Java爬虫爬取漫画示例

// 获取的script 无法直接解析，必须先将 page url 取出来，
// 这里以 [ ] 为界限，分割字符串。
String pageUrls = script.data();
int start = pageUrls.indexOf("[");
int end = pageUrls.indexOf("]") + 1;
String urls = pageUrls.substring(start, end);
//json 转 集合，这个可以总结一下，不熟悉。
List<String> urlList = JSONArray.parseArray(urls, String.class);

package com.comic;

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.comic;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.List;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.stream.Collectors;

import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.config.CookieSpecs;
import org.apache.http.client.config.RequestConfig;
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.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import com.alibaba.fastjson.JSONArray;

public class ComicSpider {
	private static final String DIR_PATH = "D:/DBC/comic/";
	private String url;
	private String root;
	private CloseableHttpClient httpClient;
	
	public ComicSpider(String url, String root) {
		this.url = url;
		// 这里不做非空校验，或者使用下面这个。
		// Objects.requireNonNull(root);
		if (root.charAt(root.length()-1) == '/') {
			root = root.substring(0, root.length()-1);
		}
		
		this.root = root;
		this.httpClient = HttpClients.createDefault();
	}
	
	public void start() {
		try {
			String html = this.getHtml(url);    //获取漫画主页数据
			List<Chapter> chapterList = this.mapChapters(html);  //解析数据，得到各话的地址
			this.download(chapterList);   //依次下载各话。
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	
	private String getHtml(String url) throws ClientProtocolException, IOException {
		HttpGet get = new HttpGet(url);
		//下面这两句，是因为总是报一个 Invalid cookie header，然后我在网上找到的解决方法。（去掉的话，不影响使用）。
		RequestConfig defaultConfig = RequestConfig.custom().setCookieSpec(CookieSpecs.STANDARD).build();
		get.setConfig(defaultConfig);
		//因为是初学，而且我这里只是请求一次数据即可，这里就简单设置一下 UA
		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");
		HttpEntity entity = null;
		String html = null;
		try (CloseableHttpResponse response = httpClient.execute(get)) {
			int statusCode = response.getStatusLine().getStatusCode();
			if (statusCode == 200) {
				entity = response.getEntity();
				if (entity != null) {
					html = EntityUtils.toString(entity, "UTF-8");
				}
			}
		}
		return html;
	}
	
	
	//获取章节名 链接地址
	private List<Chapter> mapChapters(String html) {
		Document doc = Jsoup.parse(html, "UTF-8");	
		Elements name_urls = doc.select("#chapter-list-1 > li > a");
		
		return name_urls.stream()
				.map(name_url->new Chapter(name_url.text(),
						root+name_url.attr("href")))
				.collect(Collectors.toList());
	}
	
	
	public void download(List<Chapter> chapterList) {
		chapterList.forEach(chapter->{
			//按照章节创建文件夹，每一个章节一个文件夹存放。
			File dir = new File(DIR_PATH, chapter.getName());
			if (!dir.exists()) {
				if (!dir.mkdir()) {
					try {
						throw new FileNotFoundException("无法创建指定文件夹"+dir);
					} catch (FileNotFoundException e) {
						e.printStackTrace();
					}
				}
				
				//开始按照章节下载	
				try {
					List<ComicPage> urlList = this.getPageUrl(chapter);
					urlList.forEach(page->{
						SinglePictureDownloader downloader = new SinglePictureDownloader(page, dir.getAbsolutePath());
						downloader.download();
					});
				} catch (IOException e) {
					e.printStackTrace();
				}
			}
		});
	}
	
	//获取每一个页漫画的位置
	private List<ComicPage> getPageUrl(Chapter chapter) throws IOException {
		String html = this.getHtml(chapter.getUrl());
		 Document doc = Jsoup.parse(html, "UTF-8");
		 Element script = doc.getElementsByTag("script").get(2); //获取第三个脚本的数据
		 // 获取的script 无法直接解析，必须先将 page url 取出来，
		 // 这里以 [ ] 为界限，分割字符串。
		 String pageUrls = script.data();
		 int start = pageUrls.indexOf("[");
		 int end = pageUrls.indexOf("]") + 1;
		 String urls = pageUrls.substring(start, end);
		 //json 转 集合，这个可以总结一下，不熟悉。
		 List<String> urlList = JSONArray.parseArray(urls, String.class);

		 AtomicInteger index=new AtomicInteger(0);  //我无法使用索引，这是别人推荐的方式
		 return urlList.stream()   //注意这里拼接的不是 root 路径，而是一个新的路径
		 		.map(url->new ComicPage(index.getAndIncrement(),"https://restp.dongqiniqin.com//"+url))
		 		.collect(Collectors.toList());
	}
}

 AtomicInteger index=new AtomicInteger(0);  //我无法使用索引，这是别人推荐的方式
 return urlList.stream()   //注意这里拼接的不是 root 路径，而是一个新的路径
 		.map(url->new ComicPage(index.getAndIncrement(),"https://restp.dongqiniqin.com//"+url))
 		.collect(Collectors.toList());

package com.comic;

public class Chapter {
	private String name;  //章节名
	private String url;   //对应章节的链接
	
	public Chapter(String name, String url) {
		this.name = name;
		this.url = url;
	}
	public String getName() {
		return name;
	}
	public String getUrl() {
		return url;
	}
	@Override
	public String toString() {
		return "Chapter [name=" + name + ", url=" + url + "]";
	}
}

package com.comic;

public class ComicPage {
	private int number;  //每一页的序号
	private String url;  //每一页的链接
	
	public ComicPage(int number, String url) {
		this.number = number;
		this.url = url;
	}
	
	public int getNumber() {
		return number;
	}
	public String getUrl() {
		return url;
	}
}

package com.comic;

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 CloseableHttpClient httpClient;
	private ComicPage page;
	private String filePath;
	
	private 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 "
	};
	
	public SinglePictureDownloader(ComicPage page, String filePath) {
		this.httpClient = HttpClientUtil.getHttpClient();
		this.page = page;
		this.filePath = filePath;
	}
	
	public void download() {
		HttpGet get = new HttpGet(page.getUrl());
		String url = page.getUrl();
		//取文件的扩展名
		String prefix = url.substring(url.lastIndexOf("."));
		
		Random rand = new Random();
		//设置请求头
		get.setHeader("User-Agent", headers[rand.nextInt(headers.length)]);
		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, page.getNumber()+prefix);
					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.comic;

public class Main {
	public static void main(String[] args) {
		String root = "https://www.manhuaniu.com/"; //网站根路径，用于拼接字符串
		String url = "https://www.manhuaniu.com/manhua/5830/";  //第一张第一页的url
		ComicSpider spider = new ComicSpider(url, root);
		spider.start();
	}
}