Python3通过Everything SDK访问本地文件
2024-05-11 11:48:52
需求：
本地文件中，查找在书单<信息安全从业者书单>的书籍。
原理：
遍历 README.md 将通过Everything SDK在本地查找每本书。
1、计算文件CRC32
因为只是确定本地文件的唯一性，CRC32计算效率上比md5和sha1更快，所以计算CRC.
#!usr/bin/env python
#-*- coding:utf-8 -*- import zlib
import osblock_size = 1024 * 1024
#从文件中读取block_size大小，计算CRC32
def crc32_simple(filepath):try:with open(filepath,'rb') as f:s=f.read(block_size)return zlib.crc32(s,0)except Exception as e:print(str(e))return 0#计算整个文件的crc32
def crc32_file(filepath):crc = 0try:fd = open(filepath, 'rb')while True:buffer = fd.read(block_size)if len(buffer) == 0: # EOF or file empty. return hashesfd.close()if sys.version_info[0] < 3 and crc < 0:crc += 2 ** 32return crc#返回的是十进制的值crc = zlib.crc32(buffer, crc)except Exception as e:if sys.version_info[0] < 3:error = unicode(e)else:error = str(e)print(error)return 02、文件大小自动变换单位
递归实现 文件大小根据bytes，返回合理区间['B', 'KB', 'MB', 'GB', 'TB', 'PB']。eg : 16473740 bytes--> 15.727 MB
#根据文件大小 返回合理区间，16473740 bytes--> 15.727 MB
def FormatSize(size):print(size)#递归实现，精确为最大单位值 + 小数点后三位def formatsize(integer, remainder, level):if integer >= 1024:remainder = integer % 1024integer //= 1024level += 1return formatsize(integer, remainder, level)else:return integer, remainder, levelunits = ['B', 'KB', 'MB', 'GB', 'TB', 'PB']integer, remainder, level = formatsize(size, 0, 0)if level+1 > len(units):level = -1return ( '{}.{:>03d} {}'.format(integer, remainder, units[level]) )3、调用Everything SDK，通过everything64.dll来完成交互。
import ctypes
import datetime
import struct#dll imports
everything_dll = ctypes.WinDLL (r"./Everything64.dll")
everything_dll.Everything_GetResultDateModified.argtypes = [ctypes.c_int,ctypes.POINTER(ctypes.c_ulonglong)]
everything_dll.Everything_GetResultSize.argtypes = [ctypes.c_int,ctypes.POINTER(ctypes.c_ulonglong)]
everything_dll.Everything_GetResultFileNameW.argtypes = [ctypes.c_int]
everything_dll.Everything_GetResultFileNameW.restype = ctypes.c_wchar_p#转换时间
def get_time(filetime):#convert a windows FILETIME to a python datetime#https://stackoverflow.com/questions/39481221/convert-datetime-back-to-windows-64-bit-filetimeWINDOWS_TICKS = int(1/10**-7) # 10,000,000 (100 nanoseconds or .1 microseconds)WINDOWS_EPOCH = datetime.datetime.strptime('1601-01-01 00:00:00','%Y-%m-%d %H:%M:%S')POSIX_EPOCH = datetime.datetime.strptime('1970-01-01 00:00:00','%Y-%m-%d %H:%M:%S')EPOCH_DIFF = (POSIX_EPOCH - WINDOWS_EPOCH).total_seconds() # 11644473600.0WINDOWS_TICKS_TO_POSIX_EPOCH = EPOCH_DIFF * WINDOWS_TICKS # 116444736000000000.0"""Convert windows filetime winticks to python datetime.datetime."""winticks = struct.unpack('<Q', filetime)[0]microsecs = (winticks - WINDOWS_TICKS_TO_POSIX_EPOCH) / WINDOWS_TICKSreturn datetime.datetime.fromtimestamp(microsecs)#defines 定义参看Everything.h
EVERYTHING_REQUEST_FILE_NAME = 0x00000001
EVERYTHING_REQUEST_PATH = 0x00000002
EVERYTHING_REQUEST_SIZE = 0x00000010
EVERYTHING_REQUEST_DATE_MODIFIED = 0x00000040EVERYTHING_SORT_SIZE_DESCENDING = 6#关键词搜索
