C++获取浏览器浏览历史（兼容谷歌、IE、火狐）

其他 2018-05-12 22:44:00 阅读次数: 0

我参考:http://blog.csdn.net/anda0109/article/details/41385241 贴写但是发现很多问题，我就在这个类的基础上重新写的代码，来完成获取浏览器记录，代码如下：

#pragma once

enum HistorySource
{
	HistorySource_IE,
	HistorySource_Chrome,
	HistorySource_FireFox,
};

struct BrowsData
{
public:
	// 网址
	CString strURL;

	// last_visit_time
	CString strTime;

	// 对应网址访问次数
	unsigned int nCount;

	// 重载<操作符
	bool operator < (const BrowsData &m)const
	{
		return nCount > m.nCount;
	}

	HistorySource source;
};

class BrowseHistory
{
public:
	BrowseHistory();
	~BrowseHistory();


	// 获取浏览器历史记录
	void ReadHistroy(void);
	void GetHistory(std::map<HistorySource, std::vector<BrowsData>>& vecHistory);

private:
	void readIEHistory();
	void readChromeHistory();
	void readFireFoxHistory();
	void getChromeVisitUrlTime(UINT64 milliSeconds, CString& strTime);
	void getFirefoxVisitUrlTime(UINT64 milliSeconds, CString& strTime);
	
	bool isRunning(CString exe);
	void convertUtf8ToGBK(CStringA &strUtf8);

	void urlFiltrateIE(LPWSTR lpszSourceUrlName, FILETIME visitTime);

	// Chrome网址过滤，如只取网址com前边的
	void urlFiltrateChrome(CString strUrlName, UINT64 visitTime, int iCount);

	// Firefox网址过滤，如只去网址com前边的
	void urlFiltrateFirefox(CString strUrlName, UINT64 visitTime, int iCount);

private:
	std::map<HistorySource, std::vector<BrowsData>> m_BrowsHistroyMap;//我把不同浏览器记录放到不同的链表里去
	bool m_bStatus = false;
	int m_timeZone = 0;
};


#include "stdafx.h"
#include "BrowseHistory.h"
#include <wininet.h>
#include <io.h>
#include <tlhelp32.h>
#include "CppSQLite3.h"
#include "PcTime.h"

BrowseHistory::BrowseHistory()
{
	TIME_ZONE_INFORMATION timeZone = { 0 };
	DWORD dwRet = GetTimeZoneInformation(&timeZone);
	if (dwRet == ERROR_SUCCESS)
	{
		m_timeZone = timeZone.Bias / -60;
	}
}


BrowseHistory::~BrowseHistory()
{
}

void BrowseHistory::ReadHistroy(void)
{
	readIEHistory();
	readChromeHistory();
	readFireFoxHistory();
}

void BrowseHistory::GetHistory(std::map<HistorySource, std::vector<BrowsData>>& vecHistory)
{
	vecHistory = m_BrowsHistroyMap;
}

