以编程方式阅读网页

Question

我想用C/C++编写一个程序,它将动态地读取一个网页并从中提取信息.举个例子想象一下,如果你想写一个应用程序来关注并记录一个ebay拍卖.抓住网页有简单的方法吗？提供此功能的库？是否有一种简单的方法来解析页面以获取特定数据？

Answer 1

看看cURL库:

 #include <stdio.h>
 #include <curl/curl.h>

 int main(void)
 {
   CURL *curl;
   CURLcode res;

   curl = curl_easy_init();
   if(curl) {
     curl_easy_setopt(curl, CURLOPT_URL, "curl.haxx.se");
     res = curl_easy_perform(curl);
      /* always cleanup */
    curl_easy_cleanup(curl);
   }
   return 0;
 }

顺便说一下,如果不严格要求C++.我鼓励你尝试使用C#或Java.它更容易,并有一个内置的方式.

Answer 2

Windows代码:

#include <winsock2.h>
#include <windows.h>
#include <iostream>
#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;
}