Programmatically reading a web page

Question

I want to write a program in C/C++ that will dynamically read a web page and extract information from it. As an example imagine if you wanted to write an application to foll

Answer 1

Windows code:

#include 
#include 
#include 
#pragma comment(lib,"ws2_32.lib")
using namespace std;
int main (){
    WSADATA wsaData;
    if (WSAStartup(MAKEWORD(2,2), &wsaData) != 0) {
        cout << "WSAStartup failed.\n";
        system("pause");
        return 1;
    }
    SOCKET Socket=socket(AF_INET,SOCK_STREAM,IPPROTO_TCP);
    struct hostent *host;
    host = gethostbyname("www.google.com");
    SOCKADDR_IN SockAddr;
    SockAddr.sin_port=htons(80);
    SockAddr.sin_family=AF_INET;
    SockAddr.sin_addr.s_addr = *((unsigned long*)host->h_addr);
    cout << "Connecting...\n";
    if(connect(Socket,(SOCKADDR*)(&SockAddr),sizeof(SockAddr)) != 0){
        cout << "Could not connect";
        system("pause");
        return 1;
    }
    cout << "Connected.\n";
    send(Socket,"GET / HTTP/1.1\r\nHost: www.google.com\r\nConnection: close\r\n\r\n", strlen("GET / HTTP/1.1\r\nHost: www.google.com\r\nConnection: close\r\n\r\n"),0);
    char buffer[10000];
    int nDataLength;
    while ((nDataLength = recv(Socket,buffer,10000,0)) > 0){        
        int i = 0;
        while (buffer[i] >= 32 || buffer[i] == '\n' || buffer[i] == '\r') {
            cout << buffer[i];
            i += 1;
        }
    }
    closesocket(Socket);
        WSACleanup();
    system("pause");
    return 0;
}