jsoup实现爬取网页图片

1.dao层实现:

import org.apache.commons.io.IOUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import spider.utils.JdbcUtil;
import javax.sql.DataSource;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.sql.PreparedStatement;
import java.sql.SQLException;

public class SelectAndCopyImpl implements ISelectAndCopy{
    @Override
    public void selectAndCopy(String href) {

        Document document = null;
        try {
            //根据网址获得网页源代码文档对象
            document = Jsoup.connect(href).get();
            //选择文档对象中所有的 带有src的img图片标签
            Elements select = document.select("img[src]");
            for (Element element : select) {
                String src=element.attr("src");
                System.out.println(src);
                try {
                    String theSrc="http:"+src;
                    InputStream inputStream = new URL(theSrc).openStream();
                    FileOutputStream fileOutputStream = new FileOutputStream("D:\\img/" + System.currentTimeMillis() + ".jpg");
                    IOUtils.copy(inputStream,fileOutputStream);
                    DataSource ds = JdbcUtil.getDs();
                    System.out.println(ds);
                    // 创建File对象
                    File destFile = new File("D:\\img/");
                    // 获取所有文件和文件夹
                    File[] files = destFile.listFiles();
                    // 遍历
                    for(File file : files) {
                        String imgName = file.getName();
                        try {
                            System.out.println("图片名"+imgName+"路径"+theSrc);
                            PreparedStatement preparedStatement = ds.getConnection().prepareStatement("insert into img(imgName,src) values (?,?)");
                            preparedStatement.setString(1,imgName);
                            preparedStatement.setString(2,theSrc);
                            int i = preparedStatement.executeUpdate();
                            //System.out.println("受影响的行数为:"+i);
                        } catch (SQLException e) {
                            e.printStackTrace();
                        }
                    }
                } catch (Exception e) {
                    e.printStackTrace();
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

2.Servlet层:

@WebServlet("/spider")
public class spiderServlet extends HttpServlet {
    protected void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
        String href = request.getParameter("href");
        new SelectAndCopyServiceImpl().selsctAndCopy(href);
    }
}