def searchfile(bookName):recom = re.compile(r'[《》:：、；.，,;—— -()（）【】\'\"]')keyword = recom.sub(' ',bookName).strip()if len(keyword) <1:return#文件大小倒序everything_dll.Everything_SetSort(EVERYTHING_SORT_SIZE_DESCENDING)everything_dll.Everything_SetSearchW(keyword)everything_dll.Everything_SetRequestFlags(EVERYTHING_REQUEST_FILE_NAME | EVERYTHING_REQUEST_PATH | EVERYTHING_REQUEST_SIZE | EVERYTHING_REQUEST_DATE_MODIFIED)#execute the queryeverything_dll.Everything_QueryW(1)#get the number of resultsnum_results = everything_dll.Everything_GetNumResults()#show the number of resultsresult = "\nResult Count: {}\n".format(num_results)print(keyword,result)#create buffersfile_name = ctypes.create_unicode_buffer(260)file_modi = ctypes.c_ulonglong(1)file_size = ctypes.c_ulonglong(1)bPrint = FalsenCount = 0#show resultsfor i in range(num_results):everything_dll.Everything_GetResultFullPathNameW(i,file_name,260)everything_dll.Everything_GetResultDateModified(i,file_modi)everything_dll.Everything_GetResultSize(i,file_size)filepath = ctypes.wstring_at(file_name)if filepath.endswith('.lnk') or filepath.endswith('.txt'):continue#计算文件crc32,格式化为0x1122AAFFfilecrc = hex(crc32_file(filepath)).upper().replace("0X","0x")filesize = FormatSize(file_size.value)modtime = get_time(file_modi)strInfo = "\nFilePath: {}\nSize: {} CRC32:{}".format(filepath,filesize,filecrc)print(strInfo)if not bPrint:fout.write("\n=======↓↓↓↓↓===========\n")fout.write(bookName)fout.write("\n-----------------")bPrint = Truefout.write(strInfo)nCount+=1if bPrint:fout.write("\nFind Count：{}".format(nCount))fout.write("\n=======↑↑↑↑↑===========\n")完整代码
#!usr/bin/env python
#-*- coding:utf-8 -*-
"""
@author:hiltonwei
@file: secBooksFind.py
@time: 2021/12/06
@desc: 信息安全从业者书单推荐 https://github.com/riusksk/secbookstep1 读入 README.md,读取《》内书名step2 通过everything的sdk查找文件，并计算文件CRC32校验值,写入txt中
"""import zlib
import os
import sys
import ctypes
import datetime
import struct
import io
import re#dll imports
everything_dll = ctypes.WinDLL (r"./Everything64.dll")
everything_dll.Everything_GetResultDateModified.argtypes = [ctypes.c_int,ctypes.POINTER(ctypes.c_ulonglong)]
everything_dll.Everything_GetResultSize.argtypes = [ctypes.c_int,ctypes.POINTER(ctypes.c_ulonglong)]
everything_dll.Everything_GetResultFileNameW.argtypes = [ctypes.c_int]
everything_dll.Everything_GetResultFileNameW.restype = ctypes.c_wchar_pfout = open("secBooksFind.txt", 'a+')block_size = 1024 * 1024
#从文件中读取block_size大小，计算CRC32
def crc32_simple(filepath):try:with open(filepath,'rb') as f:s=f.read(block_size)return zlib.crc32(s,0)except Exception as e:print(str(e))return 0#计算整个文件的crc32
def crc32_file(filepath):crc = 0try:fd = open(filepath, 'rb')while True:buffer = fd.read(block_size)if len(buffer) == 0: # EOF or file empty. return hashesfd.close()if sys.version_info[0] < 3 and crc < 0:crc += 2 ** 32return crc#返回的是十进制的值crc = zlib.crc32(buffer, crc)except Exception as e:if sys.version_info[0] < 3:error = unicode(e)else:error = str(e)print(error)return 0#根据文件大小 返回合理区间，16473740 bytes--> 15.727 MB
def FormatSize(size):print(size)#递归实现，精确为最大单位值 + 小数点后三位def formatsize(integer, remainder, level):if integer >= 1024:remainder = integer % 1024integer //= 1024level += 1return formatsize(integer, remainder, level)else:return integer, remainder, levelunits = ['B', 'KB', 'MB', 'GB', 'TB', 'PB']integer, remainder, level = formatsize(size, 0, 0)if level+1 > len(units):level = -1return ( '{}.{:>03d} {}'.format(integer, remainder, units[level]) )#转换时间
