如何使用Java爬虫批量爬取图片

<dependency>
    <groupId>org.apache.httpcomponents</groupId>
    <artifactId>httpclient</artifactId>
    <version>4.5.6</version>
</dependency>
	
<dependency>
   	<groupId>org.jsoup</groupId>
   	<artifactId>jsoup</artifactId>
   	<version>1.11.3</version>
</dependency>

package com.picture;

public class Picture {
	private String title;
	private String url;
	
	public Picture(String title, String url) {
		this.title = title;
		this.url = url;
	}
	public String getTitle() {
		return this.title;
	}
	public String getUrl() {
		return this.url;
	}
}

package com.picture;

public class HeaderUtil {
	public static String[] headers = {
			"Mozilla/5.0 (windows NT 6.3; WOW64) AppleWEBKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
		    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
		    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
		    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
		    "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
		    "Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11",
		    "Opera/9.25 (Windows NT 5.1; U; en)",
		    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .net CLR 1.1.4322; .NET CLR 2.0.50727)",
		    "Mozilla/5.0 (compatible; Konqueror/3.5; linux) KHTML/3.5.5 (like Gecko) (Kubuntu)",
		    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12",
		    "Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9",
		    "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
		    "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "
	};
}

package com.picture;

import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.Random;

import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.util.EntityUtils;

import com.m3u8.HttpClientUtil;

public class SinglePictureDownloader {
	private String referer;
	private CloseableHttpClient httpClient;
	private Picture picture;
	private String filePath;
	
	
	
	public SinglePictureDownloader(Picture picture, String referer, String filePath) {
		this.httpClient = HttpClientUtil.getHttpClient();
		this.picture = picture;
		this.referer = referer;
		this.filePath = filePath;
	}
	
	public void download() {
		HttpGet get = new HttpGet(picture.getUrl());
		Random rand = new Random();
		//设置请求头
		get.setHeader("User-Agent", HeaderUtil.headers[rand.nextInt(HeaderUtil.headers.length)]);
		get.setHeader("referer", referer);
		System.out.println(referer);
		HttpEntity entity = null;
		try (CloseableHttpResponse response = httpClient.execute(get)) {
			int statusCode = response.getStatusLine().getStatusCode();
			if (statusCode == 200) {
				entity = response.getEntity();
				if (entity != null) {
					File picFile = new File(filePath, picture.getTitle());
					try (OutputStream out = new BufferedOutputStream(new FileOutputStream(picFile))) {
						entity.writeTo(out);
						System.out.println("下载完毕：" + picFile.getAbsolutePath());
					}
				}
			}
		} catch (ClientProtocolException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			try {
				//关闭实体，关于 httpClient 的关闭资源，有点不太了解。
				EntityUtils.consume(entity);
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}
}

package com.m3u8;

import org.apache.http.client.config.RequestConfig;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;

public class HttpClientUtil {
	private static final int TIME_OUT = 10 * 1000;
	private static PoolingHttpClientConnectionManager pcm;   //HttpClient 连接池管理类
	private static RequestConfig requestConfig;
	
	static {
		requestConfig = RequestConfig.custom()
				.setConnectionRequestTimeout(TIME_OUT)
				.setConnectTimeout(TIME_OUT)
				.setSocketTimeout(TIME_OUT).build();
		
		pcm = new PoolingHttpClientConnectionManager();
		pcm.setMaxTotal(50);
		pcm.setDefaultMaxPerRoute(10);  //这里可能用不到这个东西。
	}
	
	public static CloseableHttpClient getHttpClient() {
		return HttpClients.custom()
				.setConnectionManager(pcm)
				.setDefaultRequestConfig(requestConfig)
				.build();
	}
}

package com.picture;

import java.io.File;
import java.io.IOException;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;

import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

import com.m3u8.HttpClientUtil;


public class PictureSpider {

	private CloseableHttpClient httpClient;
	private String referer;
	private String rootPath;
	private String filePath;
	
	public PictureSpider() {
		httpClient = HttpClientUtil.getHttpClient();
	}
	
	
	public void start(List<String> urlList) {
		urlList.stream().forEach(url->{
			this.referer = url;
			
