java/Crawler/strategy_crawler/AbstractCrawlStrategy.java

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

import java.io.IOException;

public abstract class AbstractCrawlStrategy<T> implements CrawlStrategy<T> {

    @Override
    public Document fetchDocument(String url) throws IOException {
        return Jsoup.connect(url)
                .timeout(15000)
                .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36")
                .header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8")
                .header("Accept-Language", "zh-CN,zh;q=0.9,en;q=0.8")
                .get();
    }

    protected double parsePrice(String text) {
        try {
            String cleanText = text.replaceAll("[^0-9.]", "");
            if (cleanText.isEmpty()) return 0.0;
            return Double.parseDouble(cleanText);
        } catch (Exception e) {
            return 0.0;
        }
    }

    protected double parseDiscount(double price, double originalPrice) {
        if (originalPrice <= 0) return 10.0;
        return Math.round((price / originalPrice) * 100) / 10.0;
    }
}