document.cpp

网络通信方面的代码书非常经典欢迎大家下载并学习

		else
		{
			// Everything was normal so just fixup the links
			pThis->m_pProgress->SetAborted(FALSE);
			pThis->FixupLinks();
		}
	}

	//  关闭日志文件
	pThis->m_fileLog.Close();

	// Are we doing the TOC??
	if(pThis->m_Options.bContents)
	{
		// 写入文件的尾部
		CString strText;
		strText = "</UL>\r\n</BODY>\r\n</HTML>\r\n";
		pThis->m_fileContents.Write(strText,strText.GetLength());
		pThis->m_fileContents.Close();
	}

	// 输出信息表示已经完成
	pThis->m_pProgress->SetActionTitle("********* 处理完毕 *********");
	pView->SetSnagging(FALSE);

	// 释放内存
	pThis->ClearCacheMaps();

	// Make sure the "stopping, please wait" message isn't displayed
	//pView->EndWait();

	// 如果是自动模式，关闭住窗口
	if(pThis->m_bAutoMode)
		AfxGetMainWnd()->PostMessage(WM_CLOSE);

	// 关闭WinInet会话
	try
	{
		pThis->m_Inet.CloseSession();
	}
	catch(...)
	{
	}

	pThis->m_nLevel = 0;

	return(0);
}

//释放资源，即所有文件入口以及文件下载列表
void CSnaggerDoc::ClearCacheMaps()
{
	MAP_FILES *pMapEntry;
	CString strPage;
	POSITION pos;
	int i;

	// 删除页面列表
	pos = m_arrPagesDone.GetStartPosition();
	for(i = 0; i < m_arrPagesDone.GetCount(); i++)
	{
		m_arrPagesDone.GetNextAssoc(pos,strPage,(CObject *&) pMapEntry);
		delete pMapEntry;
	}
	m_arrPagesDone.RemoveAll();

	// 删除多媒体页面列表
	pos = m_arrMediaDone.GetStartPosition();
	for(i = 0; i < m_arrMediaDone.GetCount(); i++)
	{
		m_arrMediaDone.GetNextAssoc(pos,strPage,(CObject *&) pMapEntry);
		delete pMapEntry;
	}
	m_arrMediaDone.RemoveAll();
}

// 增加一个进入下载页面文件列表的入口
void CSnaggerDoc::SetPageCacheEntry(LPCTSTR lpszPage, LPCTSTR lpszFileName, int nLevel)
{
	CString strTempPage = lpszPage;
	MAP_FILES *pMapEntry = new MAP_FILES();

	// 将网页名称以小写保存
	pMapEntry->strFileName = lpszFileName;
	pMapEntry->nMaxLevel = nLevel;
	strTempPage.MakeLower();
	strTempPage = strTempPage.SpanExcluding("#");

	// 让所有页面有一个相对路径
	CString strExt = CInet::SplitFileName(strTempPage,CInet::EXT);
	if(strExt.IsEmpty() && strTempPage.Right(1) != "/")
		strTempPage += "/";

	// Assimilate it into the collective
	m_arrPagesDone.SetAt(strTempPage,(CObject *&) pMapEntry);
	TRACE("Pages Done: "+strTempPage+"\n");

	// 设定默认名称
	if(pMapEntry->strFileName == "index.htm" && strTempPage.Find("index.htm") == -1)
	{
		// 常用的默认页文件名
		char *aszDefPages[4] = { "index.htm", "index.html", "default.htm", 
										"default.html"};

		MAP_FILES *pTempMapEntry;

		CString strServer, strObject, strUser, strPassword;
		INTERNET_PORT nPort;
		DWORD dwServiceType;
		AfxParseURLEx(strTempPage,dwServiceType,strServer,strObject,nPort,
									strUser,strPassword,
									ICU_NO_ENCODE);

		// 加入默认问卷爱你们
		if(!strServer.IsEmpty())
		{
			strServer = "http://"+strServer+"/";

			for(int i = 0; i < 4; i++)
			{
				pTempMapEntry = new MAP_FILES();
				pTempMapEntry->strFileName = pMapEntry->strFileName;
				pTempMapEntry->nMaxLevel = pMapEntry->nMaxLevel;
				m_arrPagesDone.SetAt(strServer+aszDefPages[i],(CObject *&) pTempMapEntry);
				TRACE("Pages Done: "+CString(aszDefPages[i])+"\n");
			}
		}
	}	
}

