java实现自动下载免费小说

在百度上看到别人要下一些小说，就想自己写个下小说的玩玩。

以下为自己玩玩的，不必当真。

package edu.uci.ics.crawler4j.test;import java.io.FileOutputStream;import java.io.IOException;import java.io.OutputStream;import java.io.OutputStreamWriter;import java.util.regex.Matcher;import java.util.regex.Pattern;import org.apache.http.HttpEntity;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;/** *  * @author andy.wang * @时间 2017年5月27日 */public class Plzl {public static final int READ_SIZE = 8 * 1024;private static String path="F://three//";private static String domainName="http://www.58xs.com";public static void main(String[] args) throws Exception {String s=domainName+"/html/122/122467/6226722.html";Plzl p = new Plzl();p.requestByGetMethod(s);for (int i = 0; i < 151; i++) {System.out.println("info:"+s);String u=p.requestByGetMethod(s);if ("".equals(u)) {//如果没拿到下一章的就再拿一次u=p.requestByGetMethod(s);if ("".equals(u)) {System.out.println("error:"+s);//如果还是出错就报错出来}}if (!"".equals(u)) {s=u.trim();}Thread.sleep(2000);}} private CloseableHttpClient getHttpClient(){        return HttpClients.createDefault();    }         private void closeHttpClient(CloseableHttpClient client) throws IOException{        if (client != null){            client.close();        }    }/** * 通过GET方式发起http请求 */public String requestByGetMethod(String url){String u="";//创建默认的httpClient实例CloseableHttpClient httpClient = getHttpClient();try {//用get方法发送http请求HttpGet get = new HttpGet(url);CloseableHttpResponse httpResponse = null;//发送get请求httpResponse = httpClient.execute(get);try{//response实体HttpEntity entity = httpResponse.getEntity();if (null != entity){String s =EntityUtils.toString(entity,"utf-8");u= read(s);}}finally{httpResponse.close();}} catch (Exception e) {e.printStackTrace();}finally{try{closeHttpClient(httpClient);} catch (IOException e){e.printStackTrace();}}return u;}private String read(String s) throws IOException{String u="";String txt =path+"//pmzlx.txt";// 创建文件输出流，第二个参数表示为追加的方式输出OutputStream os = new FileOutputStream(txt, true);// 转换为字符输出流，并指定文件编码为utf-8OutputStreamWriter osw = new OutputStreamWriter(os, "UTF-8");// 以自定编码的方式读取输入流if (s.lastIndexOf("content")>0) {String tilte = s.substring(s.indexOf("<h1>")+4,s.indexOf("</h1>"));//获取章节名称osw.write(tilte+"\r\n");s =s.substring(s.indexOf("下一章"),s.lastIndexOf("下一章"));//截取内容u = s.substring(s.length()-31, s.length()-2);//获取下一章的urls=s.substring(s.lastIndexOf("content")+9,s.length());//截取正文s=s.substring(0,s.indexOf("上一章"));//截取正文s=delHTMLTag(s);//去除html并且osw.write(s.replaceAll("    ", "\r\n")+"\r\n");//空格替换为换行然后写到txt文本里osw.flush();}osw.close();os.close();if ("".equals(u)) {return u;}return domainName+u;}    public String delHTMLTag(String htmlStr){         String regEx_script="<script[^>]*?>[\\s\\S]*?<\\/script>"; //定义script的正则表达式         String regEx_style="<style[^>]*?>[\\s\\S]*?<\\/style>"; //定义style的正则表达式         String regEx_html="<[^>]+>"; //定义HTML标签的正则表达式                  Pattern p_script=Pattern.compile(regEx_script,Pattern.CASE_INSENSITIVE);         Matcher m_script=p_script.matcher(htmlStr);         htmlStr=m_script.replaceAll(""); //过滤script标签                  Pattern p_style=Pattern.compile(regEx_style,Pattern.CASE_INSENSITIVE);         Matcher m_style=p_style.matcher(htmlStr);         htmlStr=m_style.replaceAll(""); //过滤style标签                  Pattern p_html=Pattern.compile(regEx_html,Pattern.CASE_INSENSITIVE);         Matcher m_html=p_html.matcher(htmlStr);         htmlStr=m_html.replaceAll(""); //过滤html标签         return htmlStr.trim(); //返回文本字符串     } }