使用Java语言的webcollector 编写一个爬取https://www.xiangha.com/caipu/95247360.html正文内容的代码程序

以下是使用Java语言和WebCollector框架编写的爬取https://www.xiangha.com/caipu/95247360.html正文内容的代码程序：

import cn.edu.hfut.dmic.webcollector.model.Page;
import cn.edu.hfut.dmic.webcollector.net.HttpRequest;
import cn.edu.hfut.dmic.webcollector.net.HttpResponse;
import cn.edu.hfut.dmic.webcollector.plugin.berkeley.BreadthCrawler;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

public class XianghaCrawler extends BreadthCrawler {
    public XianghaCrawler(String crawlPath, boolean autoParse) {
        super(crawlPath, autoParse);
        addSeed("https://www.xiangha.com/caipu/95247360.html");
    }

    public void visit(Page page, HttpRequest httpRequest, HttpResponse httpResponse) {
        String url = page.getUrl();
        if (httpResponse.getStatus() == HttpResponse.STATUS_OK) {
            Document doc = Jsoup.parse(page.getHtml());
            String title = doc.select("h1.title").text();
            String ingredients = doc.select("div.ings").text();
            String steps = doc.select("div.steps > ol > li").text();
            System.out.println(title + "\n" + ingredients + "\n" + steps);
        }
    }

    public static void main(String[] args) {
        String crawlPath = "xiangha_crawler";
        XianghaCrawler xianghaCrawler = new XianghaCrawler(crawlPath, true);
        xianghaCrawler.setThreads(2);
        xianghaCrawler.start(2);
    }
}

代码中使用WebCollector爬虫框架，实现了对目标页面的爬取。在visit方法中，使用Jsoup解析HTML文档，并提取出正文内容，最终输出到控制台。可以根据需要将输出改为保存到文件中。注意Java版本需要在1.8以上，同时需要添加WebCollector和Jsoup的依赖。