diff --git a/project/command/AutoCommand.java b/project/command/AutoCommand.java new file mode 100644 index 0000000..38b0387 --- /dev/null +++ b/project/command/AutoCommand.java @@ -0,0 +1,47 @@ +package com.example.moviecli.command; + +import com.example.moviecli.repository.MovieRepository; +import com.example.moviecli.strategy.MovieStrategyFactory; +import com.example.moviecli.view.ConsoleView; + +public class AutoCommand implements Command { + private final ConsoleView view; + private final MovieStrategyFactory factory; + private final CrawlCommand crawlCommand; + + public AutoCommand(ConsoleView view, MovieStrategyFactory factory) { + this.view = view; + this.factory = factory; + this.crawlCommand = new CrawlCommand(view, factory); + } + + @Override + public String getName() { + return "auto"; + } + + @Override + public void execute(String[] args, MovieRepository repository) { + view.printInfo("开始自动执行预设任务..."); + + // 1. 豆瓣电影 Top250 + crawlCommand.execute(new String[]{"crawl", "https://movie.douban.com/top250"}, repository); + + // 2. 新浪新闻（替代猫眼） + crawlCommand.execute(new String[]{"crawl", "https://news.sina.com.cn/"}, repository); + + // 3. 豆瓣图书 Top50 + crawlCommand.execute(new String[]{"crawl", "https://book.douban.com/top250"}, repository); + + // 4. 列出所有数据 + new ListCommand(view).execute(new String[]{"list"}, repository); + + // 5. 统计评分分布 + new StatCommand(view).execute(new String[]{"stat"}, repository); + + // 6. 导出全部数据到 movies.csv + new ExportCommand(view).execute(new String[]{"export"}, repository); + + view.printSuccess("自动任务执行完毕！已生成三个独立 CSV 文件及总文件 movies.csv。"); + } +} \ No newline at end of file diff --git a/project/command/Command.java b/project/command/Command.java new file mode 100644 index 0000000..6691498 --- /dev/null +++ b/project/command/Command.java @@ -0,0 +1,8 @@ +package com.example.moviecli.command; + +import com.example.moviecli.repository.MovieRepository; + +public interface Command { + String getName(); + void execute(String[] args, MovieRepository repository); +} \ No newline at end of file diff --git a/project/command/CrawlCommand.java b/project/command/CrawlCommand.java new file mode 100644 index 0000000..1ec3ade --- /dev/null +++ b/project/command/CrawlCommand.java @@ -0,0 +1,197 @@ +package com.example.moviecli.command; + +import com.example.moviecli.model.Movie; +import com.example.moviecli.repository.MovieRepository; +import com.example.moviecli.strategy.MovieCrawlStrategy; +import com.example.moviecli.strategy.MovieStrategyFactory; +import com.example.moviecli.view.ConsoleView; +import com.example.moviecli.exception.CrawlFailedException; +import com.example.moviecli.exception.ParseFailedException; +import com.example.moviecli.exception.SaveFailedException; +import com.opencsv.CSVWriter; +import org.jsoup.Jsoup; +import org.jsoup.nodes.Document; + +import java.io.FileWriter; +import java.util.ArrayList; +import java.util.List; + +public class CrawlCommand implements Command { + private final ConsoleView view; + private final MovieStrategyFactory factory; + + public CrawlCommand(ConsoleView view, MovieStrategyFactory factory) { + this.view = view; + this.factory = factory; + } + + @Override + public String getName() { + return "crawl"; + } + + @Override + public void execute(String[] args, MovieRepository repository) { + if (args.length < 2) { + view.printError("用法: crawl "); + view.printInfo("支持的 URL 示例："); + view.printInfo(" https://movie.douban.com/top250"); + view.printInfo(" https://news.sina.com.cn/"); + view.printInfo(" https://book.douban.com/top250"); + return; + } + String