Java/w11/datacollect/command/CrawlCommand.java

package com.example.datacollect.command;

import com.example.datacollect.exception.NetworkException;
import com.example.datacollect.exception.ParseException;
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 org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.List;
import java.util.concurrent.TimeUnit;

public class CrawlCommand implements Command {
    private static final Logger logger = LoggerFactory.getLogger(CrawlCommand.class);
    private static final int MAX_RETRY = 3; // 最大重试次数
    private static final long RETRY_INTERVAL = 1000; // 重试间隔（毫秒）

    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) {
            String errorMsg = "Crawl command usage: crawl <url>";
            logger.error(errorMsg);
            view.printError(errorMsg);
            return;
        }
        String url = args[1];
        logger.info("Start crawling url: {}", url);

        CrawlStrategy strategy = strategyFactory.getStrategy(url);
        if (strategy == null) {
            String errorMsg = "No crawl strategy found for url: " + url;
            logger.error(errorMsg);
            view.printError(errorMsg);
            return;
        }

        // 重试逻辑
        int retryCount = 0;
        while (retryCount < MAX_RETRY) {
            try {
                Document doc = fetchDocumentWithRetry(url, retryCount);
                List<Article> articles = strategy.parse(url, doc);

                // 批量添加（复用Repository的addAll方法）
                repository.addAll(articles);

                String successMsg = "Crawled " + articles.size() + " articles from url: " + url;
                logger.info(successMsg);
                view.printSuccess(successMsg);
                return; // 成功则退出重试循环
            } catch (NetworkException e) {
                retryCount++;
                String retryMsg = String.format("Network error (retry %d/%d): %s", retryCount, MAX_RETRY, e.getMessage());
                logger.warn(retryMsg);
                view.printError(retryMsg);

                if (retryCount >= MAX_RETRY) {
                    String failMsg = "Failed to crawl url after " + MAX_RETRY + " retries: " + url;
                    logger.error(failMsg, e);
                    view.printError(failMsg);
                }

                // 重试间隔
                try {
                    TimeUnit.MILLISECONDS.sleep(RETRY_INTERVAL);
                } catch (InterruptedException ie) {
                    Thread.currentThread().interrupt();
                    logger.error("Retry sleep interrupted", ie);
                    break;
                }
            } catch (ParseException e) {
                String errorMsg = "Parse failed for url: " + url;
                logger.error(errorMsg, e);
                view.printError(errorMsg);
                return; // 解析异常不重试
            } catch (Exception e) {
                String errorMsg = "Unexpected error when crawling url: " + url;
                logger.error(errorMsg, e);
                view.printError(errorMsg);
                return;
            }
        }
    }

    // 抽取文档获取逻辑，抛出网络异常
    private Document fetchDocumentWithRetry(String url, int retryCount) throws NetworkException {
        try {
            logger.debug("Fetching document (retry {}) for url: {}", retryCount, url);
            return Jsoup.connect(url)
                    .timeout(5000) // 超时时间5秒
                    .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36")
                    .get();
        } catch (Exception e) {
            throw new NetworkException("Failed to fetch document (retry " + retryCount + ") for url: " + url, e);
        }
    }
}