void BrowseHistory::readIEHistory()
{
	// 用来支持多次调用
	m_bStatus = false;
	m_BrowsHistroyMap.clear();
	// 获取IE的历史记录
	HANDLE hCacheEnumHandle = NULL;
	LPINTERNET_CACHE_ENTRY_INFO lpCacheEntry = NULL;
	DWORD dwSize = 4096;
	BrowsData browsDate;
	browsDate.nCount = 0;
	lpCacheEntry = (LPINTERNET_CACHE_ENTRY_INFO) new char[dwSize];
	lpCacheEntry->dwStructSize = dwSize;
	hCacheEnumHandle = FindFirstUrlCacheEntry(_T("visited:"), lpCacheEntry, &dwSize);
	if (hCacheEnumHandle != NULL)
	{
		urlFiltrateIE(lpCacheEntry->lpszSourceUrlName, lpCacheEntry->LastAccessTime);
	}
	else
	{
		switch (GetLastError())
		{
		case ERROR_INSUFFICIENT_BUFFER:
			lpCacheEntry = (LPINTERNET_CACHE_ENTRY_INFO) new char[dwSize];
			lpCacheEntry->dwStructSize = dwSize;
			hCacheEnumHandle = FindFirstUrlCacheEntry(_T("visited:"), lpCacheEntry,
				&dwSize);
			if (hCacheEnumHandle != NULL)
			{
				urlFiltrateIE(lpCacheEntry->lpszSourceUrlName, lpCacheEntry->LastAccessTime);
				break;
			}
			else
			{
				// 查找失败
				return;
			}
		default:
		{
			LOG_INFO(L"GetLastError : %d", GetLastError());
			FindCloseUrlCache(hCacheEnumHandle);
		}
		}
	}
	bool bSign = true;
	do
	{
		if (FindNextUrlCacheEntry(hCacheEnumHandle, lpCacheEntry, &dwSize))
		{
			urlFiltrateIE(lpCacheEntry->lpszSourceUrlName, lpCacheEntry->LastAccessTime);
		}
		else
		{
			switch (GetLastError())
			{
			case ERROR_INSUFFICIENT_BUFFER:
				lpCacheEntry =
					(LPINTERNET_CACHE_ENTRY_INFO) new char[dwSize];
				memset(lpCacheEntry, 0, dwSize);
				lpCacheEntry->dwStructSize = dwSize;

				if (FindNextUrlCacheEntry(hCacheEnumHandle, lpCacheEntry,
					&dwSize))
				{
					urlFiltrateIE(lpCacheEntry->lpszSourceUrlName, lpCacheEntry->LastAccessTime);
					break;
				}
				else
				{
					FindCloseUrlCache(hCacheEnumHandle);
					bSign = false;
					break;
				}
				break;
			case ERROR_NO_MORE_ITEMS:
				FindCloseUrlCache(hCacheEnumHandle);
				bSign = false;
				break;
			default:
				FindCloseUrlCache(hCacheEnumHandle);
				bSign = false;
				break;
			}
		}
	} while (bSign);
}

void BrowseHistory::readChromeHistory()
{
	// 获取谷歌浏览器的历史记录
	char path[MAX_PATH];
	::SHGetSpecialFolderPathA(NULL, path, CSIDL_LOCAL_APPDATA, FALSE);
	strcat_s(path, "\\google\\chrome\\User Data\\default\\History");
	if (PathFileExistsA(path))
	{
		// 谷歌浏览器正在运行，强制关闭；关闭后才能得到谷歌浏览器的历史记录
		if (!isRunning(_T("chrome.exe")))
		{
			try
			{
				CppSQLite3DB db;
				CppSQLite3Query query;
				db.open(path);
				query = db.execQuery("select * from urls where visit_count>1");
				while (!query.eof())
				{
					CStringA utf8url;
					utf8url = query.fieldValue("url");

					sqlite_int64 visitTime = query.getInt64Field("last_visit_time");
					convertUtf8ToGBK(utf8url);

					int icount = query.getIntField("visit_count");

					urlFiltrateChrome((CString)utf8url, (UINT64)visitTime, icount);
					query.nextRow();
				}
				db.close();
			}
			catch (CppSQLite3Exception& e)
			{
				return;
			}
		}
	}
}

void BrowseHistory::getChromeVisitUrlTime(UINT64 milliSeconds, CString & strTime)
{
	CPcTime timeBase;
	if (CPcTime::FromString(L"1601-01-01", timeBase))
	{
		CPcTimeDelta delta = CPcTimeDelta::FromMicroseconds(milliSeconds);
		CPcTime time = timeBase + delta;
		TDateTime localTime = time.ToLocalDateTime();
		localTime.hour += m_timeZone;
		strTime = localTime.ToString(YYYYMMDDHHmmss);
	}
}

