添加 'w10/Article.java'

w10/Article.java

@@ -0,0 +1,153 @@
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import java.time.LocalDate;
+import java.util.ArrayList;
+import java.util.List;
+
+public class Article {
+    private String title;
+    private String content;
+    private String url;
+    private String author;
+    private LocalDate publishDate;
+
+    public Article(String title, String content, String url, String author, LocalDate publishDate) {
+        this.title = title;
+        this.content = content;
+        this.url = url;
+        this.author = author;
+        this.publishDate = publishDate;
+    }
+
+    public String getAuthor() { return author; }
+    public void setAuthor(String author) { this.author = author; }
+
+    public LocalDate getPublishDate() { return publishDate; }
+    public void setPublishDate(LocalDate publishDate) { this.publishDate = publishDate; }
+
+    @Override
+    public String toString() {
+        return "标题：" + title +
+                " | 作者：" + author +
+                " | 发布日期：" + publishDate +
+                " | 链接：" + url;
+    }
+}
+
+interface CrawlStrategy {
+    List<Article> crawl();
+}
+
+class BaiduCrawl implements CrawlStrategy {
+    @Override
+    public List<Article> crawl() {
+        List<Article> articleList = new ArrayList<>();
+        try {
+            Document doc = Jsoup.connect("https://top.baidu.com/board?tab=realtime")
+                    .userAgent("Mozilla/5.0")
+                    .timeout(5000)
+                    .get();
+            Elements items = doc.getElementsByClass("category-wrap_iQLoo horizontal_1eKyQ");
+            int count = 0;
+            for (Element item : items) {
+                if (count >= 8) break;
+                String title = item.getElementsByClass("c-single-text-ellipsis").text();
+                String link = item.select("a").attr("href");
+                String fullUrl = "https://top.baidu.com" + link;
+                Article article = new Article(title, "", fullUrl, "百度热搜", LocalDate.now());
+                articleList.add(article);
+                count++;
+            }
+        } catch (Exception e) {
+            System.out.println("百度热搜爬取失败");
+        }
+        return articleList;
+    }
+}
+
+class PeopleCrawl implements CrawlStrategy {
+    @Override
+    public List<Article> crawl() {
+        List<Article> articleList = new ArrayList<>();
+        try {
+            Document doc = Jsoup.connect("http://www.people.com.cn/GB/59476/review/20260514.html")
+                    .userAgent("Mozilla/5.0")
+                    .timeout(5000)
+                    .get();
+            Elements links = doc.select("a[href^=http://politics.people.com.cn]");
+            int count = 0;
+            for (Element link : links) {
+                if (count >= 5) break;
+                String title = link.text();
+                String url = link.attr("href");
+                if (!title.isEmpty()) {
+                    Article article = new Article(title, "", url, "人民网", LocalDate.now());
+                    articleList.add(article);
+                    count++;
+                }
+            }
+        } catch (Exception e) {
+            System.out.println("人民网新闻爬取失败");
+        }
+        return articleList;
+    }
+}
+
+class StrategyFactory {
+    public static CrawlStrategy getCrawlStrategy(String type) {
+        if ("baidu".equalsIgnoreCase(type)) {
+            return new BaiduCrawl();
+        } else if ("people".equalsIgnoreCase(type)) {
+            return new PeopleCrawl();
+        }
+        return null;
+    }
+}
+
+class ArticleRepository {
+    private final List<Article> allArticles = new ArrayList<>();
+
+    public void saveArticles(List<Article> list) {
+        allArticles.addAll(list);
+    }
+
+    public List<Article> getAllArticles() {
+        return allArticles;
+    }
+}
+
+interface Command {
+    void execute();
+}
+
+class CrawlCommand implements Command {
+    private final CrawlStrategy strategy;
+    private final ArticleRepository repository;
+
+    public CrawlCommand(CrawlStrategy strategy, ArticleRepository repository) {
+        this.strategy = strategy;
+        this.repository = repository;
+    }
+
+    @Override
+    public void execute() {
+        List<Article> articles = strategy.crawl();
+        repository.saveArticles(articles);
+         articles.forEach(System.out::println);
+     }
+ }
+ class CrawlMain {
+     public static void main(String[] args) {
+         ArticleRepository repository = new ArticleRepository();
+         System.out.println("===== 百度实时热搜 =====");
+         Command baiduCmd = new CrawlCommand(StrategyFactory.getCrawlStrategy("baidu"), repository);
+         baiduCmd.execute();
+         System.out.println("\n===== 人民网头条 =====");
+         Command peopleCmd = new CrawlCommand(StrategyFactory.getCrawlStrategy("people"), repository);
+         peopleCmd.execute();
+         System.out.println("\n===== 全部新闻汇总 =====");
+         repository.getAllArticles().forEach(System.out::println);
+     }
+ }