c++ 里面关于读取多个文件内容并去重

Question

上代码，读取了快递.txt、招聘.txt、电商.txt,目前输出结果是:
www.sohu.com 快递
www.baidu.com 快递
www.yijia.com 快递
www.goole.com 招聘
www.reset.com 招聘
www.baidu.com 招聘
www.baidu.com 电商
www.easy.com 电商
www.suhu.com 电商

还未实现的功能是把上面的输出去重存储到文件，像下面所示：

www.sohu.com 快递
www.baidu.com 快递 招聘 电商
.
.

不知道该怎么去重并输出，求解惑，人比较笨，最好详细点

#include <atlstr.h>
#include <iostream>
#include <string>
#include <fstream>  
#include <cstring>
#include <io.h> 
#include <set>
using namespace std;

void GetLineAndPrint(string in_name)  
{  
    //string tname;
    ifstream fin(in_name);
    int l = in_name.size();
    string tname(in_name.substr(0,l-4));

    int pos1 = tname.find_last_of('\\');
    string name(tname.substr(pos1+1));
    //ofstream fout("1.txt",ios::app);
    typedef set<string> set_t;
    //set_t s;

    if(!fin)  
    {  
        cerr<<"open file error"<<endl;  
        exit(-1);  
    }  
    string str;
    string s;
    while(getline(fin,str))  
    {    
        s.assign(str);
        set_t str;
        str.insert(name);
        set_t st;
        st.insert(s);
        for (set_t::const_iterator p = str.cbegin(); p != str.cend(); ++p)
            cout <<s <<" "<< *p <<endl;

    } 



} 




int main()
{ 
    struct _finddata_t fileinfo;  
    string in_path;  
    string in_name;  
    cin>>in_path;  
    string curr = in_path+"\\*.txt";  
    long handle;  
    if((handle=_findfirst(curr.c_str(),&fileinfo))==-1L)  
    {  
        cout<<"没有找到匹配文件!"<<endl; 
        system("pause");
        return 0;  
    }  
    else  
    {       
        in_name = in_path + "\\" + fileinfo.name ;  
        GetLineAndPrint(in_name);  
        while(!(_findnext(handle,&fileinfo)))  
        {  
            in_name = in_path + "\\" +fileinfo.name;  
            GetLineAndPrint(in_name);  
        }  
        _findclose(handle);  
    } 
    system("pause");
    return 0;
}

Answer 1

一个问题咋还问多次呢？

 #include <atlstr.h>
#include <winbase.h>
#include <algorithm>
#include <iostream>
#include <string>
#include <list> 
#include <fstream>  
#include <vector>
#include <cstring>
#include <io.h> 
using namespace std;



typedef struct tagMember
{
    char* name;
    char* group;
}Member;
// tagMember url[500];
//struct tagMember url[9];

Member url[] =
{
    { "搜索","www.baidu.com" },
    { "搜索","www.goole.com" },
    { "购物","www.baidu.com" },
    { "购物","www.kuaidi.com" },
    { "赌博","www.baidu.com" },
};

void GetLineAndPrint(string in_name)
{
    //string tname;
    ifstream fin(in_name);
    int l = in_name.size();
    string tname(in_name.substr(0, l - 4));
    //int pos = in_name.find('.');
    //if(pos>0)
    //   tname = in_name.left(pos);
    int pos1 = tname.find_last_of('\\');
    string name(tname.substr(pos1 + 1));
    ofstream fout("1.txt", ios::app);
    if (!fin)
    {
        cerr << "open file error" << endl;
        exit(-1);
    }
    string str;
    int i = 0;
    while (getline(fin, str))
    {
        fout << name << ' ' << str << endl;
        url[i].name = new char[str.length()]; //str.data();
        url[i].group = new char[str.length()];
        memset(url[i].name, 0, str.length());
        memset(url[i].group, 0, str.length());
        int spaceindex = str.find(' ');
        if (spaceindex != str.npos)
        {
            memcpy_s(url[i].name, spaceindex + 1, str.c_str(), spaceindex + 1);
            memcpy_s(url[i].group, str.length() - spaceindex - 1, str.substr(spaceindex + 1).c_str(), str.length() - spaceindex - 1);
        }
        i++;
    }
    fin.close();
    fout.close();
}




typedef list<char*> ListType;
typedef struct ListNode
{
    char* groupName;
    ListType *next;
}NodeType;

typedef list<NodeType*> myList;
typedef myList::iterator myIter;


myIter myFind(myList& mylist, char* dest)
{
    myIter it;
    for (it = mylist.begin(); it != mylist.end(); it++)
    {
        //if ((*it)->groupName == dest)
        if (strcmp((*it)->groupName, dest) == 0)
        {
            return it;
        }
    }
    return it;
}

int main()
{
    struct _finddata_t fileinfo;
    string in_path;
    string in_name;
    cin >> in_path;
    string curr = in_path + "\\*.txt";
    long handle;
    if ((handle = _findfirst(curr.c_str(), &fileinfo)) == -1L)
    {
        cout << "没有找到匹配文件!" << endl;
        return 0;
    }
    else
    {
        in_name = in_path + "\\" + fileinfo.name;
        GetLineAndPrint(in_name);
        while (!(_findnext(handle, &fileinfo)))
        {
            in_name = in_path + "\\" + fileinfo.name;
            GetLineAndPrint(in_name);
        }
        _findclose(handle);
    }



    myList classInfo;

    NodeType* pNode;
    //插入节点
    for (size_t i = 0; i < 5; i++)
    {
        //创建一个索引节点
        myIter it = myFind(classInfo, url[i].group);
        if (it != classInfo.end())    //已存在
        {
            //存储name
            (*it)->next->push_back(url[i].name);
        }
        else    //创建新的NodeType节点
        {
            pNode = new NodeType;
            pNode->groupName = url[i].group;
            pNode->next = new ListType;    //创建list

                                           //存储当前的name
            pNode->next->push_back(url[i].name);
            classInfo.push_back(pNode);
        }
    }

    //输出：
    for (myIter it = classInfo.begin(); it != classInfo.end(); it++)
    {
        cout << (*it)->groupName << ": ";
        for (ListType::iterator bg = (*it)->next->begin();
            bg != (*it)->next->end(); bg++)
        {
            cout << (*bg) << "\t";
        }
        cout << endl;
    }

    system("pause");
    return 0;
}