htm?id=";
String TAOBAO_PRODUCT_DETAIL = "https://item.taobao.com/item.htm?id=";
String JD_PRODUCT_DETAIL = "https://item.jd.com/";
}
import com.fasterxml.jackson.annotation.JsonFormat;
import lombok.Data;
import java.io.Serializable;
import java.sql.Timestamp;
/**
- @author xivin
- @email [email protected]
- @description 商品实体类
- @date 2020/1/3br/>*/
@Data
public class Product implements Serializable {private Long id;
private Long number;
private Float price;
private Integer userId;
private String url;
private Integer platformId;
private String title;
private String describe;
private Integer status;
@JsonFormat( pattern="yyyy-MM-dd HH:mm:ss")
private Timestamp createdAt;private Timestamp updatedAt;
}
## 3.前期工作做好后开始封装 识别url工具 UrlUtils.java
/**
- @author xivin
- @email [email protected]
- @description
- @date 2020/1/3
*/
public class UrlUtils {public static UrlData analyseUrl(String url) {
UrlData urlData = new UrlData(); try { // 判空 if (StringUtils.isEmpty(url)) { urlData.setStatus(0); return urlData; } //天猫 if (url.contains(UrlConst.tmallUrlSign)) { urlData.setPlatform(UrlConst.tmallUrlSign); String numberStr = ""; /** * 切分根路径 和 参数 如: * https://detail.tmall.com/item.htm?spm=a220m.1000858.1000725.8.27832a99AfoD5W&id=604433373792 * 在 ?问号的地方切成两部分 * */ String[] roudAndParams = url.split("\\?"); if (roudAndParams.length < 2) { urlData.setStatus(0); return urlData; } /** * 获取 参数字符串,通过&切开多个参数,提取以 id=开头的即 商品id */ String paramStr = roudAndParams[1]; String[] params = paramStr.split("&"); for (int i = 0;i < params.length; i++) { if (params[i].startsWith("id=")) { numberStr = params[i].split("id=")[1]; break; } } if (StringUtils.isEmpty(numberStr)) { urlData.setStatus(0); return urlData; } Long number = new Long(numberStr); urlData.setStatus(1); urlData.setNumber(number); return urlData; } //淘宝 else if (url.contains(UrlConst.taobaoUrlSign)) { urlData.setPlatform(UrlConst.taobaoUrlSign); String numberStr = ""; /** * 切分根路径 和 参数 如: * https://detail.tmall.com/item.htm?spm=a220m.1000858.1000725.8.27832a99AfoD5W&id=604433373792 * 在 ?问号的地方切成两部分 * */ String[] roudAndParams = url.split("\\?"); if (roudAndParams.length < 2) { urlData.setStatus(0); return urlData; } /** * 获取 参数字符串,通过&切开多个参数,提取以 id=开头的即 商品id */ String paramStr = roudAndParams[1]; String[] params = paramStr.split("&"); for (int i = 0;i < params.length; i++) { if (params[i].startsWith("id=")) { numberStr = params[i].split("id=")[1]; break; } } if (StringUtils.isEmpty(numberStr)) { urlData.setStatus(0); return urlData; } Long number = new Long(numberStr); urlData.setStatus(1); urlData.setNumber(number); return urlData; } //其他 else if (url.contains(UrlConst.jingdongUrlSign)) { urlData.setPlatform(UrlConst.jingdongUrlSign); String numberStr = ""; String[] roudAndParams = url.split("jd\\.com/"); if (roudAndParams.length < 2) { urlData.setStatus(0); return urlData; } String paramStr = roudAndParams[1]; String[] params = paramStr.split(".html"); numberStr = params[0]; if (StringUtils.isEmpty(numberStr)) { urlData.setStatus(0); return urlData; } Long number = new Long(numberStr); urlData.setStatus(1); urlData.setNumber(number); return urlData; } else { urlData.setStatus(0); return urlData; } }catch (Exception e) { e.printStackTrace(); urlData.setStatus(0); return urlData; }
}
public static void main(String[] args) {
