crobotinternet.cpp

beereader source code

	sErrMsg = "";
	DWORD dwHttpStatus;
	nResult = CROBOT_ERR_SUCCESS;
	CString sMsg;

	try 
	{
		pSession = NULL;
		pHttpFile = NULL;
		pLocalFile = NULL;
		sHeader = CreateStandardHeader();
		nRead = 0;
		pBuffer = new char[1024];
		sResult = "";
		sWorkingUrl = sURL;

		/* Trim URL and add http:// if it contains no 
		   protocol identifier */

		sWorkingUrl.TrimLeft();
		sWorkingUrl.TrimRight();
		if (sWorkingUrl.Find(":") == -1) 
		{
			if (sWorkingUrl.Left(1) == "/")
				sWorkingUrl = "http:" + sWorkingUrl;
			else
				sWorkingUrl = "http://" + sWorkingUrl;
		} // End if

		// Check for invalid parameters
		if (!(sURL.IsEmpty()) && !(sOutputFilespec.IsEmpty()))
		{
			// URL is not empty and output file spec is not empty
			/* Check the URL - must be valid and 
			   of the 'http:' service type */
			DWORD dwServiceType;
			CString sServer, sObject;
			unsigned short nPort;
			if (AfxParseURL(sWorkingUrl,
							dwServiceType,
							sServer,
							sObject,
							nPort)) 
			{
				if (dwServiceType == AFX_INET_SERVICE_HTTP)
				{
					pSession = new CInternetSession(
											m_sUserAgent,
											++m_nContext,
											INTERNET_OPEN_TYPE_PRECONFIG);

					pHttpFile = (CHttpFile*) 
						pSession->OpenURL(
									sWorkingUrl,
									1,
									INTERNET_FLAG_RELOAD
									    | INTERNET_FLAG_DONT_CACHE
										| INTERNET_FLAG_TRANSFER_BINARY
										| INTERNET_FLAG_EXISTING_CONNECT,
								    sHeader,
									-1L);
					if (pHttpFile) /* OpenURL worked */
					{
						// Check the http return code
						if (!pHttpFile->QueryInfoStatusCode(dwHttpStatus))
							dwHttpStatus = 200;

						if (dwHttpStatus >= 400)
						{
							switch(dwHttpStatus)
							{
							case 404:
								nResult = CROBOT_ERR_NOT_FOUND;
								break;
							case 403:
							case 407:
								nResult = CROBOT_ERR_NOT_AUTHORIZED;
								break;
							default:
								nResult = CROBOT_ERR_CONNECTION_FAILED;
								break;
							} // End switch
						} // End if dwHttpStatus
						else /* No error - read response data */
						{
							nResult = CROBOT_ERR_SUCCESS;
							// Open local file for output
							pLocalFile = new CFile;
							pLocalFile->Open(sOutputFilespec,
											 CFile::modeWrite 
											     | CFile::modeCreate);
							// Read the data
							do 
							{
								nRead = pHttpFile->Read(pBuffer, 1023);
								if (nRead != 0)
								{
									pBuffer[nRead] = 0;
									pLocalFile->Write(pBuffer, nRead);
									if (sResult == "") sResult = pBuffer;
								} // End if
							} while (nRead != 0);
						} // End else
						// Check for error embedded in return page
					} // End if pHttpFile
					else /* OpenURL failed */
					{
						nResult = CROBOT_ERR_CONNECTION_FAILED;
					} // End else
				} // End if
				else
					// Wrong service
					nResult = CROBOT_ERR_INVALID_URL;
			} // End if
			else
				// Invalid URL
				nResult = CROBOT_ERR_INVALID_URL;
		} // End if
		else
			// Empty URL or empty filespec
			nResult = CROBOT_ERR_INVALID_PARAMETER;
	} // End try

	catch(CFileException* e) 
	{
		int nErr = e->m_cause;
		e->Delete();
		delete pLocalFile;
		pLocalFile = NULL;
		// File exception occurred
		nResult = CROBOT_ERR_FILE + nErr;
	} // End catch

	catch (CInternetException* e)
	{
		e->Delete();
		
		// Internet exception occurred
		nResult = CROBOT_ERR_CONNECTION_FAILED;
	} // End catch

	catch (...) 
	{
		// Exception occurred
		nResult = CROBOT_ERR_CONNECTION_FAILED;
	} // End catch