url = args[1]; + MovieCrawlStrategy strategy = factory.getStrategy(url); + if (strategy == null) { + view.printError("不支持该 URL 的爬取策略: " + url); + return; + } + + if (url.contains("movie.douban.com/top250")) { + crawlDoubanTop250(strategy, repository); + } else if (url.contains("news.sina.com.cn")) { + crawlSinaNews(strategy, repository); + } else if (url.contains("book.douban.com/top250")) { + crawlDoubanBookTop50(strategy, repository); + } else { + crawlSinglePage(url, strategy, repository); + } + } + + /** 豆瓣电影 Top250 -> douban_movies.csv */ + private void crawlDoubanTop250(MovieCrawlStrategy strategy, MovieRepository repository) { + List allMovies = new ArrayList<>(); + int total = 0; + for (int start = 0; start < 250; start += 25) { + String pageUrl = "https://movie.douban.com/top250?start=" + start; + try { + view.printInfo("正在爬取: " + pageUrl); + Document doc = Jsoup.connect(pageUrl) + .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36") + .timeout(15000) + .get(); + List pageMovies = strategy.parse(doc); + allMovies.addAll(pageMovies); + repository.addAll(pageMovies); + total += pageMovies.size(); + view.printInfo("已累计爬取 " + total + " 条..."); + Thread.sleep(1500); + } catch (ParseFailedException e) { + view.printError("解析失败: " + e.getMessage()); + e.printStackTrace(); + } catch (Exception e) { + CrawlFailedException ex = new CrawlFailedException("豆瓣电影爬取失败: " + pageUrl, e); + view.printError(ex.getMessage()); + ex.printStackTrace(); + } + } + view.printSuccess("豆瓣电影 Top250 全部爬取完成，共 " + total + " 条记录。"); + saveToCsv(allMovies, "douban_movies.csv"); + } + + /** 新浪新闻首页 -> sina_news.csv */ + private void crawlSinaNews(MovieCrawlStrategy strategy, MovieRepository repository) { + String url = "https://news.sina.com.cn/"; + try { + view.printInfo("正在爬取新浪新闻: " + url); + Document doc = Jsoup.connect(url) + .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36") + .timeout(15000) + .get(); + List news = strategy.parse(doc); + repository.addAll(news); + view.printSuccess("新浪新闻爬取完成，共 " + news.size() + " 条记录。"); + saveToCsv(news, "sina_news.csv"); + } catch (ParseFailedException e) { + view.printError("解析失败: " + e.getMessage()); + e.printStackTrace(); + } catch (Exception e) { + CrawlFailedException ex = new CrawlFailedException("新浪新闻爬取失败: " + url, e); + view.printError(ex.getMessage()); + ex.printStackTrace(); + } + } + + /** 豆瓣图书 Top50 -> douban_books.csv */ + private void crawlDoubanBookTop50(MovieCrawlStrategy strategy, MovieRepository repository) { + List allMovies = new ArrayList<>(); + int total = 0; + for (int start = 0; start < 50; start += 25) { + String pageUrl = "https://book.douban.com/top250?start=" + start; + try { + view.printInfo("正在爬取: " + pageUrl); + Document doc = Jsoup.connect(pageUrl) + .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36") + .timeout(15000) + .get(); + List pageMovies = strategy.parse(doc); + allMovies.addAll(pageMovies); + repository.addAll(pageMovies); + total += pageMovies.size(); + view.printInfo("已累计爬取 " + total + " 条..."); + Thread.sleep(1500); + } catch (ParseFailedException e) { + view.printError("解析失败: " + e.getMessage()); + e.printStackTrace(); + } catch (Exception e) { + CrawlFailedException ex = new CrawlFailedException("豆瓣图书爬取失败: " + pageUrl, e); + view.printError(ex.getMessage()); + ex.printStackTrace(); + } + } + view.printSuccess("豆瓣图书 Top50 爬取完成，共 " + total + " 条记录。"); + saveToCsv(allMovies, "douban_books.csv"); + } + + /** 单页兜底（未匹配的URL） */ + private void crawlSinglePage(String url, MovieCrawlStrategy strategy, MovieRepository repository) { + List allMovies = new ArrayList<>(); + try { + view.printInfo("正在爬取: " + url); + Document doc = Jsoup.connect(url) + .userAgent("Mozilla/5.0") + .timeout(10000) + .get(); + List movies = strategy.parse(doc); + allMovies.addAll(movies); + repository.addAll(movies); + view.printSuccess("爬取完成！