w10

w10/Main.java

@@ -0,0 +1,21 @@
+package com.example.datacollect;
+
+import com.example.datacollect.controller.CrawlerController;
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.strategy.StrategyFactory;
+import com.example.datacollect.view.ConsoleView;
+
+public class Main {
+
+    public static void main(String[] args) {
+        ConsoleView view = new ConsoleView();
+        ArticleRepository repository = new ArticleRepository();
+        StrategyFactory strategyFactory = new StrategyFactory();
+        CrawlerController controller = new CrawlerController(view, repository, strategyFactory);
+
+        view.printSuccess("Welcome to CLI Crawler (w10_3)! Type help for commands.");
+        while (true) {
+            controller.handle(view.readLine());
+        }
+    }
+}

w10/README.md

@@ -0,0 +1,144 @@
+# W10 作业提交：设计模式实战
+
+## 目录结构
+
+```
+w10/
+└── src/
+    └── main/
+        └── java/
+            └── com/
+                └── example/
+                    └── datacollect/
+                        ├── Main.java
+                        ├── command/
+                        │   ├── Command.java
+                        │   ├── CrawlCommand.java
+                        │   ├── AnalyzeCommand.java
+                        │   ├── ListCommand.java
+                        │   ├── HelpCommand.java
+                        │   ├── ExitCommand.java
+                        │   └── HistoryCommand.java
+                        ├── controller/
+                        │   └── CrawlerController.java
+                        ├── model/
+                        │   └── Article.java
+                        ├── repository/
+                        │   └── ArticleRepository.java
+                        ├── strategy/
+                        │   ├── CrawlStrategy.java
+                        │   ├── StrategyFactory.java
+                        │   ├── HnuNewsStrategy.java
+                        │   ├── BlogStrategy.java
+                        │   ├── NewsStrategy.java
+                        │   └── GenericNewsStrategy.java
+                        └── view/
+                            └── ConsoleView.java
+```
+
+## 必做任务完成情况
+
+### 1. ArticleRepository 完善 ✅
+- `add()`: 拒绝 null，抛出 IllegalArgumentException
+- `addAll()`: 拒绝 null 列表和列表中的 null 元素
+- `getAll()`: 返回 `Collections.unmodifiableList()` 不可变视图
+- `size()`: 返回文章数量
+- `clear()`: 清空所有文章
+
+### 2. AnalyzeCommand ✅
+- 复用策略解析但**不存储**到 Repository
+- 输出统计信息：文章总数、含作者/日期/内容的数量、使用的策略名称
+- 显示前 3 篇文章标题作为预览
+
+### 3. AI 架构审计 ✅
+
+#### 类签名汇总
+
+```java
+// Command 层
+interface Command { void execute(String[], ArticleRepository); }
+class CrawlCommand(ConsoleView, StrategyFactory)
+class AnalyzeCommand(ConsoleView, StrategyFactory)
+class ListCommand(ConsoleView)
+class HelpCommand(ConsoleView)
+class ExitCommand(ConsoleView)
+class HistoryCommand(ConsoleView, List<String>)
+
+// Controller 层
+class CrawlerController(ConsoleView, ArticleRepository, StrategyFactory)
+
+// Repository 层
+class ArticleRepository { add(), addAll(), getAll(), size(), clear() }
+
+// Strategy 层  
+interface CrawlStrategy { parse(), supports(), getPriority(), getPattern() }
+class StrategyFactory { getStrategy(url), register(), setDefaultStrategy() }
+class HnuNewsStrategy implements CrawlStrategy
+class BlogStrategy implements CrawlStrategy
+class NewsStrategy implements CrawlStrategy
+class GenericNewsStrategy implements CrawlStrategy (正则匹配)
+
+// Model 层
+class Article { title, url, content, author, publishDate }
+
+// View 层
+class ConsoleView
+```
+
+#### 架构审计结果
+
+| 检查项 | 结果 | 说明 |
+|--------|------|------|
+| **策略解耦** | ✅ 优秀 | 策略接口与实现完全分离 |
+| **Repository 封装** | ✅ 优秀 | 使用不可变视图 + null 防御 |
+| **开闭原则** | ✅ 达标 | 新增网站只需加策略类 + 注册一行 |
+| **依赖倒置** | ✅ 良好 | Command/Strategy 依赖抽象接口 |
+| **单一职责** | ✅ 达标 | 每个类职责清晰 |
+| **循环依赖** | ✅ 无 | 依赖链单向 |
+
+## 选做任务完成情况
+
+### 正则策略匹配 ✅
+- `GenericNewsStrategy` 使用正则表达式 `.*\.(news|press|article)s?\..*` 匹配新闻类网站
+
+### 默认策略 ✅
+- `StrategyFactory` 内置 `DefaultStrategy`，当没有匹配策略时返回空列表
+
+### 策略优先级 ✅
+- `CrawlStrategy` 接口新增 `getPriority()` 默认方法
+- `GenericNewsStrategy` 设置优先级为 5（高于默认优先级 1）
+- `StrategyFactory.getStrategy()` 遍历所有策略，选择优先级最高的匹配策略
+
+### 思考题答案
+
+**Q: 两个策略都 supports 同一 URL 时怎么办？**
+
+**A:** 采用**优先级机制**解决：
+
+1. 每个策略实现可以通过 `getPriority()` 返回优先级值
+2. `StrategyFactory.getStrategy()` 遍历所有策略时，记录最高优先级
+3. 如果多个策略都支持同一 URL，选择优先级最高的那个
+4. 如果优先级相同，选择最先注册的策略（遍历顺序决定）
+
+这种设计的优势：
+- 允许通用策略（如 `GenericNewsStrategy`）和专用策略（如 `HnuNewsStrategy`）共存
+- 专用策略可设置更高优先级，确保精确匹配优先
+- 通用策略作为兜底，提高系统兼容性
+
+## 命令功能对比
+
+| 命令 | 功能 | 是否存储 |
+|------|------|----------|
+| `crawl <url>` | 爬取并存储文章 | ✅ 是 |
+| `analyze <url>` | 分析文章统计（不存储） | ❌ 否 |
+| `list` | 列出已存储文章 | - |
+| `history` | 显示命令历史 | - |
+| `help` | 显示帮助 | - |
+| `exit` | 退出程序 | - |
+
+## 设计模式应用
+
+1. **策略模式**：`CrawlStrategy` 接口定义标准，各策略独立实现
+2. **工厂模式**：`StrategyFactory` 根据 URL 自动选择策略
+3. **Repository 模式**：数据访问封装，防御式编程
+4. **命令模式**：所有 Command 统一签名，易于扩展

