java/HttpBinStrategy.java

package strategy;

import model.Article;
import util.HttpUtil;
import exception.SpiderException;

public class HttpBinStrategy implements CrawlStrategy {
    @Override
    public String getName() {
        return "HttpBin";
    }
    
    @Override
    public String getUrl() {
        return "https://httpbin.org/html";
    }
    
    @Override
    public Article crawl() throws SpiderException {
        String html = HttpUtil.get(getUrl(), "UTF-8");
        
        String title = HttpUtil.extractTagSafe(html, "<h1>", "</h1>");
        String content = HttpUtil.extractTagSafe(html, "<p>", "</p>");
        
        Article article = new Article();
        article.setTitle(title);
        article.setContent(content);
        article.setUrl(getUrl());
        article.setSource(getName());
        
        return article;
    }
}