import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Main {

    public static void main(String[] args) throws Exception{
        //获取整个网页内容
        String str;
        //写入要抓取的url
        URL url = new URL("https://www.hongxiu.com/book/11809422404543803#Catalog");
        URLConnection conn = url.openConnection();
        InputStream is = conn.getInputStream();
        StringBuffer sb = new StringBuffer();
        BufferedReader reader = new BufferedReader(new InputStreamReader(conn.getInputStream(), "utf-8"));
        while((str=reader.readLine())!=null){
            sb.append(str);
        }
        //进行正则匹配
        String content = sb.toString();
        String regex = "<(a.*? data-cid=\"(.*?)\")>(.*?)</a>";
        Pattern pattern = Pattern.compile(regex, Pattern.DOTALL);
        Matcher matcher = pattern.matcher(content);

        //找出所需要的内容
        while(matcher.find()) {
            String s=matcher.group(2);
            String href = "https:"+s.substring(0, 61);//处理字符串
            String tittle = matcher.group(3);
            if(href.contains("https://www.hongxiu.com/chapter/")){
                try {
                    // 下载链接和标题
                    downHtm(href, tittle);
                    //根据章节链接存放内容
                    downTxt(href,tittle);
                } catch(Exception e) {
                    e.printStackTrace();
                }
            }
        }
        is.close();
    }

    public static void downTxt(String href, String tittle) throws Exception{
        //获取整个网页内容
        String str;
        //写入要抓取的url
        URL url = new URL(href);
        URLConnection conn = url.openConnection();
        InputStream is = conn.getInputStream();
        StringBuffer sb = new StringBuffer();
        BufferedReader reader = new BufferedReader(new InputStreamReader(conn.getInputStream(), "utf-8"));
        while((str=reader.readLine())!=null){
            sb.append(str);
        }
        //进行正则匹配---找出文章内容
        String regex = "<div class=\"read-content j_readContent\">(.*?)</div>";
        String content = sb.toString();
        Pattern pattern = Pattern.compile(regex, Pattern.DOTALL);
        Matcher matcher = pattern.matcher(content);
        //找出所需要的内容
        while(matcher.find()) {
            String pstring = matcher.group(1).replace("<p>", "").replace("<%-cInfo.content %>", "");
            File f=new File(tittle+".txt");
            FileWriter fw=null;
            fw = new FileWriter(f, true);
            fw.write(pstring);
            fw.flush();
            fw.close();

        }
        is.close();
    }

    public static void downHtm(String href,String tittle) throws Exception{
        //对于得到的url和标题----
        // 先写入一个目录（里面包含 目录和链接），点击链接之后跳转到本地文件的details目录，
        // 里面存放的是每一章节的内容
        File f=new File("1.html");
        FileWriter fw=null;

        fw = new FileWriter(f, true);
        fw.write("\r\n"+tittle+"  "+href+"\r\n");
        fw.flush();
        fw.close();

    }



}