基于visual c++之windows核心编程代码分析（55）使用GoogleUrl方便安全地解析URL

我们在进行google搜索的时候，google为了安全起见，经常对于URL通过谷歌的安全过滤，以过滤网络木马，如下图

 

 

下面我们来亲自实践，基于VC++来实现使用GoogleUrl方便安全地解析URL

#include "stdafx.h"
#include "googleurl\src\gurl.h"


void testURL(const char* lpszUrl)
{
	char szDomain[256];
	char szUrlPath[256];
	szDomain[0] = 0;
	szUrlPath[0] = 0;

	const char *szStart = NULL;
	const char *szPathStart = NULL;

	if (strnicmp(lpszUrl, "http://", 7) == 0)
	{
		//http开头
		szStart = lpszUrl + 7;
	} else if (strnicmp(lpszUrl, "https://", 8) == 0) {
		//https开头
		szStart = lpszUrl + 8;
	} else {
		szStart = lpszUrl;
	}

	szPathStart = strstr(szStart, "/");
	if (szPathStart)
	{
		strcpy(szUrlPath, szPathStart);
	}
	strncpy(szDomain, szStart, szPathStart - szStart);
	szDomain[szPathStart - szStart] = 0;

	printf("%s\nDomain: %s\nPath: %s\n", lpszUrl, szDomain, szUrlPath);
}

int _tmain(int argc, _TCHAR* argv[])
{
	std::cout << std::endl << "testURL" << std::endl;
	testURL("http://www.baidu.com/index.html");
	//testURL("http://www.ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ.com/index.html?ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ");
	
	//GoogleUrl
	std::cout << std::endl << "GoogleUrl" << std::endl;
	GURL gurl("http://user:[email protected]:8080/index.php?action=init");

	std::cout<< "URL: " << gurl << std::endl << std::endl;

	//得到域名\主机地址
	std::cout << "host() -> " << gurl.host() << std::endl;
	//得到端口号
	if (gurl.has_port())
		std::cout << "port() -> " << gurl.port() << std::endl;
	//得到query
	if (gurl.has_query())
		std::cout << "query() -> " << gurl.query() << std::endl;

	//得到用户名密码
	if (gurl.has_username())
		std::cout << "username() -> " << gurl.username() << std::endl;
	if (gurl.has_password())
		std::cout << "password() -> " << gurl.password() << std::endl;

	//得到文件名
	std::cout << "ExtractFileName() -> " << gurl.ExtractFileName() << std::endl;
	//这个也是端口号，与port()的区别就是就算没有指定端口号默认会返回HTTP 80端口
	std::cout << "EffectiveIntPort() -> " << gurl.EffectiveIntPort() << std::endl;

	//判断域名是否为IP地址
	std::cout << "HostIsIPAddress() -> " << gurl.HostIsIPAddress() << std::endl;

	std::cin.get();
	return 0;
}

 

原文链接： http://blog.csdn.net/yincheng01/article/details/7214454