def get_time(filetime):#convert a windows FILETIME to a python datetime#https://stackoverflow.com/questions/39481221/convert-datetime-back-to-windows-64-bit-filetimeWINDOWS_TICKS = int(1/10**-7) # 10,000,000 (100 nanoseconds or .1 microseconds)WINDOWS_EPOCH = datetime.datetime.strptime('1601-01-01 00:00:00','%Y-%m-%d %H:%M:%S')POSIX_EPOCH = datetime.datetime.strptime('1970-01-01 00:00:00','%Y-%m-%d %H:%M:%S')EPOCH_DIFF = (POSIX_EPOCH - WINDOWS_EPOCH).total_seconds() # 11644473600.0WINDOWS_TICKS_TO_POSIX_EPOCH = EPOCH_DIFF * WINDOWS_TICKS # 116444736000000000.0"""Convert windows filetime winticks to python datetime.datetime."""winticks = struct.unpack('<Q', filetime)[0]microsecs = (winticks - WINDOWS_TICKS_TO_POSIX_EPOCH) / WINDOWS_TICKSreturn datetime.datetime.fromtimestamp(microsecs)#defines 定义参看Everything.h
EVERYTHING_REQUEST_FILE_NAME = 0x00000001
EVERYTHING_REQUEST_PATH = 0x00000002
EVERYTHING_REQUEST_SIZE = 0x00000010
EVERYTHING_REQUEST_DATE_MODIFIED = 0x00000040EVERYTHING_SORT_SIZE_DESCENDING = 6#关键词搜索
def searchfile(bookName):recom = re.compile(r'[《》:：、；.，,;—— -()（）【】\'\"]')keyword = recom.sub(' ',bookName).strip()if len(keyword) <1:return#文件大小倒序everything_dll.Everything_SetSort(EVERYTHING_SORT_SIZE_DESCENDING)everything_dll.Everything_SetSearchW(keyword)everything_dll.Everything_SetRequestFlags(EVERYTHING_REQUEST_FILE_NAME | EVERYTHING_REQUEST_PATH | EVERYTHING_REQUEST_SIZE | EVERYTHING_REQUEST_DATE_MODIFIED)#execute the queryeverything_dll.Everything_QueryW(1)#get the number of resultsnum_results = everything_dll.Everything_GetNumResults()#show the number of resultsresult = "\nResult Count: {}\n".format(num_results)print(keyword,result)#create buffersfile_name = ctypes.create_unicode_buffer(260)file_modi = ctypes.c_ulonglong(1)file_size = ctypes.c_ulonglong(1)bPrint = FalsenCount = 0#show resultsfor i in range(num_results):everything_dll.Everything_GetResultFullPathNameW(i,file_name,260)everything_dll.Everything_GetResultDateModified(i,file_modi)everything_dll.Everything_GetResultSize(i,file_size)filepath = ctypes.wstring_at(file_name)if filepath.endswith('.lnk') or filepath.endswith('.txt'):continue#计算文件crc32,格式化为0x1122AAFFfilecrc = hex(crc32_file(filepath)).upper().replace("0X","0x")filesize = FormatSize(file_size.value)modtime = get_time(file_modi)strInfo = "\nFilePath: {}\nSize: {} CRC32:{}".format(filepath,filesize,filecrc)print(strInfo)if not bPrint:fout.write("\n=======↓↓↓↓↓===========\n")fout.write(bookName)fout.write("\n-----------------")bPrint = Truefout.write(strInfo)nCount+=1if bPrint:fout.write("\nFind Count：{}".format(nCount))fout.write("\n=======↑↑↑↑↑===========\n")#读取文件，将《》内的名称去特殊符号后，通过everything查找
def readMd(fileName):dataStr = []with io.open(fileName,'r', encoding='utf-8') as f:dataStr = f.readlines()for line in dataStr:if line.startswith('·'):#《》的内容start = line.find('《')end = line.find('》')end = end if end == -1 else end+1f0 = line[start:end]searchfile(f0)if __name__ == "__main__":readMd("README.md")fout.close()Python3通过Everything SDK访问本地文件相关推荐
- Mac上使用nginx访问本地文件夹报403的问题
Mac上使用nginx访问本地文件夹报403的问题 就是没有权限访问你配置的文件夹在 nginx.conf头行加入下面配置 user root wheel; 不过我的电脑在启动nginx访问的时候会发 ...
