1、环境
首先导入jar包
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.11.3</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
<version>3.7</version>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
<version>2.6</version>
</dependency>
然后准备一个用于解析的jsoup.html,放于webapp目录下
<html>
<head>
<title>传智播客官网-一样的教育,不一样的品质</title>
</head>
<body>
<div class="city">
<h3 id="city_bj">北京中心</h3>
<fb:img src="/2018czgw/images/slogan.jpg" class="slogan"/>
<div class="city_in">
<div class="city_con" style="display: none;">
<ul>
<li id="test" class="class_a class_b">
<a href="http://www.itcast.cn" target="_blank">
<span class="s_name">北京</span>
</a>
</li>
<li>
<a href="http://sh.itcast.cn" target="_blank">
<span class="s_name">上海</span>
</a>
</li>
<li>
<a href="http://gz.itcast.cn" target="_blank">
<span abc="123" class="s_name">广州</span>
</a>
</li>
<ul>
<li>天津</li>
</ul>
</ul>
</div>
</div>
</div>
</body>
</html>
2、3种获取Dom方式
2.1解析url
@Test
public void testJsoupUrl() throws Exception {
//解析url地址
Document document = Jsoup.parse(new URL("http://www.itcast.cn/"), 1000);
//获取title的内容
Element title = document.getElementsByTag("title").first();
System.out.println(title.text());
}
虽然使用Jsoup可以替代HttpClient直接发起请求解析数据,但是往往不会这样用,因为实际的开发过程中,需要使用到多线程,连接池,代理等等方式,而jsoup对这些的支持并不是很好,所以我们一般把jsoup仅仅作为Html解析工具使用
2.2解析字符串
@Test
public void testJsoupString() throws IOException {
//读取文件获取
//String html = FileUtils.readFileToString(new File("D:\\jsoup.html"), "UTF-8");
String html = IOUtils.toString(new FileInputStream("src/main/webapp/jsoup.html"), "UTF-8");
//解析字符串
Document document = Jsoup.parse(html);
//获取title的内容
Element title = document.getElementsByTag("title").first();
System.out.println(title.text());
}
2.3直接解析文件
@Test
public void testJsoupHtml() throws IOException {
//解析文件
// Document document = Jsoup.parse(new File("D:\\jsoup.html"),"UTF-8");
Document document = Jsoup.parse(new FileInputStream("src/main/webapp/jsoup.html"), "UTF-8", "");
//获取title内容
Element title = document.getElementsByTag("title").first();
System.out.println(title.text());
}
3、解析Dom方法
3.1dom方式遍历文档,获取元素
@Test
public void testDoucment() throws IOException {
String html = IOUtils.toString(new FileInputStream("src/main/webapp/jsoup.html"), "UTF-8");
Document document = Jsoup.parse(html);
//1.根据id查询元素getElementById
Element element = document.getElementById("city_bj");
System.out.println(element.text());
//2.根据标签获取元素getElementsByTag
element = document.getElementsByTag("title").first();
System.out.println(element.text());
//3.根据class获取元素getElementsByClass
//element = document.getElementsByClass("class_a").last();
// element = document.getElementsByClass("class_b").last();
element = document.getElementsByClass("class_a class_b").last();
System.out.println(element.text());
//4.根据属性获取元素getElementsByAttribute
// element = document.getElementsByAttribute("abc").first();
element = document.getElementsByAttributeValue("abc", "123").first();
System.out.println(element.text());
}
3.2元素中获取数据
@Test
public void testData() throws Exception {
String html = IOUtils.toString(new FileInputStream("src/main/webapp/jsoup.html"), "UTF-8");
Document document = Jsoup.parse(html);
Element element = document.getElementById("test");
//1.从元素中获取id
String id = element.id();
System.out.println(id);
//2.从元素中获取className
String className = element.className();
System.out.println(className);
//3.从元素中获取属性的值attr
id = element.attr("id");
System.out.println(id);
//4.从元素中获取所有属性attributes
Attributes attributes = element.attributes();
String s = attributes.toString();
System.out.println(s);
//5.从元素中获取文本内容text
System.out.println(element.text());
}
3.3select,css查找
@Test
public void testSelector() throws IOException {
String html = IOUtils.toString(new FileInputStream("src/main/webapp/jsoup.html"), "UTF-8");
Document document = Jsoup.parse(html);
//tagname: 通过标签查找元素,比如:span
Elements elements = document.select("span");
elements.forEach(element -> System.out.println(element.text()));
//#id: 通过ID查找元素,比如:#city_bjj
String text = document.select("#city_bj").text();
//.class: 通过class名称
text = document.select(".class_a").text();
//[attribute]: 利用属性查找元素,比如:[abc]
text = document.select("[abc]").text();
//[attr=value]: 利用属性值来查找元素,比如:[class=s_name]
text = document.select("[class=s_name]").text();
}
3.4select,css组合查找
@Test
public void testSelectors() throws IOException {
String html = IOUtils.toString(new FileInputStream("src/main/webapp/jsoup.html"), "UTF-8");
Document document = Jsoup.parse(html);
//el#id: 元素+ID,比如: h3#city_bj
String str = document.select("h3#city_bj").text();
System.out.println(str);
//el.class: 元素+class,比如: li.class_a
System.out.println(document.select("li.class_a").text());
//el[attr]: 元素+属性名,比如: span[abc]
System.out.println(document.select("span[abc]").text());
//任意组合: 比如:span[abc].s_name
System.out.println(document.select("span[abc].s_name").text());
//ancestor child: 查找某个元素下子元素,比如:.city_con li 查找"city_con"下的所有li
System.out.println(document.select(".city_con li").text());
//parent > child: 查找某个父元素下的直接子元素,比如:
//.city_con > ul > li 查找city_con第一级(直接子元素)的ul,再找所有ul下的第一级li
System.out.println(document.select(".city_con > ul > li").text());
//parent > *: 查找某个父元素下所有直接子元素
System.out.println(document.select(".city_con > *").text());
}