爬虫(整页)

public class Text02 {
public static void main(String[] args) {
// 图片下载对象
final ImageDownload imgDownload = new ImageDownload();
// 生产图片链接的(3个)
// (一)
new Thread(new Runnable() {

        @Override
        public void run() {
            for (int i = 1; i < 500; i++) {
                try {
                    imgDownload.parseImageUrl(i);
                } catch (Exception e) {
                    e.printStackTrace();
                }
            }
        }
    }).start(); 


    // (二)
    new Thread(new Runnable() {

        @Override
        public void run() {
            for (int i = 500; i < 1000; i++) {
                try {
                    imgDownload.parseImageUrl(i);
                } catch (Exception e) {
                    e.printStackTrace();

                }
            }
        }
    }).start();

    // (三)
    new Thread(new Runnable() {

        @Override
        public void run() {
            for (int i = 1000; i < 1500; i++) {
                try {
                    imgDownload.parseImageUrl(i);
                } catch (Exception e) {
                    e.printStackTrace();

                }
            }
        }
    }).start();

    // 下载图片(5个)
    // (1)
    new Thread(new Runnable() {
        @Override
        public void run() {
            while (true) {// 一直在下载
                try {
                    imgDownload.downloadimage();
                } catch (Exception e) {

                    e.printStackTrace();
                }
            }
        }
    }).start();

    // (2)
    new Thread(new Runnable() {

        @Override
        public void run() {
            while (true) {// 一直在下载
                try {
                    imgDownload.downloadimage();
                } catch (Exception e) {

                    e.printStackTrace();
                }
            }
        }
    }).start();

    // (3)
    new Thread(new Runnable() {

        @Override
        public void run() {
            while (true) {// 一直在下载
                try {
                    imgDownload.downloadimage();
                } catch (Exception e) {

                    e.printStackTrace();
                }
            }
        }
    }).start();

    // (4)
    new Thread(new Runnable() {

        @Override
        public void run() {
            while (true) {// 一直在下载
                try {
                    imgDownload.downloadimage();
                } catch (Exception e) {

                    e.printStackTrace();
                }
            }
        }
    }).start();

    // (5)
    new Thread(new Runnable() {

        @Override
        public void run() {
            while (true) {// 一直在下载
                try {
                    imgDownload.downloadimage();
                } catch (Exception e) {

                    e.printStackTrace();
                }
            }
        }
    }).start();

}

}

// 图片下载类
class ImageDownload {
// imageurl的数组
LinkedList list = new LinkedList();

// 解析连接
void parseImageUrl(int page) throws Exception {
    synchronized (this) {
        if (list.size()>100) {
        wait();
    }
    String htmlUrl = "https://www.doutula.com/article/list/?page=" + page;
    Document doc = Jsoup.connect(htmlUrl).get();
    // 获取图片连接
    Elements els = doc.select(".lazy,.image_dtb,.img--responsive");// cssQuery// css选择器// (有 id// tagName// 复合选择器)                      
    Iterator iter = els.iterator();
    while (iter.hasNext()) {
        Element obj = (Element) iter.next();
        String imageUrl = obj.attr("data-original");
        if (!imageUrl.contains(htmlUrl)) {
            continue;
        }
        this.list.add(imageUrl);
    }
    //生产完毕 通知可以下载图片
    notifyAll();
    }
}

// 下载图片
void downloadimage() throws Exception {
    synchronized (this) {
        if (this.list.size()<= 0) {
            wait();
        }
    // URL url = new URL(this.list.get(0));
    // this.list.removeFirst();

    // 拿一个删除一个用完之后就删除(合二为一)
    String imageUrl =null;
    if (this.list.size()>0) {
        imageUrl = this.list.removeFirst();
    }else{
        return;
    }
    URL url = new URL(imageUrl);
    
    URLConnection connection = url.openConnection();// 创建连接
    connection.connect();// 发送连接
    InputStream in = connection.getInputStream();
    byte[] by = new byte[1024];
    int length = -1;
    // out流
    String[] imageUrlArr = imageUrl.split("/");
    String fileName = "Image/" + imageUrlArr[imageUrlArr.length - 1];
    FileOutputStream fileout = new FileOutputStream(fileName);
    while ((length = in.read(by)) != -1) {// (循环为了防止1024放满不够用)
        // 把流写入本地文件夹里
        fileout.write(by, 0, length);// 截取 防止覆盖不了时候
    }
    fileout.close();
    in.close();
    //通知可以继续生产解析图片
    if (this.list.size()<100) {
         notify();
    }   
    }       
}

}

你可能感兴趣的:(爬虫(整页))