想要免费看小说吗？java 爬虫 抓取小说

很多人找不到想要看的小说，今天就教大家一种方法，写个爬虫直接完事，啥都不说了上代码

package com.cn.love.ui;

import java.io.DataOutputStream;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.UnsupportedEncodingException;
import java.io.Writer;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.apache.http.HttpHost;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.conn.params.ConnRoutePNames;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.params.CoreConnectionPNames;
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;


public class HttpclientJsoup {
	/**
	 * Httpclient负责发送请求
	 * Jsoup负责解析
	 * @param args
	 * @throws IOException 
	 * @throws ClientProtocolException 
	 */
	public static void main(String[] args) throws ClientProtocolException, IOException {
		//创建httpClient对象
				HttpClient httpClient = new DefaultHttpClient();
				//设置响应时间，设置传输代码时间，设置服务器                                                                                            链接超时                                                                            传输超时														代理服务器
				//httpClient.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT, 1000).setParameter(CoreConnectionPNames.SO_TIMEOUT, 1000).setParameter(ConnRoutePNames.DEFAULT_PROXY, new HttpHost("124.88.67.52",83));
				//创建get请求      3406013 68章 3432974
				String url="";
				HttpGet httpGet=new HttpGet("http://www.17k.com/list/493239.html");
//				HttpGet httpGet=new HttpGet("http://www.readnovel.com/novel/120040.html");
				//向百度服务器发送请求，获取网页源码
				HttpResponse  response = httpClient.execute(httpGet);
				//EntityUtils工具类把网页实体转换成字符串
				String content = EntityUtils.toString(response.getEntity(), "utf-8");
				//拿到网页内容了 开始解析
				Document doc = Jsoup.parse(content);
				//使用元素选择器选择 网页内容
				Elements a= doc.select(".Main .Volume dd a");
				for (int i = 0; i < a.size(); i++) {
					Element eurl = a.get(i);
					url="http://www.17k.com/"+eurl.attr("href");
				
				HttpGet httpGet1=new HttpGet(url);
				HttpResponse  response1 = httpClient.execute(httpGet1);
				String content1 = EntityUtils.toString(response1.getEntity(), "utf-8");
				Document doc1 = Jsoup.parse(content1);
				Elements es= doc1.select("h1");
				Elements qw= doc1.select(".p #chapterContentWapper");
				//System.out.println(es);
//				for (Element e:es) {
//					System.out.println(e.text()+":"+e.attr("href"));
//				}
				File file = new File("D:" + File.separator + "修罗武神.txt");
				 try {
			            // 注意，这个地方，那个true的参数，代表如果这个文件已经存在了，就把新的内容添加到该文件的最后
			            // 如果你想重新创建新文件，把true改成false就好了
			            Writer writer = new OutputStreamWriter(new FileOutputStream(file, true), "UTF-8");
			            StringBuilder builder = new StringBuilder();
			            for (int j = 0; j < es.size(); j++) {
							Element h1 = es.get(j);
							Element test = qw.get(j);
							System.out.println(h1.text());
							System.out.println(test.text());
							builder.append(h1.text());
							builder.append("
");
							builder.append(test.text());
							builder.append("
");
						 }	
			            writer.write(builder.toString());
			            writer.close();
			        } catch (UnsupportedEncodingException e) {
			            e.printStackTrace();
			        } catch (FileNotFoundException e) {
			            e.printStackTrace();
			        } catch (IOException e) {
			            e.printStackTrace();
			        }
				
				}
				
	}	
}