// 增家一个新的文件列表的入口
void CSnaggerDoc::SetMediaCacheEntry(LPCTSTR lpszMedia, LPCTSTR lpszFileName)
{
	CString strTempMedia = lpszMedia;
	MAP_FILES *pMapEntry = new MAP_FILES();

	// 文件名保存成小写
	pMapEntry->strFileName = lpszFileName;
	pMapEntry->nMaxLevel = -1;
	strTempMedia.MakeLower();
	strTempMedia = strTempMedia.SpanExcluding("#");

	// Assimilate it into the collective
	m_arrMediaDone.SetAt(strTempMedia,(CObject *&) pMapEntry);
}

//开始下载网站内容
void CSnaggerDoc::RecursiveDownload(LPCTSTR lpszURL)
{
	// 初始化参数
	m_nGottenPageCount = 0;
	m_nGottenFileCount = 0;
	m_nQueuedPageCount = 0;
	m_nTotalBytes = 0;
	m_strStartPage = lpszURL;
	ClearCacheMaps();

	// 初始化参数显示窗口
	POSITION pos = GetFirstViewPosition();
	CSnaggerView* pView = (CSnaggerView *) GetNextView(pos);
	m_pProgress = pView->GetProgress();

	m_pProgress->SetAborted(FALSE);
	UpdateStatus();

	// 启动下载线程
	CWinThread *pThread = AfxBeginThread(DownloadThread,this);
}

// Fixs up each of the downloaded pages to allow local browsing.  It
// basically goes through the downloaded page list and opens each 
// file specified then parses the page and fixes up each of the 
// links found.
//
void CSnaggerDoc::FixupLinks()
{
	BYTE *pbyBuffer = m_byBuffer;
	int nLen;
	CFile fileIn, fileOut;
	CFileException ex;
	MAP_FILES* pMapEntry;
	int nIndex;
	int nBytesWritten;
	int nSectionLength;
	int nOffset;
	CString strFixupFileName;
	CString strPage;
	CString strFileName;
	CString strTempName = m_strDirectory+"$ssnag$.htm";
	BOOL bFixup;
	int nFiles = m_arrPagesDone.GetCount();
	BOOL bIndexDone = FALSE;

	//更新参数显示窗口指示还未处理的文件数量
	m_pProgress->SetQueuedFiles(nFiles);

	// Iterate through the downloaded page list
	//获得下载页列表
	POSITION pos = m_arrPagesDone.GetStartPosition();
	for(int i = 0; i < m_arrPagesDone.GetCount() && !m_pProgress->IsAborted(); i++)
	{
		m_arrPagesDone.GetNextAssoc(pos,strPage,(CObject *&) pMapEntry);

		if(pMapEntry->strFileName == "index.htm" || 
						pMapEntry->strFileName == "index.html")
		{
			if(bIndexDone)
			{
				// 更新参数显示窗口
				m_pProgress->SetQueuedFiles(--nFiles);
				continue;
			}	
			else bIndexDone = TRUE;
		}

		//显示参数
		strFileName = m_strDirectory+pMapEntry->strFileName;
		m_pProgress->SetActionTitle("Fixing up links in file: "+pMapEntry->strFileName);

		// 打开本地文件
		TRACE("Fixing up: "+strFileName+"\n");
		if(fileIn.Open(strFileName.SpanExcluding("#"),CFile::modeRead,&ex))
		{
			pbyBuffer = m_byBuffer;

			// 把文件读入内存
			nLen = fileIn.Read(pbyBuffer,MAX_INET_BUFFER);
			fileIn.Close();

			// Parse it (tell the parser to look for only links, i.e. fixup mode)
			CSnaggerHtmlParser Parser;
			Parser.SetFixupMode(TRUE);
			Parser.ResetArrays();
			Parser.SetGetMedia(m_Options.bMultimedia);
			Parser.SetPageURL(strPage);
			Parser.ParseText((char *)pbyBuffer,nLen);

