上传文件至 'project'

project/ConsoleView.java

@@ -0,0 +1,42 @@
+package com.example.datacollect.view;
+
+import com.example.datacollect.model.Article;
+import java.util.List;
+import java.util.Scanner;
+
+public class ConsoleView {
+    private static final String ANSI_RESET = "\u001B[0m";
+    private static final String ANSI_GREEN = "\u001B[32m";
+    private static final String ANSI_RED = "\u001B[31m";
+    private static final String ANSI_BLUE = "\u001B[34m";
+
+    private final Scanner scanner = new Scanner(System.in);
+
+    public String readLine() {
+        System.out.print("> ");
+        return scanner.nextLine();
+    }
+
+    public void printSuccess(String msg) {
+        System.out.println(ANSI_GREEN + msg + ANSI_RESET);
+    }
+
+    public void printError(String msg) {
+        System.out.println(ANSI_RED + msg + ANSI_RESET);
+    }
+
+    public void printInfo(String msg) {
+        System.out.println(ANSI_BLUE + msg + ANSI_RESET);
+    }
+
+    public void display(List<Article> articles) {
+        if (articles.isEmpty()) {
+            printInfo("暂无文章，请先执行 crawl。");
+            return;
+        }
+        for (int i = 0; i < articles.size(); i++) {
+            Article a = articles.get(i);
+            System.out.println((i + 1) + ". " + a.getTitle() + " | " + a.getUrl());
+        }
+    }
+}

project/CrawlStrategy.java

@@ -0,0 +1,10 @@
+package com.example.datacollect.strategy;
+
+import com.example.datacollect.model.Article;
+import org.jsoup.nodes.Document;
+import java.util.List;
+
+public interface CrawlStrategy {
+    List<Article> parse(String url, Document doc);
+    boolean supports(String url);
+}

project/HnuNewsStrategy.java

@@ -0,0 +1,54 @@
+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 HnuNewsStrategy implements CrawlStrategy {
+    @Override
+    public boolean supports(String url) {
+        return url.contains("news.hnu.edu.cn");
+    }
+
+    @Override
+    public List<Article> parse(String url, Document doc) {
+        List<Article> articles = new ArrayList<>();
+        
+        Elements links = doc.select("a[href*='/info/']");
+        
+        for (Element link : links) {
+            String articleUrl = link.attr("abs:href");
+            
+            if (!articleUrl.startsWith("http")) {
+                articleUrl = "https://news.hnu.edu.cn" + link.attr("href").replace("..", "");
+            }
+            
+            String title = link.text().trim();
+            
+            if (title.isEmpty()) {
+                Element titleEl = link.selectFirst("h2, h3, h4, .title");
+                if (titleEl != null) {
+                    title = titleEl.text().trim();
+                }
+            }
+            
+            String content = "";
+            Element parent = link.parent();
+            if (parent != null) {
+                Element contentEl = parent.selectFirst("p, .summary, .description");
+                if (contentEl != null) {
+                    content = contentEl.text().trim();
+                }
+            }
+            
+            if (!title.isEmpty() && articleUrl.contains("/info/")) {
+                articles.add(new Article(title, articleUrl, content));
+            }
+        }
+        
+        return articles;
+    }
+}

project/NewsStrategy.java

@@ -0,0 +1,25 @@
+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 NewsStrategy implements CrawlStrategy {
+    @Override
+    public boolean supports(String url) {
+        return url.contains("news.example.com");
+    }
+
+    @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;
+    }
+}

project/StrategyFactory.java

@@ -0,0 +1,28 @@
+package com.example.datacollect.strategy;
+
+import java.util.ArrayList;
+import java.util.List;
+
+public class StrategyFactory {
+    private final List<CrawlStrategy> strategies = new ArrayList<>();
+
+    public StrategyFactory() {
+        strategies.add(new HnuNewsStrategy());
+        strategies.add(new BlogStrategy());
+        strategies.add(new NewsStrategy());
+        strategies.add(new BaiduBaikeStrategy());
+    }
+
+    public CrawlStrategy getStrategy(String url) {
+        for (CrawlStrategy s : strategies) {
+            if (s.supports(url)) {
+                return s;
+            }
+        }
+        return null;
+    }
+
+    public void register(CrawlStrategy strategy) {
+        strategies.add(strategy);
+    }
+}