2. 压缩流/解压缩流 Hutool工具包 Commons-io工具包 URL Java爬虫

压缩流/解压缩流

解压的本质:就是把zip文件中的每一个文件(zipEntry对象)拷贝到另一个文件中

文件解压程序(默认目录排在文件前面出现,有漏洞)

java 复制代码

public static void unzip(File src,File dest) throws IOException {

//创建解压缩流对象
ZipInputStream zis=new ZipInputStream(new FileInputStream(src));
//获取流中的每一个zipEntry对象
ZipEntry entry;
while((entry=zis.getNextEntry())!=null){
    //判断entry是否是文件夹

    if(entry.isDirectory()){
        File file=new File(dest,entry.getName());
        file.mkdirs();
    }
    else {

        //创建字节输出流对象
        FileOutputStream fos=new FileOutputStream(new File(dest,entry.getName()));
        int b;
        while((b=zis.read())!=-1){
            fos.write(b);
        }
        fos.close();
        zis.closeEntry();
    }
}
zis.close();
}

压缩单个文件的代码:

java 复制代码

public static void toZip(File src,File dest) throws IOException {
		//创建压缩流对象,表示要写在哪里
		ZipOutputStream zos=new ZipOutputStream(new FileOutputStream(new File(dest,"Rance.zip")));
		//把Rance.md文件当成ZipEntry对象
		ZipEntry ze=new ZipEntry("Rance.md");
		//把ZipEntry对象放到压缩流中
		zos.putNextEntry(ze);
		//创建写入对象
		FileInputStream fis=new FileInputStream(src);
		int b;
		while((b=fis.read())!=-1){
		  zos.write(b);
		}
		fis.close();
		zos.closeEntry();
		zos.close();
}

压缩文件夹

java 复制代码

public static void toDirZip(File src) throws IOException {

    String parent = src.getParent();
    String name = src.getName();
    //创建压缩流对象,关联压缩包
    ZipOutputStream zos=new ZipOutputStream(new FileOutputStream(new File(parent+"\\"+name+".zip")));
    //获取src里的每一个文件,变成ZipEntry对象,放入到压缩包中
    toZip(src,zos,name);
    zos.close();
}

private static void toZip(File src, ZipOutputStream zos,String name) throws IOException {
    File[] files = src.listFiles();
    if(files==null) return;
    for (File file : files) {
        if(file.isFile()){
            ZipEntry zip=new ZipEntry(name+"\\"+file.getName());
            zos.putNextEntry(zip);
            //写入文件的逻辑
            FileInputStream fis=new FileInputStream(file);
            int b;
            while((b=fis.read())!=-1){
                zos.write(b);
            }
        }else{
            toZip(file,zos,name+"\\"+file.getName());
        }
    }
    zos.closeEntry();
}

Commons-io工具包

Hutool工具包:

手动从网页中爬取数据:

java 复制代码

//通过链接爬取数据
String familyNameNet="https://hanyu.baidu.com/shici/detail?from=aladdin&pid=0b2f26d4c0ddb3ee693fdb1137ee1b0d&smp_names=termBrand2%2Cpoem1";
String boyNameNet="https://qiming.hao86.com/view/26491/";
String girlNameNet="https://qiming.hao86.com/view/181658/";
//爬取html文件
String s = webCrawler(familyNameNet);
String boy=webCrawler(boyNameNet);
String girl=webCrawler(girlNameNet);
//通过正则表达式把html文件中的关键数据分别出来
ArrayList<String> family = getData(s, "([\\u4e00-\\u9fa5]{4})(，|。)", 1);
ArrayList<String> boys=getData(boy,"、([\\u4e00-\\u9fa5]{2})",1);
ArrayList<String> girlsName=getData(girl,"\\)([\\u4e00-\\u9fa5]{2})",1);
//处理数据
ArrayList<String> familyName=new ArrayList<>();
for (String string : family) {
    for (int i = 0; i < string.length(); i++) {
        char c = string.charAt(i);
        familyName.add(c+"");
    }
}
//去重
ArrayList<String> boysName=new ArrayList<>();
for (String string : boys) {
    if(!boysName.contains(string)){
        boysName.add(string);
    }
}
ArrayList<String> infos = getInfos(familyName, boysName, girlsName, 70, 60);
//写出数据
BufferedWriter bw=new BufferedWriter(new FileWriter("nametest.txt"));
for (String info : infos) {
    bw.write(info);
    bw.newLine();
}
bw.close();
}

private static ArrayList<String> getInfos(ArrayList<String> familyName, ArrayList<String> boysName, ArrayList<String> girlsName, int boyCount, int girlCount) {
ArrayList<String> list=new ArrayList<>();
HashSet<String> boyhs=new HashSet<>();
//创建男的"张三-男-20"
while(true){
    if(boyhs.size()==boyCount){
        break;
    }
    Collections.shuffle(familyName);
    Collections.shuffle(boysName);
    String s=familyName.getFirst()+boysName.getFirst();
    boyhs.add(s);
}

HashSet<String> girlhs=new HashSet<>();
//创建男的"张三-女-20"
while(true){
    if(girlhs.size()==girlCount){
        break;
    }
    Collections.shuffle(familyName);
    Collections.shuffle(girlsName);
    String s=familyName.getFirst()+girlsName.getFirst();
    girlhs.add(s);
}
//男生年龄在18-30
Random r=new Random();
for (String boyh : boyhs) {
    int age=r.nextInt(13)+18;
    String s=boyh+"-男-"+age;
    list.add(s);
}

//女生年龄在18-27
for (String girlh : girlhs) {
    int age=r.nextInt(10)+18;
    String s=girlh+"-女-"+age;
    list.add(s);
}
Collections.shuffle(list);
return list;
}


public static String webCrawler(String net) throws IOException {
//创建url对象
URL url=new URL(net);
//建立连接
URLConnection connection = url.openConnection();
//创建流
InputStreamReader isr=new InputStreamReader(connection.getInputStream());
int b;
StringBuilder sb=new StringBuilder();
while((b=isr.read())!=-1){
    sb.append((char) b);
}
return sb.toString();
}

使用HuTool包进行数据爬取和文件输出:

java 复制代码

String s = HttpUtil.get("https://hanyu.baidu.com/shici/detail?from=aladdin&pid=0b2f26d4c0ddb3ee693fdb1137ee1b0d&smp_names=termBrand2%2Cpoem1");
List<String> all = ReUtil.findAll("([\\u4e00-\\u9fa5]{4})(，|。)", s, 1);
System.out.println(all);
FileUtil.writeLines(all,"nametest.txt","UTF-8");

随机点名器:

java 复制代码

BufferedReader br=new BufferedReader(new FileReader("nametest.txt"));
ArrayList<String> list=new ArrayList<>();
String s;
while((s=br.readLine())!=null){
    list.add(s);
}
br.close();
Collections.shuffle(list);
ArrayList<String> boys=new ArrayList<>();
ArrayList<String> girls=new ArrayList<>();
for (String string : list) {
    if(string.contains("男"))boys.add(string);
    else girls.add(string);
}
int boyCount=0;
int girlCount=0;
Random random=new Random();
while(boyCount!=100000) {
    int n = random.nextInt(10);
    if (n > 6){// System.out.println(girls.getFirst());
        girlCount++; }

    else {
        //System.out.println(boys.getFirst());
        boyCount++;
    }
}
System.out.println(boyCount);
System.out.println(girlCount);