java/project/BaiduBaikeStrategy.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 BaiduBaikeStrategy implements CrawlStrategy {
    @Override
    public boolean supports(String url) {
        return url.contains("baike.baidu.com");
    }

    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();
        
        String title = doc.selectFirst("h1.lemma-title, h1.title-text") != null 
            ? doc.selectFirst("h1.lemma-title, h1.title-text").text().trim() 
            : "";
        
        String content = "";
        Element contentEl = doc.selectFirst("div.lemma-summary, div.summary-content, div.j-summary");
        if (contentEl != null) {
            content = contentEl.text().trim();
        }
        
        if (!title.isEmpty()) {
            articles.add(new Article(title, url, content));
        }
        
        Elements relatedLinks = doc.select("a[href*='/item/']");
        for (Element link : relatedLinks) {
            String linkUrl = link.attr("abs:href");
            String linkTitle = link.text().trim();
            
            if (!linkTitle.isEmpty() && !linkTitle.contains("编辑") && !linkTitle.contains("分享")) {
                articles.add(new Article(linkTitle, linkUrl, ""));
            }
        }
        
        return articles;
    }
}