String tmallUrl = "https://detail.tmall.com/item.htm?spm=a220m.1000858.1000725.8.27832a99AfoD5W&id=604433373792&skuId=4233630160968&user_id=1776477331&cat_id=2&is_b=1&rn=2eff85a6a504024ee62222a0045d9ded"; UrlData tmall = analyseUrl(tmallUrl); System.out.println("tmall = " + tmall); String taobaoUrl = "https://s.taobao.com/search?spm=a230r.1.14.7.ade0695abTrJ6k&type=samestyle&app=i2i&rec_type=1&uniqpid=69915374&nid=604733501729"; UrlData taobao = analyseUrl(taobaoUrl); System.out.println("taobao = " + taobao); String jdUrl = "https://item.jd.com/100004250098.html#none"; UrlData jd = analyseUrl(jdUrl); System.out.println("jd = " + jd);
}
}
## 4.爬取天猫方法
> Java 爬虫说明:创建HttpClient,设置请求头,执行请求,解析相应!具体代码也有相应的解析
public Product soupTmallDetailById(Long number) {
try {
// 需要爬取商品信息的网站地址
String url = "https://chaoshi.detail.tmall.com/item.htm?id=" + number;
// 动态模拟请求数据
CloseableHttpClient httpclient = HttpClients.createDefault();
HttpGet httpGet = new HttpGet(url);
// 模拟浏览器浏览(user-agent的值可以通过浏览器浏览,查看发出请求的头文件获取)
httpGet.setHeader("user-agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36");
CloseableHttpResponse response = httpclient.execute(httpGet);
// 获取响应状态码
int statusCode = response.getStatusLine().getStatusCode();
try {
HttpEntity entity = response.getEntity();
// 如果状态响应码为200,则获取html实体内容或者json文件
if (statusCode == 200) {
String html = EntityUtils.toString(entity, Consts.UTF_8);
// 提取HTML得到商品信息结果
Document doc = null;
// doc获取整个页面的所有数据
doc = Jsoup.parse(html);
//输出doc可以看到所获取到的页面源代码
//System.out.println(doc);
// 通过浏览器查看商品页面的源代码,找到信息所在的div标签,再对其进行一步一步地解析
Element item = doc.select("div[class=‘tb-wrap‘]").get(0);
//Elements liList = ulList.select("div[class=‘product‘]");
// 循环liList的数据(具体获取的数据值还得看doc的页面源代码来获取,可能稍有变动)
//System.out.println("item = " + item);
Product product = new Product();
//for (Element item : ulList) {
// 商品ID
try {
product.setNumber(number);
product.setPlatformId(1);
//String id = item.select("div[class=‘tb-detail-hd‘]").select("h1").attr("data-spm");
String title = item.select("div[class=‘tb-detail-hd‘]").select("h1").text();
product.setTitle(title);
product.setUrl(UrlConst.TMALL_PRODUCT_DETAIL+number);
System.out.println("商品title:" + title);
//String priceStr = item.select("div[class=‘tm-price-panel‘]").select("div[class=‘tm-promo-type‘]").select("span[class=‘tm-price‘]").text();
return product;
}catch (Exception e) {
product.setId(0L);
product.setTitle("商品不存在");
return product;
}
// }
}
}catch (Exception e) {
e.printStackTrace();
Product product = new Product();
product.setId(0L);
product.setTitle("商品不存在");
return product;
}
}catch (Exception e) {
e.printStackTrace();
}
return null;
}
## 5.爬取京东商品详情方法
public Product soupTaobaoDetailById(Long number) {
try {
// 需要爬取商品信息的网站地址
String url = "https://item.taobao.com/item.htm?id=" + number;
// 动态模拟请求数据
CloseableHttpClient httpclient = HttpClients.createDefault();
HttpGet httpGet = new HttpGet(url);
// 模拟浏览器浏览(user-agent的值可以通过浏览器浏览,查看发出请求的头文件获取)
httpGet.setHeader("user-agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36");
CloseableHttpResponse response = httpclient.execute(httpGet);
// 获取响应状态码
int statusCode = response.getStatusLine().getStatusCode();
try {
HttpEntity entity = response.getEntity();
// 如果状态响应码为200,则获取html实体内容或者json文件
if (statusCode == 200) {
String html = EntityUtils.toString(entity, Consts.UTF_8);
// 提取HTML得到商品信息结果
Document doc = null;