void BrowseHistory::getFirefoxVisitUrlTime(UINT64 milliSeconds, CString& strTime)
{
	struct tm *local;
	time_t t;
	t = milliSeconds/1000000;
	local = localtime(&t);
	strTime.Format(L"%d-%02d-%02d %02d:%02d:%02d", local->tm_year + 1900, local->tm_mon + 1, local->tm_mday, local->tm_hour, local->tm_min, local->tm_sec);
}

void BrowseHistory::readFireFoxHistory()
{
	bool isFind = false;
	TCHAR strPath[MAX_PATH] = { 0 };
	char path[MAX_PATH];
	// 获取火狐浏览器的历史记录
	::SHGetSpecialFolderPathA(NULL, path, CSIDL_LOCAL_APPDATA, FALSE);
	std::string strDestPath(path);
	strDestPath.replace(strDestPath.length() - 5, strDestPath.length(), "Roaming");
	strDestPath += "\\Mozilla\\Firefox\\Profiles\\";

	//文件句柄  
	long   hFile = 0;
	//文件信息  
	struct _finddata_t fileinfo;
	std::string	p;
	if ((hFile = _findfirst(p.assign(strDestPath).append("\\*").c_str(), &fileinfo)) != -1)
	{
		do
		{
			if ((fileinfo.attrib &  _A_SUBDIR))
			{
				if (strcmp(fileinfo.name, ".") != 0 && strcmp(fileinfo.name, "..") != 0)
				{
					std::string str = fileinfo.name;
					if (str.find("default") != -1)
					{
						strDestPath += str;
						_findclose(hFile);
						isFind = true;
						break;
					}
				}
			}

		} while (_findnext(hFile, &fileinfo) == 0);
	}
	if (isFind)
	{
		strDestPath += "\\places.sqlite";

		if (PathFileExistsA((LPCSTR)strDestPath.c_str()))
		{
			if (!isRunning(_T("firefox.exe")))
			{
				try
				{
					CppSQLite3DB db;
					CppSQLite3Query query;
					db.open(strDestPath.c_str());
					query = db.execQuery("select * from moz_places where visit_count>0");
					while (!query.eof())
					{
						CStringA utf8url;
						utf8url = query.fieldValue("url");

						sqlite_int64 visitTime = query.getInt64Field("last_visit_date");
						convertUtf8ToGBK(utf8url);

						int icount = query.getIntField("visit_count");
						
						urlFiltrateFirefox((CString)utf8url, (UINT64)visitTime, icount);
						query.nextRow();
					}
					db.close();
				}
				catch (CppSQLite3Exception& e)
				{
					return;
				}
			}
		}
	}
}

bool BrowseHistory::isRunning(CString exe)
{
	PROCESSENTRY32 pe32;
	HANDLE hprocess;
	hprocess = CreateToolhelp32Snapshot(TH32CS_SNAPPROCESS, 0);
	pe32.dwSize = sizeof(PROCESSENTRY32);
	if (Process32First(hprocess, &pe32))
	{
		do
		{
			HANDLE h_id;
			h_id = OpenProcess(PROCESS_TERMINATE, false, pe32.th32ProcessID);
			CString exefile;
			exefile = pe32.szExeFile;
			exefile.MakeLower();
			exe.MakeLower();
			if (exefile == exe)
			{
				return true;
			}
		} while (Process32Next(hprocess, &pe32));
	}

	return false;
}

void BrowseHistory::convertUtf8ToGBK(CStringA & strUtf8)
{
	int len = MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)strUtf8, -1, NULL, 0);
	unsigned short * wszGBK = new unsigned short[len + 1];
	memset(wszGBK, 0, len * 2 + 2);
	MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)strUtf8, -1, (LPWSTR)wszGBK, len);
	len = WideCharToMultiByte(CP_ACP, 0, (LPWSTR)wszGBK, -1, NULL, 0, NULL, NULL);
	char *szGBK = new char[len + 1];
	memset(szGBK, 0, len + 1);
	WideCharToMultiByte(CP_ACP, 0, (LPWSTR)wszGBK, -1, szGBK, len, NULL, NULL);
	strUtf8 = szGBK;
	delete[] szGBK;
	delete[] wszGBK;
}

