Java爬虫：Jsoup解析HTML

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.13.1</version>
</dependency>

String html = "<div><p>this is a text</p></div>";
// 解析字符串
Document doc = Jsoup.parse(html);
System.out.println(doc);
// 解析Html片段
Document fragment = Jsoup.parseBodyFragment(html);
System.out.println(fragment);
// 从Url解析
Document doc = Jsoup.connect("https://www.baidu.com/").get();
System.out.println(doc.title());
// 使用css解析器
Element element = doc.selectFirst("title");
System.out.println(element.text());