Browse Source

上传文件至 'w11'

main
Zhuhuairui 4 weeks ago
parent
commit
5eb832d194
  1. 9
      w11/Command.java
  2. 81
      w11/CrawlCommand.java
  3. 24
      w11/ExitCommand.java
  4. 23
      w11/HelpCommand.java
  5. 23
      w11/Main.java
  6. 26
      w11/logback.xml

9
w11/Command.java

@ -0,0 +1,9 @@
package com.example.datacollect.command;
import com.example.datacollect.model.Article;
import java.util.List;
public interface Command {
String getName();
void execute(String[] args, List<Article> articles);
}

81
w11/CrawlCommand.java

@ -0,0 +1,81 @@
package com.example.datacollect.command;
import com.example.datacollect.exception.CrawlerException;
import com.example.datacollect.model.Article;
import com.example.datacollect.repository.ArticleRepository;
import com.example.datacollect.service.ScraperService;
import com.example.datacollect.strategy.ArticleCrawlStrategy;
import com.example.datacollect.view.ConsoleView;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.List;
public class CrawlCommand implements Command {
private static final Logger logger = LoggerFactory.getLogger(CrawlCommand.class);
private final ConsoleView view;
private final ArticleRepository repository;
private final ScraperService scraperService;
private static final int MAX_RETRIES = 3;
private static final long RETRY_DELAY_MS = 1000;
public CrawlCommand(ConsoleView view, ArticleRepository repository) {
this.view = view;
this.repository = repository;
this.scraperService = new ScraperService(new ArticleCrawlStrategy(), MAX_RETRIES, RETRY_DELAY_MS);
}
@Override
public String getName() {
return "crawl";
}
@Override
public void execute(String[] args, List<Article> articles) {
if (args.length < 2) {
view.printError("Usage: crawl <url>");
return;
}
String url = args[1];
logger.info("Starting crawl for URL: {}", url);
view.printInfo("Starting to crawl: " + url);
int attempts = 0;
boolean success = false;
CrawlerException lastException = null;
while (attempts < MAX_RETRIES && !success) {
attempts++;
try {
Article article = scraperService.scrape(url);
repository.save(article);
articles.add(article);
logger.info("Successfully crawled article: {}", article.getTitle());
view.printSuccess("Successfully crawled: " + article.getTitle());
success = true;
} catch (CrawlerException e) {
lastException = e;
logger.warn("Attempt {}/{} failed for URL: {}", attempts, MAX_RETRIES, url);
view.printError("Attempt " + attempts + " failed: " + e.getMessage());
if (attempts < MAX_RETRIES) {
try {
Thread.sleep(RETRY_DELAY_MS);
} catch (InterruptedException ie) {
Thread.currentThread().interrupt();
logger.error("Crawl interrupted for URL: {}", url);
view.printError("Crawl interrupted");
return;
}
}
}
}
if (!success) {
logger.error("Failed to crawl URL after {} attempts: {}", MAX_RETRIES, url);
view.printError("Failed to crawl after " + MAX_RETRIES + " attempts");
if (lastException != null) {
view.printError("Last error: " + lastException.getMessage());
}
}
}
}

24
w11/ExitCommand.java

@ -0,0 +1,24 @@
package com.example.datacollect.command;
import com.example.datacollect.model.Article;
import com.example.datacollect.view.ConsoleView;
import java.util.List;
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, List<Article> articles) {
view.printSuccess("Bye!");
System.exit(0);
}
}

23
w11/HelpCommand.java

@ -0,0 +1,23 @@
package com.example.datacollect.command;
import com.example.datacollect.model.Article;
import com.example.datacollect.view.ConsoleView;
import java.util.List;
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, List<Article> articles) {
view.printInfo("Commands: crawl <url>, list, help, exit");
}
}

23
w11/Main.java

@ -0,0 +1,23 @@
package com.example.datacollect;
import com.example.datacollect.controller.CrawlerController;
import com.example.datacollect.model.Article;
import com.example.datacollect.repository.ArticleRepository;
import com.example.datacollect.view.ConsoleView;
import java.util.ArrayList;
import java.util.List;
public class Main {
public static void main(String[] args) {
ConsoleView view = new ConsoleView();
List<Article> articles = new ArrayList<>();
ArticleRepository repository = new ArticleRepository();
CrawlerController controller = new CrawlerController(view, articles, repository);
view.printSuccess("Welcome to CLI Crawler (w11)! Type help for commands.");
while (true) {
controller.handle(view.readLine());
}
}
}

26
w11/logback.xml

@ -0,0 +1,26 @@
<?xml version="1.0" encoding="UTF-8"?>
<configuration>
<appender name="CONSOLE" class="ch.qos.logback.core.ConsoleAppender">
<encoder>
<pattern>%d{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n</pattern>
</encoder>
</appender>
<appender name="FILE" class="ch.qos.logback.core.rolling.RollingFileAppender">
<file>logs/application.log</file>
<rollingPolicy class="ch.qos.logback.core.rolling.TimeBasedRollingPolicy">
<fileNamePattern>logs/application-%d{yyyy-MM-dd}.log</fileNamePattern>
<maxHistory>30</maxHistory>
</rollingPolicy>
<encoder>
<pattern>%d{yyyy-MM-dd HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n</pattern>
</encoder>
</appender>
<logger name="com.example.datacollect" level="DEBUG"/>
<root level="INFO">
<appender-ref ref="CONSOLE"/>
<appender-ref ref="FILE"/>
</root>
</configuration>
Loading…
Cancel
Save