// Clean up and exit function

	if (pBuffer != NULL) 
	{
		delete pBuffer;
		pBuffer = NULL;
	} // End if

	if (pHttpFile != NULL) 
	{
		pHttpFile->Close();
		delete pHttpFile;
	} // End if

	if (pLocalFile != NULL) 
	{
		pLocalFile->Close();
		delete pLocalFile;
	} // End if

	if (pSession != NULL) 
	{
		pSession->Close();
		delete pSession;
	} // End if

	sErrMsg = ErrorMessage(nResult);
	if (nResult == CROBOT_ERR_SUCCESS)
		return true;
	else
		return false;
}


// --------------------------------------------------------------
// **************** public
// *              *
// *  httpHeader  *
// *              *
// ****************
// Function: Retrieves a server header for a URL and returns it
//           in CString form.
//			 See also: Similar function httpHeaderFields.
//
// Inputs:	sURL              - The target URL
//								 (example: "www.mysite.com")
//
// Outputs:	<function_result> - True if header was successfully 
//                               retrieved, false otherwise.
//			sResponse         - The header returned by the server
//			nResult           - completion code; 0 = success,
//								 n = error (defined in CRobot.h)
//			sErrMsg           - the error message, if nResult != 0

BOOL CRobotInternet::httpHeader(const CString& sUrl,
								CString& sResponse,
								int& nResult,
								CString& sErrMsg) 
{
	CInternetSession* pSession;
	CHttpConnection* pConnection;
	CHttpFile* pHttpFile;
	CString sHeader;
	int nRead;
	LPSTR pBuffer;
	CString sResult;
	CString sWorkingUrl;
	CString sMsg;
	sErrMsg = "";
	nResult = CROBOT_ERR_CONNECTION_FAILED;

	try 
	{
		pSession = NULL;
		pConnection = NULL;
		pHttpFile = NULL;
		pHttpFile = NULL;
		sHeader = CreateStandardHeader();
		nRead = 0;
		pBuffer = new char[1024];
		sResult = "";
		sWorkingUrl = sUrl;

		/* Trim URL and add http:// if it contains no 
		   protocol identifier */
		
		sWorkingUrl.TrimLeft();
		sWorkingUrl.TrimRight();
		if (sWorkingUrl.Find(":") == -1) 
		{
			if (sWorkingUrl.Left(1) == "/")
				sWorkingUrl = "http:" + sWorkingUrl;
			else
				sWorkingUrl = "http://" + sWorkingUrl;
		} // End if

		// Check for invalid parameters
		if (!sUrl.IsEmpty()) 
		{
			// URL is not empty
			/* Check the URL - must be valid and of the 'http:'
			   service type */
			DWORD dwServiceType;
			CString sServer, sObject;
			unsigned short nPort;
			if (AfxParseURL(sWorkingUrl,
							dwServiceType,
							sServer,
							sObject,
							nPort))
			{
				//URL is valid. Now check service type.
				if (dwServiceType == AFX_INET_SERVICE_HTTP) 
				{
					//Service type is valid. Make connection.
					pSession = new CInternetSession(
										m_sUserAgent,
										1,
										INTERNET_OPEN_TYPE_PRECONFIG);
					pConnection = pSession->GetHttpConnection(sServer,
															  nPort,
															  NULL,
															  NULL);
					pHttpFile = pConnection->OpenRequest(
									CHttpConnection::HTTP_VERB_HEAD,
									sObject,
									NULL,
									1,
									NULL,
									NULL,
									INTERNET_FLAG_EXISTING_CONNECT
										| INTERNET_FLAG_RELOAD
										| INTERNET_FLAG_DONT_CACHE);
					if (pHttpFile->SendRequest()) /* SendRequest worked */
					{
						DWORD dwHttpStatus;
						// Check the http return code
						if(!pHttpFile->QueryInfoStatusCode(dwHttpStatus))
							dwHttpStatus = 400;