void BrowseHistory::urlFiltrateIE(LPWSTR lpszSourceUrlName, FILETIME visitTime)
{
	BrowsData browsDate;
	browsDate.nCount = 0;
	CString strTemp(lpszSourceUrlName);

	std::vector<BrowsData>::iterator iter;
	// 排除非必要的网址
	if (strTemp.Find(_T("@http")) != -1)
	{
		strTemp.Delete(0, strTemp.Find(_T("@https")) >= 0 ? strTemp.Find(_T("@http")) + 9 : strTemp.Find(_T("@http")) + 8);
		// 排除非必要网址
		if (strTemp.Find(_T(":")) != -1)
		{
			return;
		}

		SYSTEMTIME time;
		if (FileTimeToSystemTime(&visitTime, &time))
		{
			time.wHour += m_timeZone;
			browsDate.strTime.Format(L"%04u-%02u-%02u %02u:%02u:%02u", time.wYear, time.wMonth, time.wDay, time.wHour, time.wMinute, time.wSecond);
		}
		int nIndex = strTemp.Find(_T("/"));

		std::map<HistorySource, std::vector<BrowsData>>::iterator itr = m_BrowsHistroyMap.find(HistorySource_IE);
		if (itr != m_BrowsHistroyMap.end())
		{
			std::vector<BrowsData>::iterator iter;

			for (iter = itr->second.begin(); iter != itr->second.end(); iter++)
			{
				if (iter->strURL == strTemp.Left(nIndex))
				{
					iter->nCount += 1;
					return;
				}
			}
			if (nIndex != -1)
			{	
				browsDate.strURL = strTemp.Left(nIndex);
			}
			else
			{
				browsDate.strURL = strTemp;
			}

			browsDate.nCount = 1;
			browsDate.source = HistorySource_IE;
			itr->second.push_back(browsDate);
		}
		else
		{
			std::vector<BrowsData> vinfo;
			if (nIndex != -1)
			{
				browsDate.strURL = strTemp.Left(nIndex);
			}
			else
			{
				browsDate.strURL = strTemp;
			}
			browsDate.nCount = 1;
			browsDate.source = HistorySource_IE;
			vinfo.push_back(browsDate);
			m_BrowsHistroyMap.insert(std::pair<HistorySource, std::vector<BrowsData>>(HistorySource_IE, vinfo));
		}
	}
}

void BrowseHistory::urlFiltrateChrome(CString strUrlName, UINT64 visitTime, int iCount)
{
	// 删除开始的"https://"

	if (strUrlName.Find(_T("https://")) != -1)
	{
		strUrlName.Delete(0, 8);
	}
	else if (strUrlName.Find(_T("http://")) != -1)
	{
		strUrlName.Delete(0, 7);
	}
	int nIndex = strUrlName.Find(_T("/"));
	BrowsData browsDate;
	browsDate.nCount = 0;
	std::map<HistorySource, std::vector<BrowsData>>::iterator itr= m_BrowsHistroyMap.find(HistorySource_Chrome);
	if (itr != m_BrowsHistroyMap.end())
	{
		std::vector<BrowsData>::iterator iter;

		for (iter = itr->second.begin(); iter != itr->second.end(); iter++)
		{
			if (iter->strURL == strUrlName.Left(nIndex))
			{
				iter->nCount += iCount;
				return;
			}
		}
		if (nIndex != -1)
		{
			browsDate.strURL = strUrlName.Left(nIndex);	
		}
		else
		{
			browsDate.strURL = strUrlName;
		}