共 " + movies.size() + " 条记录。"); + saveToCsv(allMovies, "unknown.csv"); + } catch (ParseFailedException e) { + view.printError("解析失败: " + e.getMessage()); + e.printStackTrace(); + } catch (Exception e) { + CrawlFailedException ex = new CrawlFailedException("爬取失败: " + url, e); + view.printError(ex.getMessage()); + ex.printStackTrace(); + } + } + + /** 保存电影/新闻列表到 CSV 文件 */ + private void saveToCsv(List items, String filename) { + if (items.isEmpty()) { + view.printInfo("没有数据可保存到 " + filename); + return; + } + try (CSVWriter writer = new CSVWriter(new FileWriter(filename))) { + String[] header = {"Rank", "Title", "OriginalTitle", "Score", "Year", "Director"}; + writer.writeNext(header); + for (Movie m : items) { + String[] line = { + String.valueOf(m.getRank()), + m.getTitle(), + m.getOriginalTitle(), + m.getScore(), + m.getYear(), + m.getDirector() + }; + writer.writeNext(line); + } + view.printSuccess("已保存 " + items.size() + " 条记录到 " + filename); + } catch (Exception e) { + SaveFailedException ex = new SaveFailedException("保存 " + filename + " 失败", e); + view.printError(ex.getMessage()); + ex.printStackTrace(); + } + } +} \ No newline at end of file diff --git a/project/command/ExitCommand.java b/project/command/ExitCommand.java new file mode 100644 index 0000000..2aead47 --- /dev/null +++ b/project/command/ExitCommand.java @@ -0,0 +1,23 @@ +package com.example.moviecli.command; + +import com.example.moviecli.repository.MovieRepository; +import com.example.moviecli.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, MovieRepository repository) { + view.printSuccess("再见！"); + System.exit(0); + } +} \ No newline at end of file diff --git a/project/command/ExportCommand.java b/project/command/ExportCommand.java new file mode 100644 index 0000000..32e4311 --- /dev/null +++ b/project/command/ExportCommand.java @@ -0,0 +1,52 @@ +package com.example.moviecli.command; + +import com.example.moviecli.model.Movie; +import com.example.moviecli.repository.MovieRepository; +import com.example.moviecli.view.ConsoleView; +import com.example.moviecli.exception.SaveFailedException; +import com.opencsv.CSVWriter; +import java.io.FileWriter; +import java.util.List; + +public class ExportCommand implements Command { + private final ConsoleView view; + + public ExportCommand(ConsoleView view) { + this.view = view; + } + + @Override + public String getName() { + return "export"; + } + + @Override + public void execute(String[] args, MovieRepository repository) { + List movies = repository.getAll(); + if (movies.isEmpty()) { + view.printError("没有数据可导出。"); + return; + } + try (CSVWriter writer = new CSVWriter(new FileWriter("movies.csv"))) { + String[] header = {"Rank", "Title", "OriginalTitle", "Score", "Year", "Director"}; + writer.writeNext(header); + for (Movie m : movies) { + String[] line = { + String.valueOf(m.getRank()), + m.getTitle(), + m.getOriginalTitle(), + m.getScore(), + m.getYear(), + m.getDirector() + }; + writer.writeNext(line); + } + view.printSuccess("导出成功：movies.csv"); + } catch (Exception e) { + // 使用自定义异常包装原始异常 + SaveFailedException ex = new SaveFailedException("导出CSV文件失败", e); + view.printError(ex.getMessage()); + ex.printStackTrace(); // 打印堆栈，体现使用了自定义异常 + } + } +} \ No newline at end of file