						if (dwHttpStatus >= 400)
						{
							switch(dwHttpStatus)
							{
							case 404:
								nResult = CROBOT_ERR_NOT_FOUND;
								break;
							case 403:
							case 407:
								nResult = CROBOT_ERR_NOT_AUTHORIZED;
								break;
							default:
								nResult = CROBOT_ERR_CONNECTION_FAILED;
								break;
							} // End switch
							unsigned long nFlag = 1; // HTTP_QUERY_CUSTOM;
							unsigned long nChars = 1023;
							DWORD nFlag2 = HTTP_QUERY_RAW_HEADERS_CRLF;
							pHttpFile->QueryInfo(nFlag2, sResult, NULL);
							sResponse = sResult;
						} // End if dwHttpStatus
						else /* No error - read response data */
						{
							nResult = CROBOT_ERR_SUCCESS;
							// Read the data
							do 
							{
								nRead = pHttpFile->Read(pBuffer, 1023);
								if (nRead != 0)
								{
									pBuffer[nRead] = 0;
									sResult += pBuffer;
								} // End if
							} while (nRead != 0);
							sResponse = sResult;
						} // End else
					} // End if pHttpFile
					else /* SendRequest failed */
						nResult = CROBOT_ERR_CONNECTION_FAILED;
					
				} // End if
				else
					// Wrong service
					nResult = CROBOT_ERR_INVALID_URL;
			} // End if
			else
				// Invalid URL
				nResult = CROBOT_ERR_INVALID_URL;
		} // End if
		else
			// Empty URL
			nResult =  CROBOT_ERR_INVALID_PARAMETER;
	} // End try

	catch (CInternetException* e) 
	{
		e->Delete();
		sResponse = sResult;

		// Internet exception occurred
		nResult =  CROBOT_ERR_CONNECTION_FAILED;
	} // End catch
	catch (...) 
	{
		sResponse = sResult;
		
		// Exception occurred
		nResult = CROBOT_ERR_CONNECTION_FAILED;
	} // End catch

// Clean up and exit function

	if (pBuffer != NULL) 
	{
		delete pBuffer;
		pBuffer = NULL;
	} // End if

	if (pHttpFile != NULL) 
	{
		pHttpFile->Close();
		delete pHttpFile; 
	} // End if

	if (pConnection != NULL) 
	{
		pConnection->Close();
		delete pConnection; 
	} // End if

	if (pSession != NULL) 
	{
		pSession->Close();
		delete pSession; 
	} // End if

	sErrMsg = ErrorMessage(nResult);
	if (nResult == CROBOT_ERR_SUCCESS)
		return true;
	else
		return false;
}


// --------------------------------------------------------------
// ********************** public
// *                    *
// *  httpHeaderFields  *
// *                    *
// **********************
// Function: Retrieves a server header for a URL and returns it in
//           CString form. Like httpHeader, but also parses header
//           into individual field names and values.
//
// Inputs:   sURL              - The target URL
//								 (example: "www.mysite.com")
//
// Outputs:	 <function_result> - True if header was successfully 
//								 retrieved, false otherwise
//			 sResponse         - The header returned by the server
//			 nResult           - Completion code. 0 = success,
//								 n = error (defined in CRobot.h)
//			 sErrMsg           - The error message, if nResult != 0
//			 m_sHeader		   - Copy of the header string
//			 m_nHeaderFields   - Set to number of header fields
//			 m_sHeadName[]     - Contains individual header field names
//			 m_sHeadValue[]    - Contains individual header field values

BOOL CRobotInternet::httpHeaderFields(const CString& sUrl,
									  CString& sResponse,
									  int& nResult,
									  CString& sErrMsg) 
{
	CInternetSession* pSession;
	CHttpConnection* pConnection;
	CHttpFile* pHttpFile;
	CString sHeader;
	int nRead;
	LPSTR pBuffer;
	CString sResult;
	CString sWorkingUrl;
	CString sMsg;
	CString sHTML, sTemp;
	int nPos;
	sErrMsg = "";
	nResult = CROBOT_ERR_SUCCESS;
	m_nHeaderFields = 0;

	try 
	{
		pSession = NULL;
		pConnection = NULL;
		pHttpFile = NULL;
		sHeader = CreateStandardHeader();
		nRead = 0;
		pBuffer = new char[1024];
		sResult = "";
		sWorkingUrl = sUrl;

