Browse Source

上传文件至 'w10'

main
SunWenxuan 1 month ago
parent
commit
cf269162bb
  1. 71
      w10/AnalyzeCommand.java
  2. BIN
      w10/ArtcleRespository.java
  3. 14
      w10/CrawlStrategy.java

71
w10/AnalyzeCommand.java

@ -0,0 +1,71 @@
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 java.util.List;
public class AnalyzeCommand implements Command {
private final ConsoleView view;
private final StrategyFactory strategyFactory;
public AnalyzeCommand(ConsoleView view, StrategyFactory strategyFactory) {
this.view = view;
this.strategyFactory = strategyFactory;
}
@Override
public String getName() {
return "analyze";
}
@Override
public void execute(String[] args, ArticleRepository repository) {
if (args.length < 2) {
view.printError("Usage: analyze <url>");
return;
}
String url = args[1];
CrawlStrategy strategy = strategyFactory.getStrategy(url);
if (strategy == null) {
view.printError("No strategy found for: " + url);
return;
}
try {
view.printInfo("Analyzing: " + url);
view.printInfo("Using strategy: " + strategy.getClass().getSimpleName());
Document doc = Jsoup.connect(url).get();
List<Article> articles = strategy.parse(url, doc);
view.printSuccess("=== Analysis Statistics ===");
view.printSuccess("URL: " + url);
view.printSuccess("Strategy: " + strategy.getClass().getSimpleName());
view.printSuccess("Articles found: " + articles.size());
if (!articles.isEmpty()) {
view.printSuccess("Sample titles:");
int count = Math.min(3, articles.size());
for (int i = 0; i < count; i++) {
view.printSuccess(" - " + articles.get(i).getTitle());
}
if (articles.size() > 3) {
view.printSuccess(" ... and " + (articles.size() - 3) + " more");
}
}
view.printSuccess("Note: Articles were NOT stored in repository");
} catch (Exception e) {
view.printError("Failed to analyze: " + e.getMessage());
}
}
}

BIN
w10/ArtcleRespository.java

Binary file not shown.

14
w10/CrawlStrategy.java

@ -0,0 +1,14 @@
import com.example.datacollect.model.Article;
import org.jsoup.nodes.Document;
import java.util.List;
public interface CrawlStrategy {
List<Article> parse(String url, Document doc);
boolean supports(String url);
default int getPriority() {
return 0;
}
}
Loading…
Cancel
Save