您的位置:首页 > Web前端 > JavaScript

Jsoup select 解析Html

2016-12-15 17:54 417 查看
参考API:jsoup API

测试类:

package wechat;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import utils.IOUtil;

/**
* date: 2016年12月15日
* author:ywflqq
* version:1.0
* 类说明
*/
public class CssQueryTest {

public static void main(String[] args) {
//读取文本内容
String txt = IOUtil.readDirOrFile("cssquerytest", "UTF-8");
//System.out.println(txt);
//利用Jsoup解析成document
Document doc = Jsoup.parse(txt);
//如果查找所有的超链接元素,cssQuery代码如下:<非常简洁>
Elements elements = doc.select("a");
for(Element ele:elements){
System.out.println(ele.toString());
}
System.out.println("-------------------");
//例如,我要找到超链接<a>元素..并且他的href属性的值为www.baidu.com,cssQuery代码如下:
elements = doc.select("a[href=www.baidu.com]");
for(Element ele:elements){
System.out.println(ele.toString());
}
System.out.println("-------------------");
//根据样式的名称,class中有空格时,写多个select或者将空格替换为.
//选择器选择的class有多个属性的写法
elements = doc.select("p.test.link");
for(Element ele:elements){
System.out.println(ele.toString());
}
System.out.println("-------------------");
//获得div下的<p>标签
elements = doc.select("div p");
for(Element ele:elements){
System.out.println(ele.toString());
}
System.out.println();
}
}


测试文件

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
<html>
<mce:script type="text/<a href="http://lib.csdn.net/base/javascript" class='replace_word' title="JavaScript知识库" target='_blank' style='color:#df3434; font-weight:bold;'>JavaScript</a>" src="http://hi.images.csdn<a href="http://lib.csdn.net/base/dotnet" class='replace_word' title=".NET知识库" target='_blank' style='color:#df3434; font-weight:bold;'>.NET</a>/js/blog/tiny_mce/themes/advanced/langs/zh.js" mce_src="http://hi.images.csdn<a href="http://lib.csdn.net/base/dotnet" class='replace_word' title=".NET知识库" target='_blank' style='color:#df3434; font-weight:bold;'>.Net</a>/js/blog/tiny_mce/themes/advanced/langs/zh.js"></mce:script><mce:script type="text/javascript" src="http://hi.images.csdn.net/js/blog/tiny_mce/plugins/syntaxhl/langs/zh.js" mce_src="http://hi.images.csdn.net/js/blog/tiny_mce/plugins/syntaxhl/langs/zh.js"></mce:script><head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>Untitled Document</title>
<mce:script src="cssQuery/cssQuery-p.js" mce_src="cssQuery/cssQuery-p.js"><!--

// --></mce:script>
</head>
<body lang="en">
<h2>cssQuery Test Page</h2>
<h3>
<abbr>
CSS
</abbr>
Level 1
</h3>
<pre>#test1-1 p a {background-color: lime;}</pre>
<div id="test1-1">
<p class="test link">
<span>This</span>
is a <a href="www.baidu.com" mce_href="www.baidu.com" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test1-2 :link {background-color: lime;}</pre>
<div id="test1-2">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<h3>
<abbr>
CSS
</abbr>
Level 2
</h3>
<pre>#test2-1 p.test.link a {background-color: lime;}</pre>
<div id="test2-1">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test2-2 p > a {background-color: lime;}</pre>
<div id="test2-2">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test2-3 span + a {background-color: lime;}</pre>
<div id="test2-3">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test2-4 p:first-child a {background-color: lime;}</pre>
<div id="test2-4">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test2-5 a:lang(en) {background-color: lime;}</pre>
<div id="test2-5">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test2-6 a[href] {background-color: lime;}</pre>
<div id="test2-6">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test2-7 a[title="This is a link"] {background-color: lime;}</pre>
<div id="test2-7">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test2-8 a[title~="is"] {background-color: lime;}</pre>
<div id="test2-8">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>div[id|=test2-9] a {background-color: lime;}</pre>
<div id="test2-9">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<h3>
<abbr>
CSS
</abbr>
Level 3
</h3>
<pre>#test3-1 span ~ a {background-color: lime;}</pre>
<div id="test3-1">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-2 p:last-child a {background-color: lime;}</pre>
<div id="test3-2">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-3 a:contains("test") {background-color: lime;}</pre>
<div id="test3-3">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-4 p :not(span) {background-color: lime;}</pre>
<div id="test3-4">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-5 p:only-child a {background-color: lime;}</pre>
<div id="test3-5">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-6 p *:nth-child(even) {background-color: lime;}</pre>
<div id="test3-6">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-7 p *:nth-last-child(2n+1) {background-color: lime;}</pre>
<div id="test3-7">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>:root #test3-8 a {background-color: lime;}</pre>
<div id="test3-8">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-9 a[title^="This"] {background-color: lime;}</pre>
<div id="test3-9">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-10 a[title*="is a"] {background-color: lime;}</pre>
<div id="test3-10">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
<pre>#test3-11 a[title$="link"] {background-color: lime;}</pre>
<div id="test3-11">
<p class="test link">
<span>This</span>
is a <a href="#" mce_href="#" title="This is a link">test</a>
link.
</p>
</div>
</body>
</html>
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: