jsoup使用教程

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

public class JsoupExample {
    public static void main(String[] args) {
        try {
            // 连接到网页并获取HTML内容
            Document doc = Jsoup.connect("https://example.com").get();

            // 使用CSS选择器查找元素
            Elements links = doc.select("a[href]");
            for (Element link : links) {
                String href = link.attr("href");
                String text = link.text();
                System.out.println("Link: " + href + ", Text: " + text);
            }

            // 修改元素内容
            Element title = doc.selectFirst("title");
            if (title != null) {
                title.text("New Title");
            }

            // 输出修改后的HTML
            System.out.println(doc.html());
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

Document doc = Jsoup.connect("https://example.com")
                    .timeout(5000) // 设置超时时间为5秒
                    .get();

Document doc = Jsoup.parse(htmlString, "", Parser.htmlParser().setTrackErrors(100));
if (doc.parser().hasErrors()) {
    System.out.println("Parsing errors: " + doc.parser().getErrors());
}

Document doc = Jsoup.connect("https://example.com")
                    .userAgent("Mozilla/5.0")
                    .timeout(5000)
                    .get();
doc.charset("UTF-8"); // 设置编码为UTF-8