简易爬虫

引入依赖包

<!-- jsoup解析html -->
		<dependency>
		    <groupId>org.jsoup</groupId>
		    <artifactId>jsoup</artifactId>
		    <version>1.12.1</version>
		</dependency>**

public static void main(String[] args) {
		//要爬的网站
		String url = "https://www.cnblogs.com/";
		try {
			//使用dom
			Document doc = Jsoup.connect(url).get();
			//System.out.println(doc);
			//根据盒子类名称寻找属性
			Elements post_item = doc.select("div.post_item");
			//System.out.println(post_list);
			for (Element element : post_item) {
				Elements post_item_body = element.select("div.post_item_body");
				System.out.println("标题："+post_item_body.select("h3").select("a").text());
				System.out.println("介绍:"+post_item_body.select("p").text() );
				System.out.println("作者:"+post_item_body.select("div.post_item_foot").select("a").text());
				System.out.println("连接"+post_item_body.select("a").attr("href"));
				Document doc2 = Jsoup.connect(post_item_body.select("a").attr("href")).get();
				Elements postBody = doc.select("div#cnblogs_post_body");
				System.out.println(doc.select("div#mainContent"));
				System.out.println("");
				System.out.println("");
				System.out.println("");
			}
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}