📄 extracttitle.cpp

📁 根据HTML的HEAD项将本机的HTML建立索引以便于浏览
💻 CPP
📖 第 1 页 / 共 2 页
字号:
12 下一页

///********************************************************
//                               \\\|///
//                             \\  - -  //
//                              (  @ @  )
//┏━━━━━━━━━━━━━oOOo-(_)-oOOo━━━━━━━━━━━━┓
//┃☆☆☆☆☆☆   ≈≈≈大家好！我是【王晓钰】≈≈≈  ☆☆☆☆☆☆┃
//┃№№№№＄＄＄＄№№№№＄＄＄＄№№№№＄＄＄＄№№№№＄＄＄ ┃
//┃¤¤※※※※ ≈≈≈≈≈≈谢谢大家的厚爱≈≈≈≈≈≈※※※※¤¤┃
//┃★★★★★主页“笑语小园”:http://xiaoyuyeah.yeah.net★★★★★┃
//┃★★★★★主页“笑语小园”:http://xiaoyuyeah.126.com ★★★★★┃
//┃★★★★★☆☆电子邮件:   Garden.XiaoYu@263.net  ☆☆★★★★★┃
//┃★★★★★OICQ: 285126                               ★★★★★┃
//┃☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆☆ ┃
//┃                                   Oooo〖王晓钰〗2001年02月12日┃
//┗━━━━━━━━━━━━━━oooO---(  )━━━━━━━━━━━━┛
//                             (   )   ) /
//                              \ (   (_/
//                               \_)
///*******************************************************
/// ExtractTitle.cpp: implementation of the CExtractTitle class.
//
//////////////////////////////////////////////////////////////////////

#include "stdafx.h"
#include "ExtractTitle.h"
#ifdef _DEBUG
#undef THIS_FILE
static char THIS_FILE[]=__FILE__;
#define new DEBUG_NEW
#endif

//////////////////////////////////////////////////////////////////////
// Construction/Destruction
//////////////////////////////////////////////////////////////////////

CExtractTitle::CExtractTitle()
{	totalFileNumber=0;
	fileNum=0;
	saved=false;
}

CExtractTitle::~CExtractTitle()
{

}
//DEL CExtractTitle::CExtractTitle(CString sourceStr,CString srcInsert,LPCTSTR insertAfter,int after=1)
//DEL {	initSource();
//DEL }
//DEL CString CExtractTitle::test()
//DEL {	//return CString("sucessful for this class");
//DEL 	/*CString ss=memFile;
//DEL 	ss.MakeLower();
//DEL 	int ii=ss.Find("<body>");
//DEL 	return ss.Left(ii);
//DEL 	ExtractFile("test.html");
//DEL 	cout<<"\n\nlook here :title\nbegin|=>"<<fileInfo.title<<"<=|end\n";
//DEL 	cout<<"\n\nlook here :topic\nbegin|=>"<<fileInfo.topic<<"<=|end\n";
//DEL 	return 	fileInfo.title;
//DEL 	*/
//DEL 	ExtractFile("test.html");
//DEL 	resultInfo.insertLine(memFileStr);
//DEL 	myWriteFile("result.html");
//DEL 	return "";
//DEL }

int CExtractTitle::myReadFile(LPCTSTR file)
{	fileInfo.name=file;
	if(!f.GetStatus(fileInfo.name,status))
		return 1;	//file not exist;
	fileInfo.size=status.m_size;
	if(status.m_size<10)	return 3;
	if(!f.Open(fileInfo.name,CFile::modeRead))
		return 2;	//error in read;
	fileInfo.length=f.GetLength();
	maxNum=fileInfo.length>MAXNUM?MAXNUM:fileInfo.length;
	maxNum=f.Read(memFile,maxNum);
	f.Close();
	memFileStr=memFile;	
	memFileStrOrginal=memFile;
	memFileStr.MakeLower();
	index=0;
	return 0;
}


CString CExtractTitle::searchTitle()
{	int start,end,length;
	start=memFileStr.Find("<title>",index)+7;
	end=memFileStr.Find("</title>",index);
	if(start<0 || end<0)	return "";
	index=end;
	length=(end-start)>MAXLENGTH?
					MAXLENGTH:(end-start);	//找到了
	fileInfo.title=memFileStrOrginal.Mid(start,length);
	if(!IsOk(fileInfo.title))	fileInfo.title+="&nbsp;";
	return fileInfo.title;
}

//查找主题，程序的关键。
CString CExtractTitle::searchTopic()
{	int start,end,length,tmpStart;
	CString scriptStr;
	tmpStart=memFileStr.Find("<body",index);		//perfect <body
	if(tmpStart>1)	index=tmpStart;
	else	index=memFileStr.Find("<",index);		//以防文中没有<body...>
	index=memFileStr.Find(">",index)+1;		//perfect <body...>
	start=index;
	do{
search:
	tmpStart=start;
	end=memFileStr.Find("<",start);
	if(end>-1)
	{	
		start=memFileStr.Find(">",end);
		if(start>-1)	
		{			///identify the :<script>
			scriptStr=memFileStrOrginal.Mid(end,start);
			if(!scriptStr.Find("<script",0))//  .CompareNoCase("<script"))
			{	start=memFileStr.Find("</script>",start);
				start=memFileStr.Find('>',start);
				goto search;
			}
			length=end-tmpStart;//(end-tmpStart)>MAXLENGTH?MAXLENGTH:(end-tmpStart);
		}
		else //原文件有问题。'<'不匹配
			length=2*MAXLENGTH;
	}
	else	length=2*MAXLENGTH;
//	fileInfo.topic.Empty();
	fileInfo.topic=memFileStrOrginal.Mid(tmpStart+1,length-1);
	}while(!IsOk(fileInfo.topic));
	index=tmpStart;
	fileInfo.topic=DelSpace(fileInfo.topic);
	if(fileInfo.topic.GetLength()>MAXLENGTH)	
		fileInfo.topic=fileInfo.topic.Left(MAXLENGTH);
	if(fileInfo.topic.GetLength()==0)	fileInfo.topic+="&nbsp;";
	fileInfo.topic+=char(0x0d);
	fileInfo.topic+=char(0x0a);
	return fileInfo.topic;
}


