您好,登錄后才能下訂單哦!
如何用Java爬蟲爬取天貓、淘寶和京東等頁面的商品詳情?這篇文章運用了實例代碼展示,代碼非常詳細(xì),可供感興趣的小伙伴們參考借鑒,希望對大家有所幫助。
<!-- 爬蟲相關(guān)Jar包依賴 -->
<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>
引入lombok 注入@Data 來避免寫get set toString等重復(fù)代碼
package java1024.xyz.vo;
import lombok.Data;
/**
@date 2020/1/3*/
@Data
br/>*/
@Data<br/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.前期工作做好后開始封裝 識別url工具 UrlUtils.java
/**
@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;
}
//天貓
if (url.contains(UrlConst.tmallUrlSign)) {
urlData.setPlatform(UrlConst.tmallUrlSign);
String numberStr = "";
/**
* 切分根路徑 和 參數(shù) 如:
* https://detail.tmall.com/item.htm?spm=a220m.1000858.1000725.8.27832a99AfoD5W&id=604433373792
* 在 ?問號的地方切成兩部分
*
*/
String[] roudAndParams = url.split("\\?");
if (roudAndParams.length < 2) {
urlData.setStatus(0);
return urlData;
}
/**
* 獲取 參數(shù)字符串,通過&切開多個參數(shù),提取以 id=開頭的即 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;
}
//淘寶
else if (url.contains(UrlConst.taobaoUrlSign)) {
urlData.setPlatform(UrlConst.taobaoUrlSign);
String numberStr = "";
/**
* 切分根路徑 和 參數(shù) 如:
* https://detail.tmall.com/item.htm?spm=a220m.1000858.1000725.8.27832a99AfoD5W&id=604433373792
* 在 ?問號的地方切成兩部分
*
*/
String[] roudAndParams = url.split("\\?");
if (roudAndParams.length < 2) {
urlData.setStatus(0);
return urlData;
}
/**
* 獲取 參數(shù)字符串,通過&切開多個參數(shù),提取以 id=開頭的即 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.爬取天貓方法
> Java 爬蟲說明:創(chuàng)建HttpClient,設(shè)置請求頭,執(zhí)行請求,解析相應(yīng)!具體代碼也有相應(yīng)的解析
public Product soupTmallDetailById(Long number) {
try {
// 需要爬取商品信息的網(wǎng)站地址
String url = "https://chaoshi.detail.tmall.com/item.htm?id=" + number;
// 動態(tài)模擬請求數(shù)據(jù)
CloseableHttpClient httpclient = HttpClients.createDefault();
HttpGet httpGet = new HttpGet(url);
// 模擬瀏覽器瀏覽(user-agent的值可以通過瀏覽器瀏覽,查看發(fā)出請求的頭文件獲?。?
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);
// 獲取響應(yīng)狀態(tài)碼
int statusCode = response.getStatusLine().getStatusCode();
try {
HttpEntity entity = response.getEntity();
// 如果狀態(tài)響應(yīng)碼為200,則獲取html實體內(nèi)容或者json文件
if (statusCode == 200) {
String html = EntityUtils.toString(entity, Consts.UTF_8);
// 提取HTML得到商品信息結(jié)果
Document doc = null;
// doc獲取整個頁面的所有數(shù)據(jù)
doc = Jsoup.parse(html);
//輸出doc可以看到所獲取到的頁面源代碼
//System.out.println(doc);
// 通過瀏覽器查看商品頁面的源代碼,找到信息所在的div標(biāo)簽,再對其進行一步一步地解析
Element item = doc.select("div[class='tb-wrap']").get(0);
//Elements liList = ulList.select("div[class='product']");
// 循環(huán)liList的數(shù)據(jù)(具體獲取的數(shù)據(jù)值還得看doc的頁面源代碼來獲取,可能稍有變動)
//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("h2").attr("data-spm");
String title = item.select("div[class='tb-detail-hd']").select("h2").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.爬取京東商品詳情方法
public Product soupTaobaoDetailById(Long number) {
try {
// 需要爬取商品信息的網(wǎng)站地址
String url = "https://item.taobao.com/item.htm?id=" + number;
// 動態(tài)模擬請求數(shù)據(jù)
CloseableHttpClient httpclient = HttpClients.createDefault();
HttpGet httpGet = new HttpGet(url);
// 模擬瀏覽器瀏覽(user-agent的值可以通過瀏覽器瀏覽,查看發(fā)出請求的頭文件獲?。?
