解析并提取HTML 元素(一）

package step2;
import java.io.File;
import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class Task {

    //通过filePath文件路径获取Docment对象
    public Document getDoc1(String url) throws IOException{
      File file=new File("./backups/www.ctrip.com.txt");
       Document document =Jsoup.parse(file,"UTF-8","http://www.ctrip.com/");

       return document ;
    }

    //获取“http://you.ctrip.com/”的Docment对象
    public Document getDoc2(String url) throws IOException{
        File file=new File("./backups/you.ctrip.com.txt");
        Document document =Jsoup.parse(file,"UTF-8","http://you.ctrip.com");

        return document ;
    }


    //获取所有链接

    public Elements getLinks(Document doc){
       Elements links=doc.select("link[href]");
        return links;
    }

    //获取第一个class为“pop_attention”的div
    public Element getDiv(Document doc){
       Element element =doc.select("div.pop_attention").first();
        return element ;
    }

    //获取所有li之后的i标签
    public Elements getI(Document doc){
     Elements element =doc.select("li>i");
        return element ;
    }

}