w10/command/AnalyzeCommand.java

@@ -0,0 +1,87 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.model.Article;
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.strategy.CrawlStrategy;
+import com.example.datacollect.strategy.StrategyFactory;
+import com.example.datacollect.view.ConsoleView;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+
+import java.util.List;
+
+public class AnalyzeCommand implements Command {
+    private final ConsoleView view;
+    private final StrategyFactory strategyFactory;
+
+    public AnalyzeCommand(ConsoleView view, StrategyFactory strategyFactory) {
+        this.view = view;
+        this.strategyFactory = strategyFactory;
+    }
+
+    @Override
+    public String getName() {
+        return "analyze";
+    }
+
+    @Override
+    public void execute(String[] args, ArticleRepository repository) {
+        if (args.length < 2) {
+            view.printError("Usage: analyze <url>");
+            return;
+        }
+        String url = args[1];
+
+        CrawlStrategy strategy = strategyFactory.getStrategy(url);
+        if (strategy == null) {
+            view.printError("No strategy found for: " + url);
+            return;
+        }
+
+        try {
+            view.printInfo("Analyzing: " + url);
+            Document doc = Jsoup.connect(url).get();
+            List<Article> parsed = strategy.parse(url, doc);
+
+            view.printInfo("=== Analysis Report ===");
+            view.printInfo("Total articles found: " + parsed.size());
+
+            int titlesWithAuthor = 0;
+            int titlesWithDate = 0;
+            int titlesWithContent = 0;
+
+            for (Article article : parsed) {
+                if (article.getAuthor() != null && !article.getAuthor().isEmpty()) {
+                    titlesWithAuthor++;
+                }
+                if (article.getPublishDate() != null && !article.getPublishDate().isEmpty()) {
+                    titlesWithDate++;
+                }
+                if (article.getContent() != null && !article.getContent().isEmpty()) {
+                    titlesWithContent++;
+                }
+            }
+
+            view.printInfo("Articles with author: " + titlesWithAuthor);
+            view.printInfo("Articles with publish date: " + titlesWithDate);
+            view.printInfo("Articles with content: " + titlesWithContent);
+            view.printInfo("Strategy used: " + strategy.getClass().getSimpleName());
+
+            if (parsed.size() > 0) {
+                view.printInfo("\nSample article titles:");
+                int limit = Math.min(3, parsed.size());
+                for (int i = 0; i < limit; i++) {
+                    view.printInfo("- " + parsed.get(i).getTitle());
+                }
+                if (parsed.size() > 3) {
+                    view.printInfo("... and " + (parsed.size() - 3) + " more");
+                }
+            }
+
+            view.printSuccess("Analysis completed (not stored)");
+
+        } catch (Exception e) {
+            view.printError("Failed to analyze: " + e.getMessage());
+        }
+    }
+}

