package pers.baijiaming.download.main;//主类
public class Main
{public static void main(String[] args){createImageDownloadThread ("https://www.bilibili.com/", "downloadImg/b站/");createImageDownloadThread("https://cn.bing.com/images/search?q=%E7%A6%8F%E5%88%A9&qs=n&form=QBIR&sp=-1&pq=%E7%A6%8F%E5%88%A9&sc=3-2&cvid=2AF12F93CAB34E8FBF902905B185583C&first=1&scenario=ImageBasicHover", "downloadImg/福利/");createTextDownloadThread("https://www.csdn.net/", "你", "Text/", "testText.txt");}//创建并执行线程，获取图片private static void createImageDownloadThread(String url, String path){new Thread(new DownloadPictures(url, path)).start();}//获取文本内容private static void createTextDownloadThread(String urlStr, String findText, String downloadPath, String fileName){new Thread(new GetText(urlStr, findText, downloadPath, fileName)).start();}
}

package pers.baijiaming.download.main;import java.io.*;           //io包
import java.util.regex.*;   //正则包
import java.net.*;          //网络包/*
* 下载图片类
* */
public final class DownloadPictures implements Runnable
{private URL url = null;     //URLprivate URLConnection urlConn =  null;  //url连接private BufferedReader bufIn = null;    //缓冲读取器，读取网页信息private static final String IMG_REG = "<img.*srcs*=s*(.*?)[^>]*?>";    //img标签正则private static final String IMG_SRC_REG = "srcs*=s*"?(.*?)("|>|s+)";    //img src属性正则private String downloadPath = null;     //保存路径//构造，参数：想要下载图片的网址、下载到的图片存放的文件路径public DownloadPictures(String urlStr, String downloadPath){createFolder(downloadPath);     //创建文件夹try {url = new URL(urlStr);urlConn = url.openConnection();//设置请求属性，有部分网站不加这句话会抛出IOException: Server returned HTTP response code: 403 for URL异常//如：b站urlConn.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");bufIn = new BufferedReader(new InputStreamReader(urlConn.getInputStream()));}catch (Exception e) {e.printStackTrace();}this.downloadPath = downloadPath;}//检测路径是否存在，不存在则创建private void createFolder(String path){File myPath = new File(path);if (!myPath.exists())   //不存在则创建文件夹myPath.mkdirs();}//下载函数public void Download(){final int N = 20;    //每一次处理的文本行数，这个数越小越容易遗漏图片链接，越大效率越低 (理论上)String line = "";String text = "";while (line != null)            //网页内容被读完时结束循环{for(int i = 0; i < N; i++)  //读取N行网页信息存入到text当中，因为src内容可能分为多行，所以使用这种方法try {line = bufIn.readLine();    //从网页信息中获取一行文本if(line != null)            //判断防止把null也累加到text中text += line;}catch (IOException e) {e.printStackTrace();}//将img标签正则封装对象再调用matcher方法获取一个Matcher对象final Matcher imgM = Pattern.compile(IMG_REG).matcher(text);if(!imgM.find())    //如果在当前text中没有找到img标签则结束本次循环continue;//将img src正则封装对象再调用matcher方法获取一个Matcher对象//用于匹配的文本为找到的整个img标签final Matcher imgSrcM = Pattern.compile(IMG_SRC_REG).matcher(imgM.group());while (imgSrcM.find())      //从img标签中查找src内容{String imageLink = imgSrcM.group(1);    //从正则中的第一个组中得到图片链接print(imageLink);       //打印一遍链接//如果得到的src内容没有写协议，则添加上
//                if(!imageLink.matches("https://[sS]*"))       //这里有问题
//                    imageLink = "https://" + imageLink;print(imageLink);       //打印一遍链接try{//缓冲输入流对象，用于读取图片链接的图片数据//在链接的图片不存在时会抛出未找到文件异常final BufferedInputStream in = new BufferedInputStream(new URL(imageLink).openStream());//文件输出流对象用于将从url中读取到的图片数据写入到本地//保存的路径为downloadPath，保存的图片名为时间戳+".png"final FileOutputStream file = new FileOutputStream(new File(downloadPath + System.currentTimeMillis() + ".png"));int temp;   //用于保存in从图片连接中获取到的数据while ((temp = in.read()) != -1)file.write(temp);   //将数据写入到本地路径中//关闭流file.close();in.close();//下载完一张图片后休息一会try {Thread.sleep(800);}catch (InterruptedException e) {e.printStackTrace();}}catch (Exception e){e.printStackTrace();}}//将text中的文本清空text = "";}}//run@Overridepublic void run(){Download(); //下载函数}//打印语句public void print(Object obj){System.out.println(obj);}
}

package pers.baijiaming.download.main;import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;public final class GetText implements Runnable
{private URL url = null;     //URLprivate URLConnection urlConn =  null;  //url连接private BufferedReader bufIn = null;    //缓冲读取器，读取网页信息//    private static final String TEXT_REG = "([[[^x00-xff]|w]&&[^u003E]])+";    //文本内容正则private static final String TEXT_REG = "[[sS]&&[^<>n ]]*";    //文本内容正则，这里有些问题，试了很久，无法排除一个空格的情况
//    <[a-zA-Z]+.*?>([sS]*?)</[a-zA-Z]*?>private String findText = null;         //要查找的内容private String downloadPath = null;     //保存路径private String fileName = null;         //文件名//构造，参数：url、要查找的文本、保存路径，文件名public GetText(String urlStr, String findText, String downloadPath, String fileName){createFolder(downloadPath);     //创建文件夹try {url = new URL(urlStr);urlConn = url.openConnection();//设置请求属性，有部分网站不加这句话会抛出IOException: Server returned HTTP response code: 403 for URL异常//如：b站urlConn.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");bufIn = new BufferedReader(new InputStreamReader(urlConn.getInputStream()));}catch (Exception e) {e.printStackTrace();}this.downloadPath = downloadPath;this.fileName = fileName;this.findText = findText;}//检测路径是否存在，不存在则创建private void createFolder(String path){File myPath = new File(path);if (!myPath.exists())   //不存在则创建文件夹myPath.mkdirs();}//下载函数private void Download(){final int N = 10;String line = "";String textStr = "";while (line != null){for(int i = 0; i < N; i++)      //将N行内容追加到textStr字符串中try {line = bufIn.readLine();if(line != null)textStr += line;}catch (IOException e) {e.printStackTrace();}try{//将img标签正则封装对象再调用matcher方法获取一个Matcher对象final Matcher textMatcher = Pattern.compile(TEXT_REG + findText + TEXT_REG).matcher(textStr);final FileWriter fw = new FileWriter(downloadPath + fileName, true);   //文件编写，续写文件while (textMatcher.find())          //查找匹配文本{fw.write(textMatcher.group() + "n");  //写入到文件中print(textMatcher.group());     //打印一遍}//                print(textStr);fw.close();textStr = "";}catch (Exception e){e.printStackTrace();}}}//run@Overridepublic void run(){Download();}//打印语句private void print(Object obj){System.out.println(obj);}
}