java/project/crawler/ExampleCrawler.java

package com.crawler.crawler.impl;

import com.crawler.crawler.BaseCrawler;
import com.crawler.model.CrawlerData;

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class ExampleCrawler extends BaseCrawler {
    @Override
    public String getCrawlerName() {
        return "ExampleCrawler";
    }

    @Override
    protected List<CrawlerData> parseHtml(String html) {
        List<CrawlerData> results = new ArrayList<>();
        
        String cleanHtml = html.replaceAll("\\s+", " ").replaceAll(">\\s*<", "><");
        
        Pattern linkPattern = Pattern.compile("<a\\s+[^>]*href\\s*=\\s*[\"']([^\"']+)[\"'][^>]*>([^<]+)</a>", Pattern.CASE_INSENSITIVE);
        Matcher matcher = linkPattern.matcher(cleanHtml);
        
        int count = 0;
        while (matcher.find() && count < 10) {
            CrawlerData data = new CrawlerData();
            data.setTitle(cleanText(matcher.group(2)));
            data.setUrl(matcher.group(1));
            results.add(data);
            count++;
        }
        
        return results;
    }
    
    private String cleanText(String text) {
        if (text == null) return null;
        return text.replaceAll("<[^>]+>", "").trim();
    }
}