w10/command/Command.java

@@ -0,0 +1,8 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.repository.ArticleRepository;
+
+public interface Command {
+    String getName();
+    void execute(String[] args, ArticleRepository repository);
+}

w10/command/CrawlCommand.java

@@ -0,0 +1,50 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.strategy.CrawlStrategy;
+import com.example.datacollect.strategy.StrategyFactory;
+import com.example.datacollect.view.ConsoleView;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+
+public class CrawlCommand implements Command {
+    private final ConsoleView view;
+    private final StrategyFactory strategyFactory;
+
+    public CrawlCommand(ConsoleView view, StrategyFactory strategyFactory) {
+        this.view = view;
+        this.strategyFactory = strategyFactory;
+    }
+
+    @Override
+    public String getName() {
+        return "crawl";
+    }
+
+    @Override
+    public void execute(String[] args, ArticleRepository repository) {
+        if (args.length < 2) {
+            view.printError("Usage: crawl <url>");
+            return;
+        }
+        String url = args[1];
+
+        CrawlStrategy strategy = strategyFactory.getStrategy(url);
+        if (strategy == null) {
+            view.printError("No strategy found for: " + url);
+            return;
+        }
+
+        try {
+            view.printInfo("Crawling: " + url);
+            Document doc = Jsoup.connect(url).get();
+            var articles = strategy.parse(url, doc);
+            for (var article : articles) {
+                repository.add(article);
+            }
+            view.printSuccess("Crawled " + articles.size() + " articles.");
+        } catch (Exception e) {
+            view.printError("Failed to crawl: " + e.getMessage());
+        }
+    }
+}

w10/command/ExitCommand.java

@@ -0,0 +1,23 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.view.ConsoleView;
+
+public class ExitCommand implements Command {
+    private final ConsoleView view;
+
+    public ExitCommand(ConsoleView view) {
+        this.view = view;
+    }
+
+    @Override
+    public String getName() {
+        return "exit";
+    }
+
+    @Override
+    public void execute(String[] args, ArticleRepository repository) {
+        view.printSuccess("Bye!");
+        System.exit(0);
+    }
+}

w10/command/HelpCommand.java

@@ -0,0 +1,28 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.view.ConsoleView;
+
+public class HelpCommand implements Command {
+    private final ConsoleView view;
+
+    public HelpCommand(ConsoleView view) {
+        this.view = view;
+    }
+
+    @Override
+    public String getName() {
+        return "help";
+    }
+
+    @Override
+    public void execute(String[] args, ArticleRepository repository) {
+        view.printInfo("Commands:");
+        view.printInfo("  crawl <url>     - Crawl articles from URL and store");
+        view.printInfo("  analyze <url>   - Analyze URL without storing");
+        view.printInfo("  list            - List all stored articles");
+        view.printInfo("  history         - Show command history");
+        view.printInfo("  help            - Show this help");
+        view.printInfo("  exit            - Exit the program");
+    }
+}