int CExtractTitle::ExtractFile(CString file)
{	saved=false;
	Display(fileInfo.name);
	totalFileNumber++;
	int result=myReadFile(file);
	if(result)
	{	::MessageBox(NULL,"读取文件有错误","错误",MB_ICONERROR|MB_OK);
		return result;
	}
	searchTitle();
	searchTopic();
//这是一种输出的信息，以后可以改。
	//if(fileNum %10==1)	Seperate();
	CString out,insertStr;
	int theIndex;
	insertStr=resultInfo.GetInsertString();
	
	out.Format("%d",fileNum);
	theIndex=insertStr.Find("</td>");
	insertStr.Insert(theIndex,out);
	theIndex=insertStr.Find("</td>",theIndex+out.GetLength()+5);

	int nn=totalPathlength;
	CString dispStr=fileInfo.name.Mid(nn);
	nn=dispStr.GetLength();
	if(nn>25)	
	{	//dispStr=dispStr.Right(25);
		nn=dispStr.ReverseFind(char(0x5c));
		dispStr=dispStr.Mid(nn);
	}
	out.Format("<a href=\"%s\" target=\"_blank\">%s</a>",
		fileInfo.name,dispStr
		);
	insertStr.Insert(theIndex,out);

	theIndex=insertStr.Find("</td>",theIndex+out.GetLength()+5);
	insertStr.Insert(theIndex,fileInfo.title);


	theIndex=insertStr.Find("</td>",theIndex+fileInfo.title.GetLength()+5);
	insertStr.Insert(theIndex,fileInfo.topic);

	theIndex=insertStr.Find("</td>",theIndex+fileInfo.topic.GetLength()+5);
	out.Format("%ub",fileInfo.size);
	insertStr.Insert(theIndex,out);

	resultInfo.insertLine(insertStr);
/*×××为了让用户能够看清楚，不要这个提示。
	CString str;
	str.Format("已经提取了%d个文件",totalFileNumber);
	Display(str);
	*/
	return 0;
}	
/*
//这是一种输出的信息，以后可以改。
	CString out1("
	<tr> 
            <td width=\"25%%\"></td>
            <td width=\"35%%\"></td>
            <td width=\"35%%\"></td>
            <td width=\"5%%\"></td>
		</tr>");


	
	CString out;
	out.LoadString(IDS_TR);
	CString fileName="<a href=\"";
	fileName+=fileInfo.name;
	fileName+="\" target=\"_blank\">";
	//int theIndex;//=fileInfo.name.ReverseFind(TCHAR(0x5c));
	fileName+=fileInfo.name.Right(20);//theIndex));
	fileName+="</a>";
	//插入文件名
	theIndex=out.Find("</td>");
	out.Insert(theIndex,fileName);
	theIndex=out.Find("</td>");
	out.Insert(theIndex,fileInfo.title);	//title
	theIndex=out.Find("</td>");
	out.Insert(theIndex,fileInfo.topic);	//topic
	theIndex=out.Find("</td>");
	out.Insert(theIndex,(LPCTSTR)fileInfo.size);	//size
	resultInfo.insertLine(out);	//fileInfo.title);//+fileInfo.name);
	return 0;
}
	*/

int CExtractTitle::ExtractDir(CString dir)
{	if(dir.Right(2)=="..")
		return -1;
	CString dispDir;
	int fileFound=0;
	dispDir.Format("<tr border=\"0\" bgcolor=\"#FFCCFF\" borderColorDark=#ffffff borderColorLight=#6868d0 > \
				   <td colspan=\"5\" class=\"14p\" height=\"1\" bgcolor=\"#FFCCFF\"> \
              <div align=\"center\"><a href=\"%s\" target=\'_blank\'>当前目录： %s</a></div> \
            </td></tr> \
			",dir,dir);
	CFileFind finder;
	dir+="\\*.htm*";
    BOOL bWorking = finder.FindFile(dir);
	while (bWorking)
	{	bWorking = finder.FindNextFile();
		fileNum++;
		if(fileFound==0)		resultInfo.insertLine(dispDir);	
		fileFound++;
		fileInfo.name=finder.GetFilePath();
		//path=finder.GetRoot();
		ExtractFile(finder.GetFilePath());
	}
	return 0;
}

int CExtractTitle::_resultInfo::insertLine(CString oneFileTopic)
{	int insertBack= out.Insert(index,oneFileTopic);
	index+=oneFileTopic.GetLength();
	return insertBack;
}


int CExtractTitle::myWriteFile(LPCTSTR file)
{	//if(f.GetStatus(file,status))	return 1;	//already exist
	if(!f.Open(file,CFile::modeCreate | CFile::modeWrite))	return 2;	//error in write;
	f.Write(resultInfo.out,resultInfo.out.GetLength());
	f.Close();
	return 0;
}

//DEL void CExtractTitle::testGood()
//DEL {	initSource();
//DEL 	char dir[50];
//DEL 	GetCurrentDirectory(50,dir);
//DEL 	path=dir;
//DEL 	ExtractDir((LPCTSTR)dir);
12 下一页
💿 文件大小 193 K
👤 上传用户 choatehou4
📂 所属分类其他
🏷️ 相关标签

#HTML #HEAD #索引
⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -