htmltotxtdlg.cpp

HTML文件到txt文件转换器

// HtmlToTxtDlg.cpp : implementation file
//

#include "stdafx.h"
#include "HtmlToTxt.h"
#include "HtmlToTxtDlg.h"

#ifdef _DEBUG
#define new DEBUG_NEW
#undef THIS_FILE
static char THIS_FILE[] = __FILE__;
#endif

/////////////////////////////////////////////////////////////////////////////
// CHtmlToTxtDlg dialog

CHtmlToTxtDlg::CHtmlToTxtDlg(CWnd* pParent /*=NULL*/)
	: CDialog(CHtmlToTxtDlg::IDD, pParent)
{
	//{{AFX_DATA_INIT(CHtmlToTxtDlg)
	m_strTxt = _T("");
	m_strHtml = _T("");
	//}}AFX_DATA_INIT
	// Note that LoadIcon does not require a subsequent DestroyIcon in Win32
	m_hIcon = AfxGetApp()->LoadIcon(IDR_MAINFRAME);
}

void CHtmlToTxtDlg::DoDataExchange(CDataExchange* pDX)
{
	CDialog::DoDataExchange(pDX);
	//{{AFX_DATA_MAP(CHtmlToTxtDlg)
	DDX_Text(pDX, IDC_EDIT_TXT, m_strTxt);
	DDX_Text(pDX, IDC_EDIT1_HTML, m_strHtml);
	//}}AFX_DATA_MAP
}

BEGIN_MESSAGE_MAP(CHtmlToTxtDlg, CDialog)
	//{{AFX_MSG_MAP(CHtmlToTxtDlg)
	ON_WM_PAINT()
	ON_WM_QUERYDRAGICON()
	ON_BN_CLICKED(IDC_BUTTON_BROWSE, OnButtonBrowse)
	ON_BN_CLICKED(IDC_BUTTON_SAVE, OnButtonSave)
	//}}AFX_MSG_MAP
END_MESSAGE_MAP()

/////////////////////////////////////////////////////////////////////////////
// CHtmlToTxtDlg message handlers

BOOL CHtmlToTxtDlg::OnInitDialog()
{
	CDialog::OnInitDialog();

	SetIcon(m_hIcon, TRUE);			// Set big icon
	SetIcon(m_hIcon, FALSE);		// Set small icon
	
	// TODO: Add extra initialization here
	
	return TRUE;  // return TRUE  unless you set the focus to a control
}

// If you add a minimize button to your dialog, you will need the code below
//  to draw the icon.  For MFC applications using the document/view model,
//  this is automatically done for you by the framework.

void CHtmlToTxtDlg::OnPaint() 
{
	if (IsIconic())
	{
		CPaintDC dc(this); // device context for painting

		SendMessage(WM_ICONERASEBKGND, (WPARAM) dc.GetSafeHdc(), 0);

		// Center icon in client rectangle
		int cxIcon = GetSystemMetrics(SM_CXICON);
		int cyIcon = GetSystemMetrics(SM_CYICON);
		CRect rect;
		GetClientRect(&rect);
		int x = (rect.Width() - cxIcon + 1) / 2;
		int y = (rect.Height() - cyIcon + 1) / 2;

		// Draw the icon
		dc.DrawIcon(x, y, m_hIcon);
	}
	else
	{
		CDialog::OnPaint();
	}
}

// The system calls this to obtain the cursor to display while the user drags
//  the minimized window.
HCURSOR CHtmlToTxtDlg::OnQueryDragIcon()
{
	return (HCURSOR) m_hIcon;
}

void CHtmlToTxtDlg::OnButtonBrowse() 
{
	CFileDialog fileDlg(TRUE,"htm",NULL,OFN_HIDEREADONLY|OFN_OVERWRITEPROMPT,
		"HTML Files(*.html)|*.html|HTML Files(*.htm)|*.htm",this);
	CString strTemp;
	if(fileDlg.DoModal()==IDOK)
	{
		m_strHtml=fileDlg.GetPathName();
		strTemp=m_strHtml;
	}
	strTemp.Replace(fileDlg.GetFileName(),"result.txt");
	m_strTxt=strTemp;
	UpdateData(FALSE);
}

void CHtmlToTxtDlg::OnButtonSave() 
{
	CFileDialog fileDlg(FALSE,"html",NULL,OFN_HIDEREADONLY|OFN_OVERWRITEPROMPT,
		"TXT Files(*.txt)|*.txt",this);
	if(fileDlg.DoModal()==IDOK)
	{
		m_strTxt=fileDlg.GetPathName();
	}
	UpdateData(FALSE);	
}

void CHtmlToTxtDlg::OnOK() 
{
	UpdateData(TRUE);
	if(m_strHtml.IsEmpty())
	{
		AfxMessageBox("请选择一个源文件(.html,.htm)");
		return;
	}
	CFile scrFile,dstFile;
	if(!scrFile.Open(m_strHtml,CFile::modeRead))
	{
		AfxMessageBox("打开源文件失败！");
		return;
	}
	if(!dstFile.Open(m_strTxt,CFile::modeCreate|CFile::modeWrite))
	{
		AfxMessageBox("建立目标文件失败！");
		return;
	}
	char buf[1024],tbuf[1024];
	int len;
	BOOL bStartHtml=FALSE,bInTag=FALSE,bPreCr=FALSE,bPreLf=FALSE;
	int num=0;
	while(1)
	{
		len=scrFile.Read(buf,1024);
		for(int i=0;i<len;i++)
		{
			if(!bStartHtml)
			{
				if(strstr(buf,"<body"))
				{
					bStartHtml=TRUE;
				}
/*
				if(buf[i]=='<')
				{
					bStartHtml=TRUE;
					bInTag=TRUE;
					//continue;
				}
*/
			}
			else
			{
				if(buf[i]=='<')
				{
					bInTag=TRUE;
					//continue;
				}
				if(bInTag)
				{
					if(buf[i]=='>')
					{
						bInTag=FALSE;
						//continue;
					}
				}
				else
				{
					if((buf[i]!='\t')&&/*(buf[i]!='\r')&&*/(buf[i]!=' ')/*&&(buf[i]!='\n')*/)
					{
						if((buf[i]=='\r')||(buf[i]=='\n'))
						{
							if(!bPreCr)
							{
								bPreCr=TRUE;
								tbuf[num]=buf[i];
								num++;
							}
							else if(!bPreLf)
							{
								bPreLf=TRUE;
								tbuf[num]=buf[i];
								num++;
							}
						}
						else
						{
							bPreCr=FALSE;
							bPreLf=FALSE;
							tbuf[num]=buf[i];
							num++;
						}
					}
				}
			}
		}
		tbuf[num]='\0';
		int tLen=strlen(tbuf);
		dstFile.Write(tbuf,tLen);
		num=0;
		memset(tbuf,0,1024);
		if(len<1024)
			break;

	}
	scrFile.Close();
	dstFile.Close();
	AfxMessageBox("转换完毕");
	
	//CDialog::OnOK();
}