// doc获取整个页面的所有数据
doc = Jsoup.parse(html);
//输出doc可以看到所获取到的页面源代码
//System.out.println(doc);
// 通过浏览器查看商品页面的源代码,找到信息所在的div标签,再对其进行一步一步地解析
Element item = doc.select("div[class=‘tb-item-info-r‘]").get(0);
//Elements liList = ulList.select("div[class=‘product‘]");
// 循环liList的数据(具体获取的数据值还得看doc的页面源代码来获取,可能稍有变动)
//System.out.println("item = " + item);
Product product = new Product();
//for (Element item : ulList) {
// 商品ID
try {
product.setNumber(number);
product.setPlatformId(2);
//String id = item.select("div[class=‘tb-detail-hd‘]").select("h1").attr("data-spm");
String title = item.select("div[class=‘tb-title‘]").select("h3").text();
product.setTitle(title);
product.setUrl(UrlConst.TAOBAO_PRODUCT_DETAIL+number);
System.out.println("商品title:" + title);
return product;
}catch (Exception e) {
product.setId(0L);
product.setTitle("商品不存在");
return product;
}
// }
}
}catch (Exception e) {
e.printStackTrace();
Product product = new Product();
product.setId(0L);
product.setTitle("商品不存在");
return product;
}
}catch (Exception e) {
e.printStackTrace();
}
return null;
}
## 6.天猫搜索功能
public List<Product> soupTaobaoByKeyWord(String keyword) {
try {
String input = "毛巾";
// 需要爬取商品信息的网站地址 实际中把input改成 keyword
String url = "https://list.tmall.com/search_product.htm?q=" + input;
// 动态模拟请求数据
CloseableHttpClient httpclient = HttpClients.createDefault();
HttpGet httpGet = new HttpGet(url);
// 模拟浏览器浏览(user-agent的值可以通过浏览器浏览,查看发出请求的头文件获取)
httpGet.setHeader("user-agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36");
CloseableHttpResponse response = httpclient.execute(httpGet);
// 获取响应状态码
int statusCode = response.getStatusLine().getStatusCode();
try {
HttpEntity entity = response.getEntity();
// 如果状态响应码为200,则获取html实体内容或者json文件
if (statusCode == 200) {
String html = EntityUtils.toString(entity, Consts.UTF_8);
// 提取HTML得到商品信息结果
Document doc = null;
// doc获取整个页面的所有数据
doc = Jsoup.parse(html);
//输出doc可以看到所获取到的页面源代码
// System.out.println(doc);
// 通过浏览器查看商品页面的源代码,找到信息所在的div标签,再对其进行一步一步地解析
Elements ulList = doc.select("div[class=‘view grid-nosku‘]");
Elements liList = ulList.select("div[class=‘product‘]");
// 循环liList的数据(具体获取的数据值还得看doc的页面源代码来获取,可能稍有变动)
for (Element item : liList) {
// 商品ID
String id = item.select("div[class=‘product‘]").select("p[class=‘productStatus‘]").select("span[class=‘ww-light ww-small m_wangwang J_WangWang‘]").attr("data-item");
System.out.println("商品ID:" + id);
// 商品名称
String name = item.select("p[class=‘productTitle‘]").select("a").attr("title");
System.out.println("商品名称:" + name);
// 商品价格
String price = item.select("p[class=‘productPrice‘]").select("em").attr("title");
System.out.println("商品价格:" + price);
// 商品网址
String goodsUrl = item.select("p[class=‘productTitle‘]").select("a").attr("href");
System.out.println("商品网址:" + goodsUrl);
// 商品图片网址
String imgUrl = item.select("div[class=‘productImg-wrap‘]").select("a").select("img").attr("data-ks-lazyload");
System.out.println("商品图片网址:" + imgUrl);
System.out.println("------------------------------------");
}
// 消耗掉实体
EntityUtils.consume(response.getEntity());
} else {
// 消耗掉实体
EntityUtils.consume(response.getEntity());
}
} finally {
response.close();
}
}catch (Exception e) {
e.printStackTrace();
}
return null;
}
## 7.利用爬虫技术完成的一个 商品历史价格记录网站 项目——值得吗?价格记录网站 github地址:https://github.com/xivinChen/zhi-de-ma
原文地址:https://blog.51cto.com/12219995/2465468