student1.xml
<?xml version="1.0" encoding="UTF-8" ?>
<students>
<student number="0001">
<name id="1">tom</name>
<age>18</age>
<sex>male</sex>
</student><student number="0002">
<name>jack</name>
<age>18</age>
<sex>male</sex>
</student><student number="0003">
<name>alice</name>
<age>18</age>
<sex>male</sex>
</student>
</students>
JsoupDemo1
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
import java.io.File;
import java.io.IOException;
public class JsoupDemo1 {
public static void main(String[] args) throws IOException {
//2.获取Document对象,根据xml文档获取
//2.1获取 student.xml
String path = JsoupDemo1.class.getClassLoader().getResource("student1.xml").getPath();
//2.2解析xml文档,加载文档进去内存获取dom树---》Document
Document document = Jsoup.parse(new File(path), "utf-8");
//3.获取元素对象,Element
Elements elements = document.getElementsByTag("name");
System.out.println(elements.size());
//3.1获取第一个元素
System.out.println(elements.get(0));
//3.2获取数据
String name=elements.text();
System.out.println(name);
}
}
JsoupDemo2
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
import java.io.File;
import java.io.IOException;
import java.net.URL;
/**
* Jsoup 对象功能
*/
public class JsoupDemo2 {
public static void main(String[] args) throws IOException {
//2.获取Document对象,根据xml文档获取
//2.1获取 student.xml
String path = JsoupDemo2.class.getClassLoader().getResource("student1.xml").getPath();
//2.2解析xml文档,加载文档进去内存获取dom树---》Document
// Document document = Jsoup.parse(new File(path), "utf-8");
// System.out.println(document);
//2.parse(String html):解析xml或者html字符串
/* String str="<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n" +
"\n" +
"\n" +
"<students>\n" +
"\t<student number=\"itcast_0001\">\n" +
"\t\t<name>tom</name>\n" +
"\t\t<age>18</age>\n" +
"\t\t<sex>male</sex>\n" +
"\t</student><student number=\"0002\">\n" +
"\t\t<name>jack</name>\n" +
"\t\t<age>18</age>\n" +
"\t\t<sex>male</sex>\n" +
"\t</student><student number=\"0003\">\n" +
"\t\t<name>alice</name>\n" +
"\t\t<age>18</age>\n" +
"\t\t<sex>male</sex>\n" +
"\t</student>\n" +
"\t\n" +
"</students>";
Document document = Jsoup.parse(str);
System.out.println(document);*/
//3.parse(URL url,int timeoutMillis)通过网络路径获取html.或xml
URL url=new URL("http://www.baidu.com");
Document document = Jsoup.parse(url, 10000);
System.out.println(document);
}
}
JsoupDemo3
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.File;
import java.io.IOException;
/**
* Document/Element对象功能
*/
public class JsoupDemo3 {
public static void main(String[] args) throws IOException {
//1.获取student.xml的path
String path = JsoupDemo3.class.getClassLoader().getResource("student1.xml").getPath();
//2.获取Document对象
Document document = Jsoup.parse(new File(path), "utf-8");
//3.获取元素对象
//3.1获取所有的student对象
Elements elements = document.getElementsByTag("student");
System.out.println(elements);
System.out.println("--------------------------");
//3.2获取属性名为id的元素对象们
Elements elements1 = document.getElementsByAttribute("id");
System.out.println(elements1);
System.out.println("--------------------------");
//3.2获取Number属性值为0001的元素对象
Elements elements2 = document.getElementsByAttributeValue("number","0001");
System.out.println(elements2);
System.out.println("--------------------------");
//3.3获取id的属性值de 元素对象
Element elementById = document.getElementById("1");
System.out.println(elementById);
}
}