jsoup

jsoup

解析url

package Jsoup;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.junit.Test;
import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
public class JsoupTest {
    @Test
    public void testUrl() throws IOException {
        Document doc = Jsoup.parse(new URL("http://www.baidu.com"), 3000);
        Elements title1 = doc.getElementsByTag("link");
        for (Element e:title1
             ) {
            System.out.println(e);
        }
    }
}
//输出
<link rel="dns-prefetch" href="//dss1.bdstatic.com">
<link rel="dns-prefetch" href="//ss1.bdstatic.com">
<link rel="dns-prefetch" href="//sp0.baidu.com">
<link rel="dns-prefetch" href="//sp1.baidu.com">
<link rel="dns-prefetch" href="//sp2.baidu.com">

解析字符串

    @Test
    public void testString() throws Exception{
        //获取字符串.由html组成的txt文本。
        String s = FileUtils.readFileToString(new File("C:\\Users\\DELL\\Desktop\\demo.txt"), "utf-8");
        //解析字符串
        Document doc = Jsoup.parse(s);
        Elements title = doc.getElementsByTag("title");
        System.out.println(title);

    }
}
//输出
<title>百度一下，你就知道</title>

解析文件

   @Test
    public void testFile() throws Exception{
        Document document = Jsoup.parse(new File("C:\\Users\\DELL\\Desktop\\demo.txt"), "utf8");
        Elements title = document.getElementsByTag("title");
        System.out.println(title);
    }

使用DOM方式遍历文档

获取Element 最常用的四种方式

1. 根据id getElementById

2. 根据tag getElementsByTag

   如

   ,