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);
// 獲取響應(yīng)狀態(tài)碼
int statusCode = response.getStatusLine().getStatusCode();
try {
HttpEntity entity = response.getEntity();
// 如果狀態(tài)響應(yīng)碼為200,則獲取html實體內(nèi)容或者json文件
if (statusCode == 200) {
String html = EntityUtils.toString(entity, Consts.UTF_8);
// 提取HTML得到商品信息結(jié)果
Document doc = null;
// doc獲取整個頁面的所有數(shù)據(jù)
doc = Jsoup.parse(html);
//輸出doc可以看到所獲取到的頁面源代碼
//System.out.println(doc);
// 通過瀏覽器查看商品頁面的源代碼,找到信息所在的div標(biāo)簽,再對其進行一步一步地解析
Element item = doc.select("div[class='tb-item-info-r']").get(0);
//Elements liList = ulList.select("div[class='product']");
// 循環(huán)liList的數(shù)據(jù)(具體獲取的數(shù)據(jù)值還得看doc的頁面源代碼來獲取,可能稍有變動)
//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("h2").attr("data-spm");
String title = item.select("div[class='tb-title']").select("h4").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.天貓搜索功能
public List<Product> soupTaobaoByKeyWord(String keyword) {
try {
String input = "毛巾";
// 需要爬取商品信息的網(wǎng)站地址 實際中把input改成 keyword
String url = "https://list.tmall.com/search_product.htm?q=" + input;
// 動態(tài)模擬請求數(shù)據(jù)
CloseableHttpClient httpclient = HttpClients.createDefault();
HttpGet httpGet = new HttpGet(url);
// 模擬瀏覽器瀏覽(user-agent的值可以通過瀏覽器瀏覽,查看發(fā)出請求的頭文件獲?。?
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);
// 獲取響應(yīng)狀態(tài)碼
int statusCode = response.getStatusLine().getStatusCode();
try {
HttpEntity entity = response.getEntity();
// 如果狀態(tài)響應(yīng)碼為200,則獲取html實體內(nèi)容或者json文件
if (statusCode == 200) {
String html = EntityUtils.toString(entity, Consts.UTF_8);
// 提取HTML得到商品信息結(jié)果
Document doc = null;
// doc獲取整個頁面的所有數(shù)據(jù)
doc = Jsoup.parse(html);
//輸出doc可以看到所獲取到的頁面源代碼
// System.out.println(doc);
// 通過瀏覽器查看商品頁面的源代碼,找到信息所在的div標(biāo)簽,再對其進行一步一步地解析
Elements ulList = doc.select("div[class='view grid-nosku']");
Elements liList = ulList.select("div[class='product']");
// 循環(huán)liList的數(shù)據(jù)(具體獲取的數(shù)據(jù)值還得看doc的頁面源代碼來獲取,可能稍有變動)
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);
// 商品名稱
String name = item.select("p[class='productTitle']").select("a").attr("title");
System.out.println("商品名稱:" + name);
// 商品價格
String price = item.select("p[class='productPrice']").select("em").attr("title");
System.out.println("商品價格:" + price);
// 商品網(wǎng)址
String goodsUrl = item.select("p[class='productTitle']").select("a").attr("href");
System.out.println("商品網(wǎng)址:" + goodsUrl);
// 商品圖片網(wǎng)址
String imgUrl = item.select("div[class='productImg-wrap']").select("a").select("img").attr("data-ks-lazyload");
System.out.println("商品圖片網(wǎng)址:" + imgUrl);
System.out.println("------------------------------------");
}
// 消耗掉實體
EntityUtils.consume(response.getEntity());
} else {
// 消耗掉實體
EntityUtils.consume(response.getEntity());
}
} finally {
response.close();
}
}catch (Exception e) {
e.printStackTrace();
}
return null;
}
關(guān)于Java爬蟲的使用就分享到這里了,希望以上內(nèi)容可以對大家有一定的幫助,可以學(xué)到更多知識。如果覺得文章不錯,可以把它分享出去讓更多的人看到。
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點不代表本網(wǎng)站立場,如果涉及侵權(quán)請聯(lián)系站長郵箱:is@yisu.com進行舉報,并提供相關(guān)證據(jù),一經(jīng)查實,將立刻刪除涉嫌侵權(quán)內(nèi)容。