- 服务器读取本地文件,java远程服务器访问本地文件
java远程服务器访问本地文件 内容精选 换一换 云服务器网络异常.防火墙未放行本地远程桌面端口.云服务器CPU负载过高等场景均可能导致云服务器无法正常登录.本节操作介绍无法登录Linux弹性云服务器 ...
- java访问文件服务器,java远程服务器访问本地文件
java远程服务器访问本地文件 内容精选 换一换 云服务器网络异常.防火墙未放行本地远程桌面端口.云服务器CPU负载过高等场景均可能导致云服务器无法正常登录.本节操作介绍无法登录Linux弹性云服务器 ...
- 谷歌浏览器关闭跨域限制，允许跨域请求，设置允许访问本地文件
1. 设置允许访问本地文件 只需要右键谷歌浏览器的快捷方式,查看属性,在目标一栏中空出一格然后加入字符串--allow-file-access-from-files,点击确定即可. 2. 允许跨域请求 ...
- 惨痛的教训，NSURL访问本地文件的问题
今天终于有空调试之前碰到但未解决的一个问题.问题是这样的:使用http将一个视频文件(mp4格式)下载到documents目录下,拿到这个路径,ios4.3sdk下,iphone模拟器上播放失败,提示 ...
- 通过ip访问本地文件spring boot
spring boot通过ip访问本地文件 方案一: 继承WebMvcConfigurerAdapter并重写addResourceHandlers方法(SpringBoot2.0及Spring 5. ...
- 解决谷歌访问本地文件和跨域问题
解决谷歌访问本地文件和跨域问题(非代码) 一.解决不能访问本地文件问题 一般浏览器是不能通过load方法来加载本地文件的,那么我们可以右键点击属性. 然后将"–allow-file-acce ...
- 技术小白的第一篇博客 --- 虚拟机访问本地文件设置
虚拟机访问本地文件夹 最近工作中需要使用到虚拟机在不同操作系统上测试软件,总是从服务器拷贝文件太麻烦,就找了一下虚拟机可以直接访问本地文件夹的设置方法,这里就是简单记录一下. 1.在虚拟机的设置页面中 ...
- flash不能访问本地文件
flash出现"不能访问本地资源";解决方案 linux下,如果没有文件夹自行创建 在/home/{user}/.macromedia/Flash_Player/#Security ...
- java访问本地文件_详解Java读取本地文件并显示在JSP文件中
详解Java读取本地文件并显示在JSP文件中 当我们初学IMG标签时,我们知道通过设置img标签的src属性,能够在页面中显示想要展示的图片.其中src的值,可以是磁盘目录上的绝对,也可以是项目下的相 ...
最新文章
- 敏捷开发中如何定义“完成”？
- 记忆模糊、记忆泛化的关键分子开关被发现
- java webdav服务,nginx+webdav
- 为什么德国人工作这么慢，但效率却很高？
- 你可能不知道的switch
- rabbitmq延迟队列实现
- Android测试写入文本Log
- mysql深度解析_百万级数据下的mysql深度解析
- CSDN公众号新功能上线，居然还能搜出小姐姐？？？（文末有福利）
- 基于JAVA+SpringMVC+Mybatis+MYSQL的超市订单管理系统
- Security+ 学习笔记29 虚拟化
- 有效利用PLM系统能为企业带来什么？
- 启动springboot项目APPLICATION FAILED TO START
- 颜色所代表的人的性格
- 使用Frida hook 获取native层代码的返回值
- badboy简介和回放
- 手把手教你做主成分分析
- Altium Designer原理图转OrCAD原理图方法
- VIT ④function 、Object-oriented programming in Python
- Yolov5 系列1--- Yolo发展史以及Yolov5模型详解