Java/w10/datacollect/strategy/NewsStrategy.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;
import java.util.regex.Pattern;

public class NewsStrategy implements CrawlStrategy {
    // 使用正则匹配
    private static final Pattern URL_PATTERN = Pattern.compile(".*news\\.example\\.com.*");
    @Override
    public boolean supports(String url) {
        return URL_PATTERN.matcher(url).matches();
    }

    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();
        Elements items = doc.select(".article-headline");
        for (Element e : items) {
            articles.add(new Article(e.text(), url, ""));
        }
        return articles;
    }
    @Override
    public int getPriority(){
        return 10;
    }
}