函数计算实战-java爬虫程序从指定网站获取图片并存储到对象存储中的例子

前段时间阿里云函数计算推出了Java8版本的编译环境，我结合一个java语言来完成函数计算的代码编写，该示例主要是模拟一个网站图片爬虫，把指定网站的指定页面的图片全部获取并保存到对象存储中，画了一个简单的架构图如下：

流程讲解：

用户输入某个网站地址，并把爬虫系统部署到函数计算上，执行后函数计算会自动把某网站的图片抓取到本地，并通过内网的方式上传到对象存储（OSS）上。这里涉及到两段代码，一段是网站爬取图片的代码，一段是把图片上传到对象存储（略），我们下面结合上面的框图来看看代码构成。

在函数计算上执行的代码：

/*
 * Created on 2017-9-16
 *
 * TODO To change the template for this generated file go to
 * Window - Preferences - Java - Code Style - Code Templates
 */
package com.aliyun.function.crawler;

/**
 * @author fuhw
 *
 * TODO To change the template for this generated type comment go to Window -
 * Preferences - Java - Code Style - Code Templates
 */
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.List;

import com.aliyun.fc.runtime.Context;
import com.aliyun.fc.runtime.StreamRequestHandler;

public class index implements StreamRequestHandler {

	private static final String URL = "https://www.csdn.com";
	private static final String ECODING = "UTF-8";
	private static final String IMGURL_REG = "<img.*src=(.*?)[^>]*?>";
	private static final String IMGSRC_REG = "http:\"?(.*?)(\"|>|\\s+)";

	@Override public void handleRequest(InputStream inputStream,
			OutputStream outputStream, Context context) throws IOException {
		List<String> imgUrl ;
		try {
			catchImg cm = new catchImg();
			String HTML = cm.getHTML(URL);
			imgUrl = cm.getImageUrl(HTML);
			List<String> imgSrc = cm.getImageSrc(imgUrl);
			cm.Download(imgSrc);
		} catch (Exception e) {
			System.out.println("fail download image! ");
		}

		outputStream.write("download image is OK!".getBytes());
	}
}

爬虫系统代码：

package com.aliyun.function.crawler;

import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class catchImg {

	// 地址
	private static final String URL = "http://www.csdn.net";

	// 编码
	private static final String ECODING = "UTF-8";

	// 获取img标签正则
	private static final String IMGURL_REG = "<img.*src=(.*?)[^>]*?>";

	// 获取src路径的正则
	private static final String IMGSRC_REG = "http:\"?(.*?)(\"|>|\\s+.(gif|png|jpg|bmp|jpeg|tif|tiff))";

	public static void main(String[] args) throws Exception {
		catchImg cm = new catchImg();
		//获得html文本内容
		String HTML = cm.getHTML(URL);
		//获取图片标签
		List<String> imgUrl = cm.getImageUrl(HTML);
		//获取图片src地址
		List<String> imgSrc = cm.getImageSrc(imgUrl);
		//下载图片
		cm.Download(imgSrc);
	}

	/***************************************************************************
	 * 获取HTML内容
	 *
	 * @param url
	 * @return
	 * @throws Exception
	 */
	public String getHTML(String url) throws Exception {
		URL uri = new URL(url);
		URLConnection connection = uri.openConnection();
		InputStream in = connection.getInputStream();
		byte[] buf = new byte[1024];
		int length = 0;
		StringBuffer sb = new StringBuffer();
		while ((length = in.read(buf, 0, buf.length)) > 0) {
			sb.append(new String(buf, ECODING));
		}
		in.close();
		return sb.toString();
	}

	/***************************************************************************
	 * 获取ImageUrl地址
	 *
	 * @param HTML
	 * @return
	 */
	public List<String> getImageUrl(String HTML) {
		Matcher matcher = Pattern.compile(IMGURL_REG).matcher(HTML);
		List<String> listImgUrl = new ArrayList<String>();
		while (matcher.find()) {
			listImgUrl.add(matcher.group());
		}
		return listImgUrl;
	}

	/***************************************************************************
	 * 获取ImageSrc地址
	 *
	 * @param listImageUrl
	 * @return
	 */
	public List<String> getImageSrc(List<String> listImageUrl) {
		List<String> listImgSrc = new ArrayList<String>();
		for (String image : listImageUrl) {
			Matcher matcher = Pattern.compile(IMGSRC_REG).matcher(image);
			while (matcher.find()) {
				String str = matcher.group().substring(0,
						matcher.group().length() - 1);
				listImgSrc.add(str);
			}
		}
		return listImgSrc;
	}

	/***************************************************************************
	 * 下载图片
	 *
	 * @param listImgSrc
	 */
	public void Download(List<String> listImgSrc) {
		try {
			//System.out.println("listImgSrc size = "+listImgSrc.size());
			for (String url : listImgSrc) {
				String imageName = url.substring(url.lastIndexOf("/") + 1, url
						.length());
				URL uri = new URL(url);
				InputStream in = uri.openStream();
//				FileOutputStream fo = new FileOutputStream("/tmp/"
				FileOutputStream fo = new FileOutputStream(""
						+ new File(imageName));
				byte[] buf = new byte[1024];
				int length = 0;
				System.out.println("Start : " + url);
				while ((length = in.read(buf, 0, buf.length)) != -1) {
					fo.write(buf, 0, length);
				}
				in.close();
				fo.close();
				//System.out.println("success");
			}
		} catch (Exception e) {
			//e.printStackTrace();
			//System.out.println("fail download in void Download function");
		}
	}
}