			CString strServer, strObject, strUser, strPassword;
			INTERNET_PORT nPort;
			DWORD dwServiceType;
			AfxParseURLEx(strPage,dwServiceType,strServer,strObject,nPort,
									strUser,strPassword,
									ICU_NO_ENCODE);
			CString strOrigHost = "http://"+strServer+"/";

			// 打开个临时文件
			if(fileOut.Open(strTempName,CFile::modeCreate|CFile::modeWrite,&ex))
			{
				CString strURL;

				nIndex = 0;
				nBytesWritten = 0;
				nOffset = 0;

				// 写入文件并整理(如果有必要）
				for(int j = 0; j < Parser.GetFixups().arrURL.GetSize(); j++)
				{
					strURL = Parser.GetFixups().arrURL.GetAt(j);

					// 是否整理完文本文件
					if(Parser.GetFixups().arrTextPage.GetAt(j))
					{
						// 是否要下载这个文件
						if(!ShouldGetPage(strURL,pMapEntry))
						{
							// 获得本地文件
							strFixupFileName = pMapEntry->strFileName;
							bFixup = TRUE;
						}
						else
						{							
							AfxParseURLEx(strURL,dwServiceType,strServer,
									strObject,nPort,strUser,strPassword,
									ICU_NO_ENCODE);

							if(!strServer.IsEmpty())
							{
								strFixupFileName = strURL;
								bFixup = TRUE;
							}
							else bFixup = FALSE;
						}
					}
					else // 多媒体文件整理
					{
						// 是否下载多媒体文件
						if(!ShouldGetMedia(strURL,pMapEntry))
						{
							// 获取文件名
							strFixupFileName = pMapEntry->strFileName;
							bFixup = TRUE;
						}
						else bFixup = FALSE;
					}

					// 写入数据
					nSectionLength = Parser.GetFixups().arrIndex.GetAt(j)-nIndex-nOffset;

					try
					{
						fileOut.Write(pbyBuffer,nSectionLength);
					}
					catch(...)
					{
					}

					nBytesWritten += nSectionLength;
					pbyBuffer += nSectionLength;
					nOffset = 0;

					// 是否获得整理的入口
					if(bFixup)
					{
						// 写入文件
						try
						{
							fileOut.Write(" \"",2);
							fileOut.Write(strFixupFileName,strFixupFileName.GetLength());
						}
						catch(...)
						{
						}

						// 找到原来文件的开始除
						while(*pbyBuffer == ' ') 
						{
							pbyBuffer++;
							nBytesWritten++;
							nOffset++;
						}

						// Is the filename in quotes?
						if(*pbyBuffer == '"') 
						{
							// 找到最后
							do
							{
								pbyBuffer++;
								nBytesWritten++;
								nOffset++;
							}
							while(*pbyBuffer != '"');

							pbyBuffer++;
							nBytesWritten++;
							nOffset++;
						}
						else
						{
							// Not in quotes, so just look for the first
							// trailing blank
							do
							{
								pbyBuffer++;
								nBytesWritten++;
								nOffset++;
							}
							while(*pbyBuffer != ' ');
						}

						// Write a trailing quote and blank, just to be safe
						fileOut.Write("\" ",2);
					}

					// 保存开始整理的位置
					nIndex = Parser.GetFixups().arrIndex.GetAt(j);
				}

				// 完成整理，然后写入剩余的数据
				try
				{
					if(nLen-nBytesWritten > 0)
						fileOut.Write(pbyBuffer,nLen-nBytesWritten);
				}
				catch(...)
				{
				}

				fileOut.Close();
			}
		}

		// 用整理过的文件替代原始文件
		remove(strFileName.SpanExcluding("#"));
		rename(strTempName,strFileName.SpanExcluding("#"));

		// 更新参数显示串口
		m_pProgress->SetQueuedFiles(--nFiles);
	}

	// 删除临时文件，因为有可能中间用户要硬性停止
	remove(strTempName);
}

/////////////////////////////////////////////////////////////////////////////
// CSnaggerDoc diagnostics

#ifdef _DEBUG

// Check validity of object
void CSnaggerDoc::AssertValid() const
{
	CDocument::AssertValid();
}

// Dump the object
void CSnaggerDoc::Dump(CDumpContext& dc) const
{
	CDocument::Dump(dc);
}
#endif //_DEBUG