1. 解析
-
解析:操作xml文档,将文档中的数据读取到内存中
-
操作xml文档
1. 解析(读取):将文档中的数据读取到内存中
2. 写入:将内存中的数据保存到xml文档中。持久化的存储 -
解析xml的方式:
1. DOM:将标记语言文档一次性加载进内存,在内存中形成一颗dom树
* 优点:操作方便,可以对文档进行CRUD的所有操作
* 缺点:占内存
2. SAX:逐行读取,基于事件驱动的。
* 优点:不占内存。
* 缺点:只能读取,不能增删改 -
xml常见的解析器:
- JAXP:sun公司提供的解析器,支持dom和sax两种思想
- DOM4J:一款非常优秀的解析器
- Jsoup:jsoup 是一款Java 的HTML解析器,可直接解析某个URL地址、HTML文本内容。它提供了一套非常省力的API,可通过DOM,CSS以及类似于jQuery的操作方法来取出和操作数据。
- PULL:Android操作系统内置的解析器,sax方式的。
2. Jsoup
-
Jsoup:jsoup 是一款Java 的HTML解析器,可直接解析某个URL地址、HTML文本内容。它提供了一套非常省力的API,可通过DOM,CSS以及类似于jQuery的操作方法来取出和操作数据。
-
步骤:
1. 导入jar包
2. 获取Document对象
3. 获取对应的标签Element对象
4. 获取数据 -
XML文件(student.xml)
<?xml version="1.0" encoding="UTF-8" ?>
<students>
<student number="siyi_0001">
<name id="1">
<xing>张</xing>
<ming>三</ming>
</name>
<age>18</age>
<sex>male</sex>
</student>
<student number="siyi_0002">
<name>jack</name>
<age>18</age>
<sex>male</sex>
</student>
</students>
- Demo1
package 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 {
//2.获取Document对象,根据XML文档获取
//2.1获取student.xml的path
String path = JsoupDemo1.class.getClassLoader().getResource("student.xml").getPath();
//2.2解析xml文档,加载文档进内存,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name的Element对象
Element element = elements.get(0);
//3.2获取数据
String name = element.text();
System.out.println(name);
}
}
运行结果:
- Demo2
package jsoup;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import java.io.IOException;
import java.net.URL;
public class JsoupDemo2 {
public static void main(String[] args) throws IOException {
//2.1获取student.xml的path
String path = JsoupDemo2.class.getClassLoader().getResource("student.xml").getPath();
//2.2解析xml文档,加载文档进内存,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html字符串
/*String str = "<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n" +
"\n" +
" <students>\n" +
" \t<student number=\"siyi_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=\"siyi_0002\">\n" +
"\t\t<name>jack</name>\n" +
"\t\t<age>18</age>\n" +
"\t\t<sex>male</sex>\n" +
"\t</student>\n" +
"\n" +
" </students>";
Document document = Jsoup.parse(str);
System.out.println(document);*/
//3.parse(URL url,int timeoutMillis):通过网络路径获取指定的html或xml的文档对象
URL url = new URL("https://baike.baidu.com/item/jsoup/9012509?fr=aladdin");//代表网络种的一个资源
Document document = Jsoup.parse(url,5000);
System.out.println(document);
}
}
运行结果(百度百科标签太多,就不全截屏了):
- Demo3
package 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 JsoupDemo3 {
public static void main(String[] args) throws IOException {
//1.获取student.xml的path
String path = JsoupDemo3.class.getClassLoader().getResource("student.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
Elements elements1 = document.getElementsByAttribute("id");
System.out.println(elements1);
System.out.println("-------------------");
//3.3获取属性值为heima_0001的元素对象
Elements elementsByAttributeValue = document.getElementsByAttributeValue("number", "siyi_0001");
System.out.println(elementsByAttributeValue);
System.out.println("-------------------");
Element elementById = document.getElementById("1");
System.out.println(elementById);
}
}
运行结果:
- Demo4
package 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 JsoupDemo4 {
public static void main(String[] args) throws IOException {
//1.获取student.xml的path
String path = JsoupDemo4.class.getClassLoader().getResource("student.xml").getPath();
//2.获取Document对象
Document document = Jsoup.parse(new File(path), "utf-8");
//通过document对象获取name标签,获取所有的name标签
Elements elements = document.getElementsByTag("name");
System.out.println(elements.size());
System.out.println("------------");
Element ele_student = document.getElementsByTag("student").get(0);
Elements ele_name = ele_student.getElementsByTag("name");
System.out.println(ele_name.size());
System.out.println("------------");
//获取student对象的属性值
String number = ele_student.attr("number");
System.out.println(number);
System.out.println("------------");
//获取文本内容
String text = ele_name.text();
String html = ele_name.html();
System.out.println(text);
System.out.println(html);
}
}
运行结果:
- Demo5
package 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 JsoupDemo5 {
public static void main(String[] args) throws IOException {
//1.获取student.xml的path
String path = JsoupDemo5.class.getClassLoader().getResource("student.xml").getPath();
//2.获取Document对象
Document document = Jsoup.parse(new File(path), "utf-8");
//3.查询name标签
Elements elements = document.select("name");
System.out.println(elements);
System.out.println("--------");
//4.查询id值为1的元素
Elements elements1 = document.select("#1");
System.out.println(elements1);
System.out.println("--------");
//5.获取student标签并且number属性值为siyi_0001的age子标签
//5.1获取student标签并且number属性值为siyi_0001
Elements elements2 = document.select("student[number='siyi_0001']");
System.out.println(elements2);
System.out.println("--------");
//5.2获取student标签并且number属性值为siyi_0001的age子标签
Elements elements3 = document.select("student[number='siyi_0001']>age");
System.out.println(elements3);
}
}
运行结果:
- Demo6
package jsoup;
import cn.wanghaomiao.xpath.exception.XpathSyntaxErrorException;
import cn.wanghaomiao.xpath.model.JXDocument;
import cn.wanghaomiao.xpath.model.JXNode;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
import java.io.File;
import java.io.IOException;
import java.util.List;
public class JsoupDemo6 {
public static void main(String[] args) throws IOException, XpathSyntaxErrorException {
//1.获取student.xml的path
String path = JsoupDemo6.class.getClassLoader().getResource("student.xml").getPath();
//2.获取Document对象
Document document = Jsoup.parse(new File(path), "utf-8");
//3.根据document对象,创建JXDocument对象
JXDocument jxDocument = new JXDocument(document);
//结合Xpath语法查询
//4.1查询所有的student标签
List<JXNode> jxNodes = jxDocument.selN("//student");
for (JXNode jxNode : jxNodes){
System.out.println(jxNode);
}
System.out.println("--------");
//4.2查询
List<JXNode> jxNodes1 = jxDocument.selN("//student/name");
for (JXNode jxNode:jxNodes1) {
System.out.println(jxNode);
}
System.out.println("--------");
//4.3查询student标签下带有id属性的name标签
List<JXNode> jxNodes2 = jxDocument.selN("//student/name[@id]");
for (JXNode jxNode:jxNodes2) {
System.out.println(jxNode);
}
System.out.println("--------");
//4.4查询student标签下带有id属性的name标签 并且id属性值为1
List<JXNode> jxNodes3 = jxDocument.selN("//student/name[@id='1']");
for (JXNode jxNode:jxNodes3) {
System.out.println(jxNode);
}
}
}
运行结果: