packagecom.vfsd.net;importjava.io.File;importjava.io.FileOutputStream;importjava.io.IOException;importjava.io.InputStream;importjava.io.OutputStream;importjava.net.HttpURLConnection;importjava.net.URL;importjava.text.DateFormat;importjava.text.SimpleDateFormat;importjava.util.ArrayList;importjava.util.Date;importjava.util.List;importjavax.servlet.ServletException;importjavax.servlet.annotation.WebServlet;importjavax.servlet.http.HttpServlet;importjavax.servlet.http.HttpServletRequest;importjavax.servlet.http.HttpServletResponse;importorg.jsoup.Jsoup;importorg.jsoup.nodes.Document;importorg.jsoup.nodes.Element;importorg.jsoup.select.Elements;/*** Servlet implementation class GetImgFromHtml*/@WebServlet("/GetImgFromHtml")public class GetImgFromHtml extendsHttpServlet {private static final long serialVersionUID = 1L;/***@seeHttpServlet#HttpServlet()*/
publicGetImgFromHtml() {super();//TODO Auto-generated constructor stub
}/***@seeHttpServlet#doGet(HttpServletRequest request, HttpServletResponse response)*/
protected void doGet(HttpServletRequest request, HttpServletResponse response) throwsServletException, IOException {//TODO Auto-generated method stub//response.getWriter().append("Served at: ").append(request.getContextPath());
getDataHTML1();
}/***@seeHttpServlet#doPost(HttpServletRequest request, HttpServletResponse response)*/
protected void doPost(HttpServletRequest request, HttpServletResponse response) throwsServletException, IOException {//TODO Auto-generated method stub
doGet(request, response);
}public static void getDataHTML1() throwsIOException{
String aHrefStr= "http://www.xxx.com/youji/123.html";
System.out.println(aHrefStr);
String dirNameIndex= "1";
System.out.println(dirNameIndex);int dataSize1 =getImg(aHrefStr,dirNameIndex);//int dataSize2 = getImg1(aHrefStr,dirNameIndex);
}public static int getImg(String stringUrl,String dirNameParam) throwsIOException {
String agent1= "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36";
Document documentRoot=Jsoup.connect(stringUrl).userAgent(agent1).get();//System.out.println(documentRoot);//Elements imgElements = documentRoot.getElementsByClass("lazy");
Elements imgElements = documentRoot.getElementsByTag("img");
List list = new ArrayList();
System.out.println("==="+imgElements.size());int i = 0;for(Element imgElement : imgElements) {//imgElement.getElementsByClass("");
String imgSrcStr = imgElement.attr("data-original");//获取到src的值
String imgUrl="";
String imgName=getImgNameByTime(dirNameParam);