爬虫获取网站内的数据，获得完整姓名
网站一：姓氏
网站二：男生名字
网站三：女生名字
进行拼接，获取完整的男生女生姓名。
//导包
import org.apache.commons.io.FileUtils;
import java.io.*;
import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;public class test {public static void main(String[] args) throws IOException {String familynamenet="https://hanyu.baidu.com/shici/detail?pid=0b2f26d4c0ddb3ee693fdb1137ee1b0d&from=kg0";String boynamenet="http://www.haoming8.cn/baobao/10881.html//oracle.com/java/technologies/javase/javase-jdk8-downloads.html";String girlnamenet="http://www.haoming8.cn/baobao/7641.html//oracle.com/java/technologies/javase/javase-jdk8-downloads.html";String familynamestr=webcrawler(familynamenet);String boynamestr=webcrawler(boynamenet);String girlnamestr=webcrawler(girlnamenet);ArrayList<String> boynametemplist=getData(boynamestr,"([\\u4E00-\\u9FA5]){2}(、|。)",1);ArrayList<String> familynametemplist=getData(familynamestr,"(.{4})(,|.)",1);ArrayList<String> girlnametemplist=getData(girlnamestr,"(.. ){4}..",0);//处理数据ArrayList<String> familynamelist=new ArrayList<>();for(String str:familynametemplist) {for (int i = 0; i < str.length(); i++) {char c = str.charAt(i);familynamelist.add(c+"");}}ArrayList<String> boynamelist=new ArrayList<>();for(String str:boynametemplist) {if(!boynamelist.contains(str)){boynamelist.add(str);}}ArrayList<String> girlnamelist=new ArrayList<>();for(String str:girlnametemplist) {String[] arr=str.split(" ");for(int i=0;i<arr.length;i++){girlnamelist.add(arr[i]);}}//生成数据// 姓名（唯一）]getinfos(familynamelist,boynamelist,girlnamelist,10,10);}/*方法作用：获取男生和女生信息形参一：装着姓氏的集合参数二：装着男生姓名的集合参数三：装着女生姓名的集合参数四；男生个数参数五：女生个数*/public static ArrayList<String>getinfos(ArrayList<String> familynamelist,ArrayList<String> boynamelist,ArrayList<String> girlnamelist,int boycount,int girlcount){//生成男生不重复的名字HashSet<String> boyhs=new HashSet<>();while(true){if(boyhs.size()==boycount){break;}Collections.shuffle(familynamelist);Collections.shuffle(boynamelist);boyhs.add(familynamelist.get(0)+boynamelist.get(0));}HashSet<String> girlhs=new HashSet<>();while(true) {if (girlhs.size() == girlcount) {break;}Collections.shuffle(familynamelist);Collections.shuffle(girlnamelist);girlhs.add(familynamelist.get(0) + girlnamelist.get(0));}System.out.println(boyhs);System.out.println(girlhs);return null;}/*getData()方法作用：根基正则表达式获取字符串中的数据。参数一：完整字符串参数二：正则表达式参数三：返回值：真正想要的数据*/public static ArrayList<String> getData(String str,String regex,int index){ArrayList<String> list=new ArrayList<>();Pattern pattern=Pattern.compile(regex);Matcher matcher=pattern.matcher(str);while(matcher.find()){list.add(matcher.group(index));}return list;}/*webcrawler()方法作用：从网络中爬取数据，把数据拼接成字符串返回形参：网址返回值：爬取到的所有数据。*/public static String webcrawler(String net) throws IOException {StringBuilder sb=new StringBuilder();URL url=new URL(net);URLConnection conn=url.openConnection();InputStreamReader isr=new InputStreamReader(conn.getInputStream());int ch;while((ch=isr.read())!=-1){sb.append((char)ch);}isr.close();return sb.toString();}
}
登陆操作：
正确的用户名和密码保存在文件中，先从文件中读取，再与输入的进行比较判断。
public class test {public static void main(String[] args) throws IOException {BufferedReader br=new BufferedReader(new FileReader("src\\a.txt"));String line=br.readLine();br.close();String[] userInfo=line.split("&");String[] arr1=userInfo[0].split("=");String[] arr2=userInfo[1].split("=");String rightusername=arr1[1];String rightpassword=arr2[1];Scanner sc=new Scanner(System.in);System.out.println("请输入用户名：");sc.nextLine();String username=sc.nextLine();System.out.println("请输入密码：");String password=sc.nextLine();if(rightusername.equals(username)&&rightpassword.equals(password)){System.out.println("登陆成功");}else{System.out.println("登陆失败");}}
}