爬取數(shù)據(jù)

導入jar包

<properties> <java.version>1.8</java.version> <elasticsearch.version>7.6.1</elasticsearch.version> </properties> <dependencies> <dependency> <groupId>org.jsoup</groupId> <artifactId>jsoup</artifactId> <version>1.10.2</version> </dependency> <dependency> <groupId>com.alibaba</groupId> <artifactId>fastjson</artifactId> <version>1.2.62</version> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-data-redis</artifactId> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-data-elasticsearch</artifactId> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-thymeleaf</artifactId> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-web</artifactId> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-devtools</artifactId> <scope>runtime</scope> <optional>true</optional> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-configuration-processor</artifactId> <optional>true</optional> </dependency> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> <optional>true</optional> </dependency> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-test</artifactId> <scope>test</scope> <exclusions><exclusion> <groupId>org.junit.vintage</groupId> <artifactId>junit-vintage-engine</artifactId></exclusion> </exclusions> </dependency> </dependencies>

新建實體類

@Data@NoArgsConstructor@AllArgsConstructorpublic class Content { private String title; private String img; private String price;}

編寫爬蟲工具類

public class HtmlParseUtil { public static void main(String[] args) throws Exception { new HtmlParseUtil().parseDDJJ('包').forEach(System.out::println); } public List<Content> parseDDJJ(String keywords) throws Exception { //爬取url地址 String url = 'https://search.xxxx.com/Search?keyword='+keywords; //解析網(wǎng)頁，30s內(nèi)未爬取成功，打印錯誤 Document document = Jsoup.parse(new URL(url),30000); //獲取每一本書籍的id Element element = document.getElementById('DJ_goodsList'); //獲取所有的li標簽 Elements elements = element.getElementsByTag('li'); ArrayList<Content> goodsList = new ArrayList<>(); //遍歷li標簽的內(nèi)容 for (Element el : elements) { String img = el.getElementsByTag('img').eq(0).attr('src'); String price = el.getElementsByClass('p-price').eq(0).text(); String title = el.getElementsByClass('p-name').eq(0).text(); Content content = new Content(); content.setTitle(title); content.setPrice(price); content.setImg(img); goodsList.add(content); } return goodsList; }}

可以看到內(nèi)容、圖片、價格系數(shù)爬取

到此這篇關(guān)于SpringBoot中使用Jsoup爬取網(wǎng)站數(shù)據(jù)的方法的文章就介紹到這了,更多相關(guān)SpringBoot Jsoup爬取內(nèi)容請搜索好吧啦網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持好吧啦網(wǎng)！