java/project/CrawlCommand.java

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 <url>");
            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<Movie> 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<Movie> 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<Movie> 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<Movie> 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<Movie> 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<Movie> allMovies = new ArrayList<>();
        try {
            view.printInfo("正在爬取: " + url);
            Document doc = Jsoup.connect(url)
                    .userAgent("Mozilla/5.0")
                    .timeout(10000)
                    .get();
            List<Movie> 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<Movie> 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();
        }
    }
}