java 爬小说

package com.jby.resource.service.impl;

import org.jsoup.Connection;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.junit.Test;

import java.io.*;

/**

• txt小说下载

• @author Administrator
  */
  public class MyTxt {

  static String url = “http://www.zzzcn.org/8_8187/3899817.html”;

  @Test
  public void addition_isCorrect() {
  createFile();
  start();
  }

  public static void start() {
  parse(url);
  }

  private static void parse(String serverString) {
  System.out.println(serverString);
  // 可以使用Jsoup自带的网络请求方式：
  Document document = null;
  try {
  Connection conn = Jsoup.connect(serverString).timeout(3000);
  conn.header(“User-Agent”, “Mozilla/5.0 (Windows NT 6.1; WOW64; rv:33.0) Gecko/20100101 Firefox/33.0”);
  document = conn.get();
  } catch (Exception e) {
  // e.printStackTrace();
  System.err.println(e.getMessage());
  }
  // String string = document.toString();
  // System.out.println(“document:” + string);

   // 解析xml
   // document = (Document) Jsoup.parse(serverString);
   if (document == null) {
       System.err.println("链接错误  正在重试。。。");
       try {
           Thread.sleep(3000);
       } catch (InterruptedException e) {
           throw new RuntimeException(e);
       }
       start();
       return;
   }
  
   Elements title = document.select("div");// 得到table标签中的内容
   for (Element item : title) {
       String name = item.attr("class");
       if (name.equals("bookname")) {
           Elements h1 = item.select("h1");
           String txt = "\r\n" + h1.text();
           getTxt(txt);
           System.out.println(txt);
       }
   }
  
   Elements div = document.select("div");// 得到table标签中的内容
   for (Element item : div) {
       // System.out.println("--------------------------");
       // System.out.println(item);
  
       String name = item.attr("id");
       if (name.equals("content")) {
           System.out.println(item.text().length());
           String[] line = item.text().split(" ");
           int n = line.length;
           for (int i = 0; i < n; i++) {
               getTxt(line[i]);
           }
       }
   }
  
   Elements div1 = document.select("div");// 得到table标签中的内容
   for (Element item : div1) {
       String name = item.attr("class");
       if (name.equals("bottem2")) {
  
           Elements a = item.select("a");
           for (Element item1 : a) {
               String name1 = item1.text();
               if (name1.equals("下一章")) {
                   String href = item1.attr("href");
                   System.out.println(href);
  
                   if (!href.contains(".html")) {
                       endTxt();
                   } else {
                       url = "http://www.zzzcn.org" + href;
                       start();
                       return;
                   }
               }
           }
       }
   }
  

  }

  public static void getTxt(String msg) {
  String t = msg;
  saveTxt(t + “\r\n”);
  }

  public static void endTxt() {
  try {
  writer.close();
  } catch (IOException e) {
  // TODO Auto-generated catch block
  e.printStackTrace();
  }
  }

  static BufferedWriter writer;

  public static void createFile() {
  File f = new File(“D:\txt\2.txt”);
  FileOutputStream writerStream = null;
  try {
  writerStream = new FileOutputStream(f, true);
  writer = new BufferedWriter(new OutputStreamWriter(writerStream, “UTF-8”));
  } catch (FileNotFoundException | UnsupportedEncodingException e) {
  e.printStackTrace();
  }
  }

  public static void saveTxt(String msg) {
  try {
  // System.out.println(msg);
  writer.write(msg);
  writer.flush();
  } catch (IOException e) {
  e.printStackTrace();
  }
  }

}