旅游网站大数据分析 - 数据抓取

第1关：利用Jsoup抓取携程旅游网的数据

package step1;
import java.io.File;
import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

public class Task {
	/**
	 * @param filePath	文件路径：backups/www.ctrip.com.txt/
	 * @return
	 * @throws IOException
	 */

	public Document getHtml1(String url) throws IOException{
           
        Document document = Jsoup.parse( new File( "./backups/www.ctrip.com.txt" ) , "utf-8" );
		   // System.out.println(document.title());
		   // System.out.println(document);
        
		return document;
	} 
	/**
	 * 
	 * @param url	网址http://hotels.ctrip.com/domestic-city-hotel.html
	 * @return
	 * @throws IOException
	 */
	public Document getHtml2(String url) throws IOException{
        Document document = Jsoup.p