这里两个函数实现GB2313与UTF8格式的互转,主要用于VC++在获取网页内容时解决乱码问题,因为VC++默认字符集是GB2312的,一般中文网站可能返回的是UTF-8编码,所以可以用U2G函数进行转换。
char* U2G(const char* utf8) { int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0); wchar_t* wstr = new wchar_t[len+1]; memset(wstr, 0, len+1); MultiByteToWideChar(CP_UTF8, 0, utf8, -1, wstr, len); len = WideCharToMultiByte(CP_ACP, 0, wstr, -1, NULL, 0, NULL, NULL); char* str = new char[len+1]; memset(str, 0, len+1); WideCharToMultiByte(CP_ACP, 0, wstr, -1, str, len, NULL, NULL); if(wstr) delete[] wstr; return str; } //GB2312到UTF-8的转换 char* G2U(const char* gb2312) { int len = MultiByteToWideChar(CP_ACP, 0, gb2312, -1, NULL, 0); wchar_t* wstr = new wchar_t[len+1]; memset(wstr, 0, len+1); MultiByteToWideChar(CP_ACP, 0, gb2312, -1, wstr, len); len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL); char* str = new char[len+1]; memset(str, 0, len+1); WideCharToMultiByte(CP_UTF8, 0, wstr, -1, str, len, NULL, NULL); if(wstr) delete[] wstr; return str; }
c++ gb2312 utf8 转换函数