IO练习爬取数据姓名并在本地保存

注意代码中使用了hutool包

hutool: 🍬小而全的Java工具类库,使Java拥有函数式语言般的优雅,让Java语言也可以“甜甜的”。 (gitee.com)

package a_综合练习;

import cn.hutool.core.io.FileUtil;

import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.nio.charset.Charset;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class a_爬取名字 {
    public static void main(String[] args) throws IOException {
        String nameFirst = "https://zhuanlan.zhihu.com/p/25056561";
        String boynames = "http://www.haoming8.cn/baobao/10881.html";
        String girlName = "http://www.haoming8.cn/baobao/7641.html";
        String nameFirstContent = webCrawler(nameFirst);
        String boyNameContent = webCrawler(boynames);
        String girlNameContent = webCrawler(girlName);
        String nameFirstRegex = "(. ){7}.";
        String zenze = "([\\u4E00-\\u9FA5]{2})(、|。)";
        String girlNameRegex = "(.. ){4}..";
        //处理男孩数据
        ArrayList<String> boyNameTemporaryList = panDuan(boyNameContent, zenze, 1);
        HashSet<String> boyNameSet = boyNameDataProcessing(boyNameTemporaryList);
        System.out.println(boyNameSet);
        //处理女孩数据
        ArrayList<String> girlNameTemporaryList = panDuan(girlNameContent, girlNameRegex, 0);
        HashSet<String> girlNameSet = girlNameDateProcessing(girlNameTemporaryList);
        System.out.println(girlNameSet);
        //处理姓数据
        ArrayList<String> nameFirstTemporaryList = panDuan(nameFirstContent, nameFirstRegex, 0);
        HashSet<String> nameFirstSet = NameFirstDataProcessing(nameFirstTemporaryList);
        System.out.println(nameFirstSet);
        //进行拼接
        nameSplicing(boyNameSet,girlNameSet,nameFirstSet,40,20);
    }

    private static void nameSplicing(HashSet<String> boyNameSet, HashSet<String> girlNameSet, HashSet<String> nameset, int boyNumber, int girlNumber) {
        ArrayList<String> name = new ArrayList<>();
        int[] girlAge = {18, 28};
        int[] boyAge = {18, 30};
        ArrayList<String> boyName = splicing(boyNameSet, nameset, boyNumber, boyAge,'男');
        ArrayList<String> girlName = splicing(girlNameSet, nameset, girlNumber, girlAge,'女');
        name.addAll(boyName);
        name.addAll(girlName);
        FileUtil.writeLines(name, "C:\\IDEA代码\\javalean\\ab_IOlean\\src\\a_综合练习\\a.txt", Charset.forName("UTF-8"));
    }

    private static ArrayList<String> splicing(HashSet<String> nameLast, HashSet<String> nameFirst, int number, int[] ages,char sex) {
        ArrayList<String> name = new ArrayList<>();
        Random rs = new Random();
        for (int i = 0; i < number; i++) {
            String first = rondomSet(nameFirst);
            String last = rondomSet(nameLast);
            int age = rs.nextInt(ages[1] - ages[0] + 1) + ages[0];
            name.add(first + last +"-"+ sex+"-"+ age);
        }
        return name;
    }

    private static String rondomSet(HashSet<String> set) {
        Random rs = new Random();
        int rondomNumber = rs.nextInt(set.size());
        Iterator<String> iterator = set.iterator();
        for (int i = 0; i < rondomNumber - 1; i++) {
            iterator.next();
        }
        return iterator.next();
    }

    private static HashSet<String> NameFirstDataProcessing(ArrayList<String> NameFirstTemporaryList) {
        HashSet<String> NameFirstTemporarySet = new HashSet<>();
        for (String s : NameFirstTemporaryList) {
            String[] split = s.split(" ");
            NameFirstTemporarySet.addAll(Arrays.asList(split));
        }
        return NameFirstTemporarySet;
    }

    private static HashSet<String> girlNameDateProcessing(ArrayList<String> girlNameTemporaryList) {
        HashSet<String> girlNameTemporarySet = new HashSet<>();
        for (String s : girlNameTemporaryList) {
            String[] split = s.split(" ");
            girlNameTemporarySet.addAll(Arrays.asList(split));
        }
        return girlNameTemporarySet;
    }

    private static HashSet<String> boyNameDataProcessing(ArrayList<String> boyNameTemporaryList) {
        HashSet<String> boyNameTemporaryset = new HashSet<>();
        for (String s : boyNameTemporaryList) {
            boyNameTemporaryset.add(s);
        }
        return boyNameTemporaryset;
    }

    private static ArrayList<String> panDuan(String content, String regex, int dex) {
        ArrayList<String> list = new ArrayList<>();
        Pattern pattern = Pattern.compile(regex);
        Matcher matcher = pattern.matcher(content);
        while (matcher.find()) {
            String group = matcher.group(dex);
            list.add(group);
        }
        return list;
    }

    private static String webCrawler(String website) throws IOException {
        StringBuilder sb = new StringBuilder();
        URL url = new URL(website);
        URLConnection uc = url.openConnection();
        InputStreamReader isr = new InputStreamReader(uc.getInputStream());
        int ch;
        while ((ch = isr.read()) != -1) {
            sb.append((char) ch);
        }
        //关闭资源
        isr.close();
        //System.out.println(sb);
        return sb.toString();
    }
}

结果演示

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值