			String dirName = url.substring(22, url.length()-1);  //根据标题名字去创建目录
			//创建分类目录
			File path = new File("D:/DraGonFile/DBC/mzt/", dirName); //硬编码路径，需要用户自己指定一个
			if (!path.exists()) {
				path.mkdir();
				rootPath = path.toString();
			}
			
			for (int i = 1; i <= 10; i++) {  //分页获取图片数据，简单获取几页就行了
				this.page(url + "page/"+ 1);  
			}
		});
	}
	

	
	public void page(String url) {
		System.out.println("url：" + url);
		String html = this.getHtml(url);   //获取页面数据
		Map<String, String> picMap = this.extractTitleUrl(html);  //抽取图片的url
		
		if (picMap == null) {
			return ;
		}
		//获取标题对应的图片页面数据
		this.getPictureHtml(picMap);
	}
	
	private String getHtml(String url) {
		String html = null;
		HttpGet get = new HttpGet(url);
		get.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36");
		get.setHeader("referer", url);
		try (CloseableHttpResponse response = httpClient.execute(get)) {
			int statusCode = response.getStatusLine().getStatusCode();
			if (statusCode == 200) {
				HttpEntity entity = response.getEntity();
				if (entity != null) {
					html = EntityUtils.toString(entity, "UTf-8");   //关闭实体？
				}
			}
			else {
				System.out.println(statusCode);
			}
		} catch (ClientProtocolException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} 
		return html;
	}
	
	private Map<String, String> extractTitleUrl(String html) {
		if (html == null) {
			return null;
		}
		Document doc = Jsoup.parse(html, "UTF-8");
		Elements pictures = doc.select("ul#pins > li");
		
		//不知为何，无法直接获取 a[0]，我不太懂这方面的知识。
		//那我就多处理一步，这里先放下。
		Elements pictureA = pictures.stream()
				.map(pic->pic.getElementsByTag("a").first())
				.collect(Collectors.toCollection(Elements::new));
		
		return pictureA.stream().collect(Collectors.toMap(
				pic->pic.getElementsByTag("img").first().attr("alt"),
				pic->pic.attr("href")));
	}
	
	
	private void getPictureHtml(Map<String, String> picMap) {
		//进入标题页，在标题页中再次分页下载。
		picMap.forEach((title, url)->{
			//分页下载一个系列的图片，每个系列一个文件夹。
			File dir = new File(rootPath, title.trim());
			if (!dir.exists()) {
				dir.mkdir();
				filePath = dir.toString();  //这个 filePath 是每一个系列图片的文件夹
			}
			
			for (int i = 1; i <= 60; i++) {
				String html = this.getHtml(url + "/" + i);
				if (html == null) {
					//每个系列的图片一般没有那么多，
					//如果返回的页面数据为 null，那就退出这个系列的下载。
					return ; 
				}
				Picture picture = this.extractPictureUrl(html);
				System.out.println("开始下载");
				//多线程实在是太快了（快并不是好事，我改成单线程爬取吧）
				
				SinglePictureDownloader downloader = new SinglePictureDownloader(picture, referer, filePath);
				downloader.download();
				try {
					Thread.sleep(1500);   //不要爬的太快了，这里只是学习爬虫的知识。不要扰乱别人的正常服务。
					System.out.println("爬取完一张图片，休息1.5秒。");
				} catch (InterruptedException e) {
					e.printStackTrace();
				}
			}
		});
	}
	
	
	private Picture extractPictureUrl(String html) {
		Document doc = Jsoup.parse(html, "UTF-8");
		//获取标题作为文件名
		String title = doc.getElementsByTag("h2")
				.first()
				.text();

		//获取图片的链接（img 标签的 src 属性）
		String url = doc.getElementsByAttributeValue("class", "main-image")
				.first()
				.getElementsByTag("img")
				.attr("src");
		
		//获取图片的文件扩展名
		title = title + url.substring(url.lastIndexOf("."));		
		return new Picture(title, url);
	}
}

package com.picture;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;


public class BootStrap {
	public static void main(String[] args) {		
		//反爬措施：UA、refer 简单绕过就行了。
		//refer   https://www.mzitu.com
		
		//使用数组做一个爬虫队列
		String[] urls = new String[] {
			"https://www.mzitu.com/xinggan/",     
			"https://www.mzitu.com/zipai/"   
		};
		
		// 添加初始队列，启动爬虫
		List<String> urlList = new ArrayList<>(Arrays.asList(urls));
		PictureSpider spider = new PictureSpider();
		spider.start(urlList);
	}
}

for (int i = 1; i <= 10; i++) {  //分页获取图片数据，简单获取几页就行了
	this.page(url + "page/"+ 1);  
}