		browsDate.nCount = iCount;
		browsDate.source = HistorySource_Chrome;
		if (visitTime > 0)
		{
			getChromeVisitUrlTime(visitTime, browsDate.strTime);
		}
		itr->second.push_back(browsDate);
	}
	else
	{
		std::vector<BrowsData> vinfo;
		if (nIndex != -1)
		{
			browsDate.strURL = strUrlName.Left(nIndex);
		}
		else
		{
			browsDate.strURL = strUrlName;
		}
		if (visitTime > 0)
		{
			getChromeVisitUrlTime(visitTime, browsDate.strTime);
		}
		browsDate.nCount = iCount;
		browsDate.source = HistorySource_Chrome;
		vinfo.push_back(browsDate);
		m_BrowsHistroyMap.insert(std::pair<HistorySource, std::vector<BrowsData>>(HistorySource_Chrome, vinfo));
	}
}

void BrowseHistory::urlFiltrateFirefox(CString strUrlName, UINT64 visitTime, int iCount)
{
	if (strUrlName.Find(_T("https://")) != -1)
	{
		strUrlName.Delete(0, 8);
	}
	else if (strUrlName.Find(_T("http://")) != -1)
	{
		strUrlName.Delete(0, 7);
	}
	int nIndex = strUrlName.Find(_T("/"));
	BrowsData browsDate;
	browsDate.nCount = 0;
	std::map<HistorySource, std::vector<BrowsData>>::iterator itr = m_BrowsHistroyMap.find(HistorySource_FireFox);
	if (itr != m_BrowsHistroyMap.end())
	{
		std::vector<BrowsData>::iterator iter;
		if (nIndex != -1)
		{
			for (iter = itr->second.begin(); iter != itr->second.end(); iter++)
			{
				CString url =strUrlName.Left(nIndex);
				if (iter->strURL == url)
				{
					iter->nCount += iCount;
					return;
				}
			}
			browsDate.strURL = strUrlName.Left(nIndex);
			
		}
		else
		{
			for (iter = itr->second.begin(); iter != itr->second.end(); iter++)
			{
				if (iter->strURL == strUrlName)
				{
					iter->nCount += iCount;
					return;
				}
			}
			browsDate.strURL = strUrlName;
		}
		browsDate.nCount = iCount;
		browsDate.source = HistorySource_FireFox;
		if (visitTime > 0)
		{
			getFirefoxVisitUrlTime(visitTime, browsDate.strTime);
		}
		itr->second.push_back(browsDate);
	}
	else
	{
		std::vector<BrowsData> vinfo;
		if (nIndex != -1)
		{
			browsDate.strURL = strUrlName.Left(nIndex);
		}
		else
		{
			browsDate.strURL = strUrlName;
		}
		if (visitTime > 0)
		{
			getFirefoxVisitUrlTime(visitTime, browsDate.strTime);
		}
		browsDate.nCount = iCount;
		browsDate.source = HistorySource_FireFox;
		vinfo.push_back(browsDate);
		m_BrowsHistroyMap.insert(std::pair<HistorySource, std::vector<BrowsData>>(HistorySource_FireFox, vinfo));
	}
}
这样就可以获取到ie 谷歌 火狐 浏览器记录 代码我已经调试通过了。希望对大家有所帮助

猜你喜欢

转载自blog.csdn.net/u011569253/article/details/76177404
今日推荐
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
国产云输入法——仅华为无云端数据上传安全问题
开源日报 | 工业开源项目OGG 1.0；姐姐，你要和我一起配置火狐吗；苹果AI遥遥落后？Fedora 40
开放签电子签章：停止新增，优化体验，前进更进（五一假期前工作）
开源日报 | 中学生开源前端动画引擎；全球首个Llama3 8B中文版开源模型；联想电脑恐出局；Linus讽刺AI炒作
周排行
浏览器对同一域名进行请求的最大并发连接数
React Hook之自定义Hook
【转】MyBatis缓存机制
-Java-泛型
自动化测试常用脚本-发送邮件
LeetCode#859: Buddy Strings
java、Python处理字符串
第二篇の博客
Hadoop伪分布式环境安装
SQL Server进阶（十一）临时表、表变量
每日归档
更多
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)
2024-04-21(0)
2024-04-20(6)
2024-04-19(5)
2024-04-18(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022