parselink.cpp

此源码功能是捕获网页中的链接并进行分析

/***************************************************************************
                          ParseLink.cpp  -  description
                             -------------------
    begin                : April 3, 2005
    ParseLink: Parse linkss from raw data.
    usage: ParseLink SrcFile
 ***************************************************************************/

#include "WebDataFile.h"
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <dirent.h>
#include <iostream>
#include <string>
#include <vector>
#include <cstdlib>
#include <time.h>

using namespace std;

int main(int argc, char* argv[])
{
	if( argc != 2 ){
		cout << "ExtractUrl: Extract Urls from raw data." << endl;
		cout << "usage:\t ExtractUrl RawDataFile" << endl;

		return -1;
	}

	//InitDataBuffer
	CWebDataFile iWebDataFile;        
	if(! iWebDataFile.InitDataBuffer()){
                std::cerr << "Insuficient memory.\n";
		return -2;
        }       
	
	//OpenFile
	char* sFileName = argv[1];
	if(! iWebDataFile.OpenFile(sFileName)){
		cout << "Fail to open file \"" << sFileName << "\"" << endl;
                        return -3;
	}
	//cout << "Open file " << sFileName << "...\n";

	while(true){
		// Get a page object to process
		if(! iWebDataFile.GetAWebPage((string)argv[1])){
			cout << "Error: GetAWebPage() returned a false!" << endl;
			break;
		}

	}
	iWebDataFile.CloseFile();
}