Jsoup获取url所有链接

版权声明:原创文章转载请声明出处https://blog.csdn.net/qq_40374604 https://blog.csdn.net/qq_40374604/article/details/84030310

 效果

直接上代码

package wang.test;


	import org.jsoup.Jsoup;
	import org.jsoup.helper.Validate;
	import org.jsoup.nodes.Document;
	import org.jsoup.nodes.Element;
	import org.jsoup.select.Elements;

	import java.io.IOException;

	/**
	 * Example program to list links from a URL.
	 */
	public class App2 {
	    /**
	     * @param args
	     * @throws IOException
	     */
	    public static void main(String[] args) throws IOException {
	        //Validate.isTrue(args.length == 1, "usage: supply url to fetch");
	        //String url = args[0];
	        String url ="http://politics.people.com.cn/n1/2018/1106/c1001-30383657.html";
	        print("Fetching %s...", url);

	        Document doc = Jsoup.connect(url).get();
	        Elements links = doc.select("a[href]");
	        Elements media = doc.select("[src]");
	        Elements imports = doc.select("link[href]");

	        print("\nMedia: (%d)", media.size());
	        for (Element src : media) {
	            if (src.tagName().equals("img"))
	                print(" * %s: <%s> %sx%s (%s)",
	                        src.tagName(), src.attr("abs:src"), src.attr("width"), src.attr("height"),
	                        trim(src.attr("alt"), 20));
	            else
	                print(" * %s: <%s>", src.tagName(), src.attr("abs:src"));
	        }

	        print("\nImports: (%d)", imports.size());
	        for (Element link : imports) {
	            print(" * %s <%s> (%s)", link.tagName(),link.attr("abs:href"), link.attr("rel"));
	        }

	        print("\nLinks: (%d)", links.size());
	        for (Element link : links) {
	            print(" * a: <%s>  (%s)", link.attr("abs:href"), trim(link.text(), 35));
	        }
	    }

	    private static void print(String msg, Object... args) {
	        System.out.println(String.format(msg, args));
	    }

	    private static String trim(String s, int width) {
	        if (s.length() > width)
	            return s.substring(0, width-1) + ".";
	        else
	            return s;
	    }
	}

猜你喜欢

转载自blog.csdn.net/qq_40374604/article/details/84030310
今日推荐