xml解析器_Jsoup_快速入门、Jsoup对象
xml解析器_Jsoup_快速入门
导jar包,右击libs,点击添加为库,选择模块库即可
package cn.itcast.xml.jsoup; 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; public class jsoupDemo1 { public static void main(String[] args) throws IOException { //获取Document对象,根据xml文档获取 //获取student.xml的path String path = jsoupDemo1.class.getClassLoader().getResource("student.xml").getPath(); //解析xml文档,加载文档进内存,获取dom树 Document parse = Jsoup.parse(new File(path), "utf-8"); //获取元素对象 Elements element = parse.getElementsByTag("name"); System.out.println(element.size()); //获取第一个那么的Element对象 Element element1 = element.get(0); //获取数据 String text = element1.text(); System.out.println(text); } }
xml解析器_Jsoup对象
Jsoup:工具类,可以解析html或xml文档,返回Document
parse:解析html或xml文档,返回Document
parse(File in,String charsetName):解析xml或html文件的
parse(String html):解析xml或html字符串
parse(URL url,int timeoutMillis):通过网络路径获取指定的html或xml的文档对象
Dovument:文档对象,代表内存中的dom树
Elements:元素 Element对象的集合,可以当做ArrayList<Element>来使用
Element:元素对象
Node:节点对象
package cn.itcast.xml.jsoup; 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; import java.net.URL; public class jsoupDemo2 { public static void main(String[] args) throws IOException { //获取Document对象,根据xml文档获取 //获取student.xml的path String path = jsoupDemo2.class.getClassLoader().getResource("student.xml").getPath(); String str = "<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n" + "\n" + "<students>\n" + "\n" + "\t<student number=\"heima_0001\">\n" + "\t\t<name>tom</name>\n" + "\t\t<age>18</age>\n" + "\t\t<sex>male</sex>\n" + "\t</student>\n" + "\t<student number=\"heima_0002\">\n" + "\t\t<name>jack</name>\n" + "\t\t<age>18</age>\n" + "\t\t<sex>female</sex>\n" + "\t</student>\n" + "\n" + "</students>"; Document parse = Jsoup.parse(str); System.out.println(parse); } }
package cn.itcast.xml.jsoup; 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; import java.net.URL; public class jsoupDemo2 { public static void main(String[] args) throws IOException { //获取Document对象,根据xml文档获取 //获取student.xml的path String path = jsoupDemo2.class.getClassLoader().getResource("student.xml").getPath(); /*String str = "<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n" + "\n" + "<students>\n" + "\n" + "\t<student number=\"heima_0001\">\n" + "\t\t<name>tom</name>\n" + "\t\t<age>18</age>\n" + "\t\t<sex>male</sex>\n" + "\t</student>\n" + "\t<student number=\"heima_0002\">\n" + "\t\t<name>jack</name>\n" + "\t\t<age>18</age>\n" + "\t\t<sex>female</sex>\n" + "\t</student>\n" + "\n" + "</students>"; Document parse = Jsoup.parse(str); System.out.println(parse);*/ URL url = new URL("https://www.1688.com/"); Document parse = Jsoup.parse(url, 10000); System.out.println(parse); } }