爬虫

w10/src/main/java/com/example/datacollect/Main.java

@@ -0,0 +1,23 @@
+package com.example.datacollect;
+
+import com.example.datacollect.controller.CrawlerController;
+import com.example.datacollect.repository.ArticleRepository;
+import com.example.datacollect.service.CrawlerService;
+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();
+        CrawlerService service = new CrawlerService(repository, strategyFactory);
+        CrawlerController controller = new CrawlerController(view, service);
+
+        view.printSuccess("Welcome to CLI Crawler (w10_3)! Type help for commands.");
+        while (true) {
+            controller.handle(view.readLine());
+        }
+    }
+}

w10/src/main/java/com/example/datacollect/command/Command.java

@@ -0,0 +1,6 @@
+package com.example.datacollect.command;
+
+public interface Command {
+    String getName();
+    void execute(String[] args);
+}

w10/src/main/java/com/example/datacollect/command/CrawlCommand.java

@@ -0,0 +1,40 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.model.Article;
+import com.example.datacollect.service.CrawlerService;
+import com.example.datacollect.view.ConsoleView;
+import java.util.List;
+
+public class CrawlCommand implements Command {
+    private final ConsoleView view;
+    private final CrawlerService service;
+
+    public CrawlCommand(ConsoleView view, CrawlerService service) {
+        this.view = view;
+        this.service = service;
+    }
+
+    @Override
+    public String getName() {
+        return "crawl";
+    }
+
+    @Override
+    public void execute(String[] args) {
+        if (args.length < 2) {
+            view.printError("Usage: crawl <url>");
+            return;
+        }
+        String url = args[1];
+
+        try {
+            view.printInfo("Crawling: " + url);
+            List<Article> articles = service.crawl(url);
+            view.printSuccess("Crawled " + articles.size() + " articles.");
+        } catch (IllegalArgumentException e) {
+            view.printError(e.getMessage());
+        } catch (RuntimeException e) {
+            view.printError(e.getMessage());
+        }
+    }
+}

w10/src/main/java/com/example/datacollect/command/ExitCommand.java

@@ -0,0 +1,22 @@
+package com.example.datacollect.command;
+
+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) {
+        view.printSuccess("Bye!");
+        System.exit(0);
+    }
+}

w10/src/main/java/com/example/datacollect/command/HelpCommand.java

@@ -0,0 +1,21 @@
+package com.example.datacollect.command;
+
+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) {
+        view.printInfo("Commands: crawl <url>, list, help, exit");
+    }
+}

w10/src/main/java/com/example/datacollect/command/ListCommand.java

@@ -0,0 +1,24 @@
+package com.example.datacollect.command;
+
+import com.example.datacollect.service.CrawlerService;
+import com.example.datacollect.view.ConsoleView;
+
+public class ListCommand implements Command {
+    private final ConsoleView view;
+    private final CrawlerService service;
+
+    public ListCommand(ConsoleView view, CrawlerService service) {
+        this.view = view;
+        this.service = service;
+    }
+
+    @Override
+    public String getName() {
+        return "list";
+    }
+
+    @Override
+    public void execute(String[] args) {
+        view.display(service.getAllArticles());
+    }
+}

w10/src/main/java/com/example/datacollect/controller/CrawlerController.java

@@ -0,0 +1,44 @@
+package com.example.datacollect.controller;
+
+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.ListCommand;
+import com.example.datacollect.service.CrawlerService;
+import com.example.datacollect.view.ConsoleView;
+import java.util.HashMap;
+import java.util.Map;
+
+public class CrawlerController {
+    private final Map<String, Command> commands = new HashMap<>();
+    private final ConsoleView view;
+
+    public CrawlerController(ConsoleView view, CrawlerService service) {
+        this.view = view;
+        register(new HelpCommand(view));
+        register(new ListCommand(view, service));
+        register(new CrawlCommand(view, service));
+        register(new ExitCommand(view));
+    }
+
+    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;
+        }
+
+        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);
+    }
+}

w10/src/main/java/com/example/datacollect/model/Article.java

@@ -0,0 +1,45 @@
+package com.example.datacollect.model;
+
+public class Article {
+    private String title;
+    private String url;
+    private String content;
+
+    public Article(String title, String url, String content) {
+        this.title = title;
+        this.url = url;
+        this.content = content;
+    }
+
+    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;
+    }
+
+    @Override
+    public String toString() {
+        return "Article{"
+                + "title='" + title + '\''
+                + ", url='" + url + '\''
+                + '}';
+    }
+}

w10/src/main/java/com/example/datacollect/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());
+        }
+    }
+}