		/* Trim URL and add http:// if it contains no 
		   protocol identifier */
		
		sWorkingUrl.TrimLeft();
		sWorkingUrl.TrimRight();
		if (sWorkingUrl.Find(":") == -1) 
		{
			if (sWorkingUrl.Left(1) == "/")
				sWorkingUrl = "http:" + sWorkingUrl;
			else
				sWorkingUrl = "http://" + sWorkingUrl;
		} // End if

		// Check for invalid parameters
		if (!sUrl.IsEmpty()) 
		{
			// URL is not empty
			/* Check the URL - must be valid and of the 'http:'
			   service type */
			DWORD dwServiceType;
			CString sServer, sObject;
			unsigned short nPort;
			if (AfxParseURL(sWorkingUrl,
							dwServiceType,
							sServer,
							sObject,
							nPort)) 
			{
				// URL is valid. Now check service type.
				if (dwServiceType == AFX_INET_SERVICE_HTTP) 
				{
					//Service type is valid. Make connection.
					pSession = new CInternetSession(
										m_sUserAgent,
										1,
										INTERNET_OPEN_TYPE_PRECONFIG);
					pConnection = pSession->GetHttpConnection(sServer,
															  nPort,
															  NULL,
															  NULL);

					pHttpFile = pConnection->OpenRequest(
									CHttpConnection::HTTP_VERB_HEAD,
									sObject,
									NULL,
									1,
									NULL,
									NULL,
									INTERNET_FLAG_EXISTING_CONNECT
										| INTERNET_FLAG_RELOAD
										| INTERNET_FLAG_DONT_CACHE);
					pHttpFile->SendRequest();
					
					unsigned long nFlag = 1;	// HTTP_QUERY_CUSTOM;
					unsigned long nChars = 1023;
					DWORD nFlag2 = HTTP_QUERY_RAW_HEADERS_CRLF;
					pHttpFile->QueryInfo(nFlag2, sResult, NULL);
					sResponse = sResult;
					nResult =  CROBOT_ERR_SUCCESS;
				} // End if
				else
					// Wrong service
					nResult = CROBOT_ERR_INVALID_URL;
			} // End if
			else
				// Invalid URL
				nResult = CROBOT_ERR_INVALID_URL;
		} // End if
		else
			// Empty URL
			nResult =  CROBOT_ERR_INVALID_PARAMETER;
	} // End try

	catch (CInternetException* e) 
	{
		e->Delete();
		sResponse = sResult;
		
		// Internet exception occurred
		nResult =  CROBOT_ERR_CONNECTION_FAILED;
	} // End catch
	catch (...) 
	{
		sResponse = sResult;
		
		// Exception occurred
		nResult = CROBOT_ERR_CONNECTION_FAILED;
	} // End catch

// Clean up and exit function

	if (pBuffer != NULL) 
	{
		delete pBuffer;
		pBuffer = NULL;
	} // End if

	if (pHttpFile != NULL)
	{
		pHttpFile->Close();
		delete pHttpFile; 
	} // End if

	if (pConnection != NULL)
	{
		pConnection->Close();
		delete pConnection; 
	} // End if

	if (pSession != NULL)
	{
		pSession->Close();
		delete pSession; 
	} // End if

	sErrMsg = ErrorMessage(nResult);
	if (nResult == CROBOT_ERR_SUCCESS)
	{
		// Parse header into individual fields
		m_sHeader = sResponse;
		m_nHeaderFields = 0;
		sHTML = sResponse;
		if (sHTML.Right(1) != "\n")
			sHTML += "\n";
		nPos = sHTML.Find("\n");
		while (nPos != -1)
		{
			sTemp = sHTML.Left(nPos);
			sHTML = sHTML.Mid(nPos + 1);
			nPos = sTemp.Find(":");
			if (nPos != -1)
			{
				m_sHeadName[m_nHeaderFields] = sTemp.Left(nPos);
				m_sHeadValue[m_nHeaderFields] = sTemp.Mid(nPos+1);
				m_sHeadValue[m_nHeaderFields].TrimLeft();
				m_sHeadValue[m_nHeaderFields].TrimRight();
				m_nHeaderFields++;
			} // End if
			nPos = sHTML.Find("\n");
		} // End while
		return true;
	} // End if
	else
		return false;
}


// --------------------------------------------------------------
// ************************ public
// *                      *
// *  httpGetHeaderField  *