1. Jsoup import org.jsoup.Jsoup; import org.jsoup.nodes.Document; import org.jsoup.nodes.Element; public class JsoupExample { public static void main(String[] args) { String html = "<html><body><a href='https://example.com'>Example</a></body></html>"; Document doc = Jsoup.parse(html); Element link = doc.select("a").first(); String url = link.attr("href"); String text = link.text(); System.out.println("URL: " + url); System.out.println("Text: " + text); } } 2. HTMLUnit import com.gargoylesoftware.htmlunit.WebClient; import com.gargoylesoftware.htmlunit.html.DomElement; import com.gargoylesoftware.htmlunit.html.HtmlPage; public class HTMLUnitExample { public static void main(String[] args) { try (final WebClient webClient = new WebClient()) { HtmlPage page = webClient.getPage("https://example.com"); DomElement link = page.getFirstByXPath("//a"); String url = link.getAttribute("href"); String text = link.getTextContent(); System.out.println("URL: " + url); System.out.println("Text: " + text); } catch (Exception e) { e.printStackTrace(); } } }


上一篇:
下一篇:
切换中文