WinSock C++编程获取网页

深碍√TFBOYSˉ_ 2022-05-19 09:08 206阅读 0赞

使用WinSock。

#include <string>
    #include <iostream>
    #include <fstream>
    #include "winsock2.h"
    #include <time.h>
    
    #pragma comment(lib, "ws2_32.lib") 
    
    using namespace std;
    
    #define DEFAULT_PAGE_BUF_SIZE 1048576
    
    void main()
    {
        WSADATA wsaData;
        int err;
        err = WSAStartup(MAKEWORD(2,2), &wsaData);
        if( err != 0 )
        {
            return;
        }
    
        // timer is start
    
        clock_t start, finish;
        double duration;
        start = clock();
    
        char host[] = "www.baidu.com";
        char *request = "GET / HTTP/1.0\r\nHost: www.baidu.com\r\nConnection: Close\r\n\r\n";
    
        struct hostent *hp;
        hp = gethostbyname(host);
        if(hp == NULL)
        { 
            cout << "gethostbyname() error in GetIpByHost: " << host << endl;
            return;
        }
        
        // 获取域名对应的IP
    
        struct in_addr inAddr;
        LPSTR lpAddr;
        lpAddr = hp->h_addr;
        memmove(&inAddr,lpAddr,4);
    
        int sock, ret = 0, optval = 1;
        struct sockaddr_in sa;
        sa.sin_family = AF_INET;        
        sa.sin_port = htons(80);
        sa.sin_addr.s_addr = inet_addr(inet_ntoa(inAddr));
        
        sock = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
        connect(sock, (SOCKADDR*)&sa, sizeof(sa));
        if(sock == -1)
        {
            return;
        }
        if(sock == -2)
        {
            return;
        }
    
        // send the "GET" data
    
        ret = send(sock, request, strlen(request), 0);
    
        // 网页内容长度。可以从http头部数据中获取 "Content-Length:"
    
        int m_nContentLength = DEFAULT_PAGE_BUF_SIZE;
        
        char *pageBuf;
        pageBuf = (char *)malloc(m_nContentLength);
        memset(pageBuf, 0, m_nContentLength);
    
        int bytesRead = 0;
        while(ret > 0)
        {
            ret = recv(sock, pageBuf + bytesRead, m_nContentLength - bytesRead, 0);
            
            if(ret > 0)
            {
                bytesRead += ret;
            }
        }
        pageBuf[bytesRead] = '\0';
    
        cout << bytesRead << endl;
    
        // write the html content to the file
    
        ofstream ofs;
        ofs.open("ofs.txt");
        ofs << pageBuf << endl;
    
        ofs.close();
        free(pageBuf);
        closesocket(sock);
        WSACleanup();
    
        // timer is finish
    
        finish = clock();
        duration = (double)(finish - start) / CLOCKS_PER_SEC;
        cout << "have cost " << duration << " seconds\n";
        
        return;
    }