Java爬虫爬取图片脚本

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Main {

// 地址
// private static final String URL = "https://voice.hupu.com/nba/2176298.html";
// 获取img标签正则
private static final String IMGURL_REG = "data-original=(.?)[^>]?>";
// 获取src路径的正则
// private static final String IMGSRC_REG = "[a-zA-z]+://[^\s]";
private static final String IMGSRC_REG = "[a-zA-z]+://[^\s]*";
private static final String Download_path = "/Users/yangjunchao/imgdownload/";
public static void main(String[] args) {
// for (long id = 55467; id <= 55467; id++) {
// try {
// System.out.println(id);
// String url = "http://tieba.baidu.com/p/51970"+id;
// System.out.println(url);
// Main cm = new Main();
// //获得html文本内容
// String HTML = cm.getHtml(url);
// //获取图片标签
// List imgUrl = cm.getImageUrl(HTML);
// //获取图片src地址
// List imgSrc = cm.getImageSrc(imgUrl);
// //下载图片
// cm.Download(imgSrc);
//
// } catch (Exception e) {
// System.out.println("发生错误");
// System.out.println(e);
// }
// }
// }
try {
String url = "http://588ku.com/beijing/0-0-pxnum-0-8-0-0-0-1/?h=bd&sem=1";
System.out.println(url);
Main cm = new Main();
//获得html文本内容
String HTML = cm.getHtml(url);
//获取图片标签
List imgUrl = cm.getImageUrl(HTML);
//获取图片src地址
List imgSrc = cm.getImageSrc(imgUrl);
//下载图片
cm.Download(imgSrc);
} catch (Exception e) {
System.out.println("发生错误");
System.out.println(e);
}
}
//获取HTML内容
private String getHtml(String url)throws Exception{
URL url1=new URL(url);
URLConnection connection=url1.openConnection();
InputStream in=connection.getInputStream();
InputStreamReader isr=new InputStreamReader(in);
BufferedReader br=new BufferedReader(isr);
String line;
StringBuffer sb=new StringBuffer();
while((line=br.readLine())!=null){
sb.append(line,0,line.length());
sb.append('\n');
}
br.close();
isr.close();
in.close();
return sb.toString();
}
//获取ImageUrl地址
private List getImageUrl(String html){
Matcher matcher=Pattern.compile(IMGURL_REG).matcher(html);
Listlistimgurl=new ArrayList();
while (matcher.find()){
listimgurl.add(matcher.group());
}
return listimgurl;
}
//获取ImageSrc地址
private List getImageSrc(List listimageurl){
List listImageSrc=new ArrayList();
for (String image:listimageurl){
Matcher matcher=Pattern.compile(IMGSRC_REG).matcher(image);
while (matcher.find()){
listImageSrc.add(matcher.group().substring(0, matcher.group().length()-1));
}
}
return listImageSrc;
}
//下载图片
private void Download(List listImgSrc) {
try {
//开始时间
Date begindate = new Date();
for (String url : listImgSrc) {
//开始时间
Date begindate2 = new Date();
String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());
URL uri = new URL(url);
InputStream in = uri.openStream();
FileOutputStream fo = new FileOutputStream(new File(Download_path+imageName));
byte[] buf = new byte[1024];
int length = 0;
System.out.println("开始下载:" + url);
while ((length = in.read(buf, 0, buf.length)) != -1) {
fo.write(buf, 0, length);
}
in.close();
fo.close();
System.out.println(imageName + "下载完成");
//结束时间
Date overdate2 = new Date();
double time = overdate2.getTime() - begindate2.getTime();
System.out.println("耗时：" + time / 1000 + "s");
}
Date overdate = new Date();
double time = overdate.getTime() - begindate.getTime();
System.out.println("总耗时：" + time / 1000 + "s");
} catch (Exception e) {
System.out.println("下载失败");
System.out.println(e);
}
}
}