java使用jsoup爬虫入门

左手的ㄟ右手 2022-05-24 10:13 296阅读 0赞

一、maven项目里pom添加jsoup依赖

<dependency>
        <groupId>org.jsoup</groupId>
        <artifactId>jsoup</artifactId>
        <version>1.9.2</version>
    </dependency>

二、以csdn网址为例，获取页面，使用dom获取内容，写入本地

public class JsoupDemo {
    	private static OutputStream os;
    
    	public static void main(String[] args) {
    		try {
    			Document doc = Jsoup.connect("https://www.csdn.net/").get();
    //			System.out.println(doc.title()); //CSDN-专业IT技术社区
    			//把文章标题和连接写入txt文件
    			Element feedlist_id = doc.getElementById("feedlist_id");
    			Elements h2 = feedlist_id.select("h2.csdn-tracking-statistics");
    			Elements a = h2.select("a");
    			//指定文件名及路径
    			File file = new File("E:\\jsoup\\word\\test.txt"); 
    			if (!file.exists()) {
    				file.createNewFile();
    			}
    			//写入本地
    			PrintWriter pw = new PrintWriter("E:\\jsoup\\word\\test.txt","UTF-8"); 
    			for (Element element : a) {
    				pw.println(element.text());
    				pw.println(element.attr("href")); 
    				pw.println("------------------------------------------------------------------------------------------------------------------------------------");
    			}
    			pw.close(); //关闭输出流
    			//获取页面上的图片保存到本地
    			Elements imgs = doc.select("img[src$=.png]");
    			for (Element element : imgs) {
    				String img = element.attr("src");
    				String url = "http:"+img;
    				System.out.println(url);
    				System.out.println(url.indexOf("csdn"));
    				if (url.indexOf("csdn")==-1) {
    					continue;
    				}
    				URL u = new URL(url);
    				URLConnection uc=u.openConnection();
    		        //获取数据流
    		        InputStream is=uc.getInputStream();
    		        //获取后缀名
    		        String imageName = img.substring(img.lastIndexOf("/") + 1,img.length());
    		        //写入本地
    		        os = new FileOutputStream(new File("E:\\jsoup\\img", imageName));
    		        byte[] b = new byte[1024];
    		        int i=0;
    		        while((i=is.read(b))!=-1){
    		          os.write(b, 0, i);
    		        }
    		        is.close();
    		        os.close();
    			}
    		} catch (IOException e) {
    			e.printStackTrace();
    		}
    	}
    }

三、效果如下

![70][]

![70 1][]

jsoup爬虫demo： [https://download.csdn.net/download/qq\_15260315/10524321][https_download.csdn.net_download_qq_15260315_10524321]

[70]: /images/20220524/3215bef2fdfd402f8de843597b53c9e0.png
[70 1]: /images/20220524/62c9f9be3ccc43f2a98b9b854ec71cc5.png
[https_download.csdn.net_download_qq_15260315_10524321]: https://download.csdn.net/download/qq_15260315/10524321