C++网页抓取

     如何抓取一个网页内容，大家可能对于php的操作很熟悉了吧，php的话很多方法，CURL、file_get_contents等方法，但是C++又是怎样做呢？效率咋样呢？其实，抓取的速度，受你PC机的带宽或是服务器的带宽影响很大.....

     贴代码：

#include<windows.h>
#include<Wininet.h>
#include<iostream>
#include<fstream>
#include<string>
#include<time.h>
#pragma comment(lib,"WinInet.lib")
using namespace std;

int main()
{
	clock_t start, finish;
	double use_time;
	start = clock();       //开始计时
	HINTERNET hINet, hHttpFile;               
	char szSizeBuffer[32];
	DWORD dwLengthSizeBuffer = sizeof(szSizeBuffer);
	hINet = InternetOpen("IE6.0", INTERNET_OPEN_TYPE_PRECONFIG, NULL, NULL, 0 );    //InternetOpen初始化WININET.DLL
	string url = "http://www.jyu.edu.cn";          //目标网页

	if ( !hINet )
	{
		cout << "InternetOpen fail" << endl;
		return 1;
	}

	hHttpFile = InternetOpenUrl(hINet, url.c_str(), NULL, 0, 0, 0);  //这个函数连接到一个网络服务器上并且最被从服务器上读取数据

	if(!hHttpFile)
	{
		cout << "error open url" << endl;
		return 1;
	}

	BOOL bQuery = HttpQueryInfo(hHttpFile,
	HTTP_QUERY_CONTENT_LENGTH,
	szSizeBuffer,
	&dwLengthSizeBuffer, NULL); //得到关于文件的信息

	if(bQuery ==false)
	{
		InternetCloseHandle(hINet); 
		cout << "error query info" << endl;
		return 3;
	}

	int FileSize=atol(szSizeBuffer);    //atol函数把字符串转换成长整型数
	string revData;
	revData.resize(FileSize);

	DWORD dwBytesRead;
	BOOL bRead = InternetReadFile(hHttpFile, &revData[0], FileSize, &dwBytesRead);     //web浏览器将在InternetReadFile上循环 ，不停地从Internet上读入数据块。

	if(!bRead)
	{
		cout << "error to read file" << endl;
		return 4;
	}

	ofstream   out_file("jyu.html");   
	out_file << revData;              //输出到文件
	InternetCloseHandle(hHttpFile);   //关闭句柄
	InternetCloseHandle(hINet);
	finish = clock();
	use_time = (double)(finish - start) / CLOCKS_PER_SEC;
	cout << "爬虫抓取地址为:" << url << endl;
	cout << "页面抓取成功!用时:" << use_time << " s" << endl;
	system("pause");
	return 0;
}

运行结果: