webextract.cpp

来自「从htm/html格式的网页文件中提取内容。将要提取内容的网页文件用鼠标拖入窗口」· C++ 代码 · 共 69 行

#include "StdAfx.h"
#include "stdio.h"
#include "Extract.h"
#include "time.h"

void funProcessDir(string strDir);

int main(int argc,char *argv[])
{
	char strFilename[100];
	Extract extract;
	cout << "***********************************************" << endl ;
	cout << "§  Function:                                §" << endl ;
	cout << "§  Extract contents from htm/html files.    §" << endl ;
	cout << "§  网页内容提取 Version1.0                  §" << endl ;
	cout << "***********************************************" << endl ;
	cout << "************************ ablenavy 2006-07-20***" << endl<<endl ;
	
	cout << "     请输入文件夹或文件名，按回车键。 " << endl ;
	cout << "     =========支持鼠标拖拽==========" << endl ;

	gets(strFilename);
	string str = strFilename;
	string strDest = "";
	int nPos;
	clock_t start, finish;
	start=clock();
	//strDest="E:\aa";
	if (!strDest.empty()) 
	{
		while (nPos != -1) {
			strDest = strDest.substr(0,nPos) + "\\" + strDest.substr(nPos) ;
			nPos = strDest.find("\\",nPos+2);
		}
		strDest += "\\" ;
	}
	
	nPos = str.find("\\");
	while (nPos != -1) {
		str = str.substr(0,nPos) + "\\" + str.substr(nPos) ;
		nPos = str.find("\\",nPos+2);
	}
	if (str.find("\"") != -1) 
	{
		str = str.substr(1,str.length()-2);
	}
	if (str.find(".") != -1) 
	{
		extract.funProcessFile(str);
	}
	else
	{
		str += "\\" ; 
		//extract.funProcessDirectory(str,"","htm");
		//extract.funProcessDirectory(str,"","html");
		extract.funProcessDirectory(str,strDest,"htm");
		extract.funProcessDirectory(str,strDest,"html");
	}

	finish=clock();
	float nTime=(float)(finish-start)/CLOCKS_PER_SEC;
	cout << endl << "OK ! It took " << nTime << " seconds." << endl;
	
	getchar();
	getchar();
	return 0;
}