w10/command/HistoryCommand.java

@@ -0,0 +1,33 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.view.ConsoleView;
+
+import java.util.List;
+
+public class HistoryCommand implements Command {
+    private final ConsoleView view;
+    private final List<String> commandHistory;
+
+    public HistoryCommand(ConsoleView view, List<String> commandHistory) {
+        this.view = view;
+        this.commandHistory = commandHistory;
+    }
+
+    @Override
+    public String getName() {
+        return "history";
+    }
+
+    @Override
+    public void execute(String[] args, ArticleRepository repository) {
+        if (commandHistory.isEmpty()) {
+            view.printInfo("No command history.");
+            return;
+        }
+        view.printInfo("Command history:");
+        for (int i = 0; i < commandHistory.size(); i++) {
+            view.printInfo((i + 1) + ". " + commandHistory.get(i));
+        }
+    }
+}

w10/command/ListCommand.java

@@ -0,0 +1,22 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.view.ConsoleView;
+
+public class ListCommand implements Command {
+    private final ConsoleView view;
+
+    public ListCommand(ConsoleView view) {
+        this.view = view;
+    }
+
+    @Override
+    public String getName() {
+        return "list";
+    }
+
+    @Override
+    public void execute(String[] args, ArticleRepository repository) {
+        view.display(repository.getAll());
+    }
+}

w10/controller/CrawlerController.java

@@ -0,0 +1,56 @@
+package com.example.datacollect.controller;
+
+import com.example.datacollect.command.AnalyzeCommand;
+import com.example.datacollect.command.Command;
+import com.example.datacollect.command.CrawlCommand;
+import com.example.datacollect.command.ExitCommand;
+import com.example.datacollect.command.HelpCommand;
+import com.example.datacollect.command.HistoryCommand;
+import com.example.datacollect.command.ListCommand;
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.strategy.StrategyFactory;
+import com.example.datacollect.view.ConsoleView;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+public class CrawlerController {
+    private final Map<String, Command> commands = new HashMap<>();
+    private final ConsoleView view;
+    private final ArticleRepository repository;
+    private final List<String> commandHistory = new ArrayList<>();
+
+    public CrawlerController(ConsoleView view, ArticleRepository repository, StrategyFactory strategyFactory) {
+        this.view = view;
+        this.repository = repository;
+        register(new HelpCommand(view));
+        register(new ListCommand(view));
+        register(new CrawlCommand(view, strategyFactory));
+        register(new AnalyzeCommand(view, strategyFactory));
+        register(new ExitCommand(view));
+        register(new HistoryCommand(view, commandHistory));
+    }
+
+    private void register(Command command) {
+        commands.put(command.getName(), command);
+    }
+
+    public void handle(String input) {
+        String text = input == null ? "" : input.trim();
+        if (text.isEmpty()) {
+            return;
+        }
+
+        commandHistory.add(text);
+
+        String[] args = text.split("\\s+");
+        String cmdName = args[0].toLowerCase();
+        Command command = commands.get(cmdName);
+        if (command == null) {
+            view.printError("Unknown command: " + cmdName);
+            return;
+        }
+        command.execute(args, repository);
+    }
+}

w10/model/Article.java

@@ -0,0 +1,73 @@
+package com.example.datacollect.model;
+
+public class Article {
+    private String title;
+    private String url;
+    private String content;
+    private String author;
+    private String publishDate;
+
+    public Article(String title, String url, String content) {
+        this.title = title;
+        this.url = url;
+        this.content = content;
+    }
+
+    public Article(String title, String url, String content, String author, String publishDate) {
+        this.title = title;
+        this.url = url;
+        this.content = content;
+        this.author = author;
+        this.publishDate = publishDate;
+    }
+
+    public String getTitle() {
+        return title;
+    }
+
+    public void setTitle(String title) {
+        this.title = title;
+    }
+
+    public String getUrl() {
+        return url;
+    }
+
+    public void setUrl(String url) {
+        this.url = url;
+    }
+
+    public String getContent() {
+        return content;
+    }
+
+    public void setContent(String content) {
+        this.content = content;
+    }
+
+    public String getAuthor() {
+        return author;
+    }
+
+    public void setAuthor(String author) {
+        this.author = author;
+    }
+
+    public String getPublishDate() {
+        return publishDate;
+    }
+
+    public void setPublishDate(String publishDate) {
+        this.publishDate = publishDate;
+    }
+
+    @Override
+    public String toString() {
+        return "Article{"
+                + "title='" + title + '\''
+                + ", url='" + url + '\''
+                + ", author='" + author + '\''
+                + ", publishDate='" + publishDate + '\''
+                + '}';
+    }
+}

w10/repository/ArticleRepository.java

@@ -0,0 +1,41 @@
+package com.example.datacollect.repository;
+
+import com.example.datacollect.model.Article;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+public class ArticleRepository {
+    private final List<Article> articles = new ArrayList<>();
+
+    public void add(Article article) {
+        if (article == null) {
+            throw new IllegalArgumentException("Article cannot be null");
+        }
+        articles.add(article);
+    }
+
+    public void addAll(List<Article> newArticles) {
+        if (newArticles == null) {
+            throw new IllegalArgumentException("Article list cannot be null");
+        }
+        for (Article article : newArticles) {
+            if (article == null) {
+                throw new IllegalArgumentException("Article in list cannot be null");
+            }
+            articles.add(article);
+        }
+    }
+
+    public List<Article> getAll() {
+        return Collections.unmodifiableList(articles);
+    }
+
+    public int size() {
+        return articles.size();
+    }
+
+    public void clear() {
+        articles.clear();
+    }
+}

w10/strategy/BlogStrategy.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 BlogStrategy implements CrawlStrategy {
+    @Override
+    public boolean supports(String url) {
+        return url.contains("blog.example.com");
+    }
+
+    @Override
+    public List<Article> parse(String url, Document doc) {
+        List<Article> articles = new ArrayList<>();
+        Elements titles = doc.select(".post-title");
+        for (Element e : titles) {
+            articles.add(new Article(e.text(), url, ""));
+        }
+        return articles;
+    }
+}

w10/strategy/CrawlStrategy.java

@@ -0,0 +1,19 @@
+package com.example.datacollect.strategy;
+
+import com.example.datacollect.model.Article;
+import org.jsoup.nodes.Document;
+import java.util.List;
+import java.util.regex.Pattern;
+
+public interface CrawlStrategy {
+    List<Article> parse(String url, Document doc);
+    boolean supports(String url);
+    
+    default int getPriority() {
+        return 1;
+    }
+    
+    default Pattern getPattern() {
+        return null;
+    }
+}

w10/strategy/GenericNewsStrategy.java

@@ -0,0 +1,57 @@
+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 GenericNewsStrategy implements CrawlStrategy {
+    private static final Pattern PATTERN = Pattern.compile(".*\\.(news|press|article)s?\\..*");
+    private static final int PRIORITY = 5;
+
+    @Override
+    public boolean supports(String url) {
+        return PATTERN.matcher(url).find();
+    }
+
+    @Override
+    public List<Article> parse(String url, Document doc) {
+        List<Article> articles = new ArrayList<>();
+        
+        Elements items = doc.select("article, .news-item, .article-item, [class*='news'], [class*='article']");
+        
+        for (Element item : items) {
+            String title = item.selectFirst("h1, h2, h3, .title, [class*='title']") != null 
+                ? item.selectFirst("h1, h2, h3, .title, [class*='title']").text().trim() 
+                : "";
+            
+            String articleUrl = item.selectFirst("a[href]") != null 
+                ? item.selectFirst("a[href]").attr("abs:href") 
+                : url;
+            
+            String content = item.selectFirst("p, .content, [class*='content']") != null 
+                ? item.selectFirst("p, .content, [class*='content']").text().trim() 
+                : "";
+
+            if (!title.isEmpty()) {
+                articles.add(new Article(title, articleUrl, content));
+            }
+        }
+        
+        return articles;
+    }
+
+    @Override
+    public int getPriority() {
+        return PRIORITY;
+    }
+
+    @Override
+    public Pattern getPattern() {
+        return PATTERN;
+    }
+}

w10/strategy/HnuNewsStrategy.java

@@ -0,0 +1,49 @@
+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 listItems = doc.select("ul.list11 li");
+
+        for (Element li : listItems) {
+            Element link = li.selectFirst("a");
+            if (link == null) continue;
+
+            String articleUrl = link.attr("href");
+            if (!articleUrl.startsWith("http")) {
+                articleUrl = "https://news.hnu.edu.cn" + articleUrl.replace("..", "");
+            }
+
+            String title = "";
+            Element titleEl = link.selectFirst("h4.l2.h4s2");
+            if (titleEl != null) {
+                title = titleEl.text().trim();
+            }
+
+            String content = "";
+            Element contentEl = link.selectFirst("p.l3.ps3");
+            if (contentEl != null) {
+                content = contentEl.text().trim();
+            }
+
+            if (!title.isEmpty()) {
+                articles.add(new Article(title, articleUrl, content));
+            }
+        }
+
+        return articles;
+    }
+}

w10/strategy/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;
+    }
+}

w10/strategy/StrategyFactory.java

@@ -0,0 +1,107 @@
+package com.example.datacollect.strategy;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.regex.Pattern;
+
+public class StrategyFactory {
+    private final List<CrawlStrategy> strategies = new ArrayList<>();
+    private CrawlStrategy defaultStrategy;
+
+    public StrategyFactory() {
+        strategies.add(new HnuNewsStrategy());
+        strategies.add(new BlogStrategy());
+        strategies.add(new NewsStrategy());
+        strategies.add(new GenericNewsStrategy());
+        defaultStrategy = new DefaultStrategy();
+    }
+
+    public CrawlStrategy getStrategy(String url) {
+        CrawlStrategy matched = null;
+        int highestPriority = Integer.MIN_VALUE;
+
+        for (CrawlStrategy s : strategies) {
+            boolean supports = false;
+            
+            Pattern pattern = s.getPattern();
+            if (pattern != null) {
+                supports = pattern.matcher(url).find();
+            } else {
+                supports = s.supports(url);
+            }
+
+            if (supports) {
+                int priority = s.getPriority();
+                if (priority > highestPriority) {
+                    highestPriority = priority;
+                    matched = s;
+                }
+            }
+        }
+
+        if (matched != null) {
+            return matched;
+        }
+
+        return defaultStrategy;
+    }
+
+    public void register(CrawlStrategy strategy) {
+        strategies.add(strategy);
+    }
+
+    public void register(CrawlStrategy strategy, int priority) {
+        strategies.add(new PrioritizedStrategy(strategy, priority));
+    }
+
+    public void setDefaultStrategy(CrawlStrategy defaultStrategy) {
+        this.defaultStrategy = defaultStrategy;
+    }
+
+    private static class PrioritizedStrategy implements CrawlStrategy {
+        private final CrawlStrategy delegate;
+        private final int priority;
+
+        public PrioritizedStrategy(CrawlStrategy delegate, int priority) {
+            this.delegate = delegate;
+            this.priority = priority;
+        }
+
+        @Override
+        public List<Article> parse(String url, Document doc) {
+            return delegate.parse(url, doc);
+        }
+
+        @Override
+        public boolean supports(String url) {
+            return delegate.supports(url);
+        }
+
+        @Override
+        public int getPriority() {
+            return priority;
+        }
+
+        @Override
+        public Pattern getPattern() {
+            return delegate.getPattern();
+        }
+    }
+
+    private static class DefaultStrategy implements CrawlStrategy {
+        @Override
+        public List<Article> parse(String url, Document doc) {
+            return List.of();
+        }
+
+        @Override
+        public boolean supports(String url) {
+            return false;
+        }
+
+        @Override
+        public int getPriority() {
+            return Integer.MIN_VALUE;
+        }
+    }
+}

w10/view/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());
+        }
+    }
+}