Java/w10/datacollect/strategy/DefaultStrategy.java

package com.example.datacollect.strategy;
import com.example.datacollect.model.Article;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.util.ArrayList;
import java.util.List;
public class DefaultStrategy implements  CrawlStrategy{
    @Override
    public boolean supports(String url) {
        return true; // 兜底策略
    }
    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();
        // 通用逻辑：提取所有 h1 或 h2 作为标题
        Elements titles = doc.select("h1, h2");
        for (Element e : titles) {
            articles.add(new Article(e.text(), url, ""));
        }
        return articles;
    }
    @Override
    public int getPriority() {
        return -1; // 优先级最低
    }
}