python-使用Python进行数字取证调查

1、你曾经去过哪里？——在注册表中分析无线访问热点：

以管理员权限开启cmd，输入如下命令来列出每个网络显示出profile Guid对网络的描述、网络名和网关的MAC地址：

reg query "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Windows NT\
CurrentVersion\NetworkList\Signatures\Unmanaged" /s

使用WinReg读取Windows注册表中的内容：

这里需要用到Python的_winreg库，在Windows版是默认安装好的。

连上注册表后，使用OpenKey()函数打开相关的键，在循环中依次分析该键下存储的所有网络network profile，其中FirstNetwork网络名和DefaultGateway默认网关的Mac地址的键值打印出来。

#!/usr/bin/python
#coding=utf-8
from _winreg import *

# 将REG_BINARY值转换成一个实际的Mac地址
def val2addr(val):
    addr = ""
    for ch in val:
        addr += ("%02x " % ord(ch))
    addr = addr.strip(" ").replace(" ", ":")[0:17]
    return addr

# 打印网络相关信息
def printNets():
    net = "SOFTWARE\Microsoft\Windows NT\CurrentVersion\NetworkList\Signatures\Unmanaged"
    key = OpenKey(HKEY_LOCAL_MACHINE, net)
    print "\n[*]Networks You have Joined."
    for i in range(100):
        try:
            guid = EnumKey(key, i)
            netKey = OpenKey(key, str(guid))
            (n, addr, t) = EnumValue(netKey, 5)
            (n, name, t) = EnumValue(netKey, 4)
            macAddr = val2addr(addr)
            netName = name
            print '[+] ' + netName + '  ' + macAddr
            CloseKey(netKey)
        except:
            break

def main():
    printNets()

if __name__ == '__main__':
    main()

调用方式：winreg.ph

使用Mechanize把Mac地址传给Wigle：

此处增加了对Wigle网站的访问并将Mac地址传递给Wigle来获取经纬度等物理地址信息。

#!/usr/bin/python
#coding=utf-8
from _winreg import *
import mechanize
import urllib
import re
import urlparse
import os
import optparse

# 将REG_BINARY值转换成一个实际的Mac地址
def val2addr(val):
    addr = ""
    for ch in val:
        addr += ("%02x " % ord(ch))
    addr = addr.strip(" ").replace(" ", ":")[0:17]
    return addr

# 打印网络相关信息
def printNets(username, password):
    net = "SOFTWARE\Microsoft\Windows NT\CurrentVersion\NetworkList\Signatures\Unmanaged"
    key = OpenKey(HKEY_LOCAL_MACHINE, net)
    print "\n[*]Networks You have Joined."
    for i in range(100):
        try:
            guid = EnumKey(key, i)
            netKey = OpenKey(key, str(guid))
            (n, addr, t) = EnumValue(netKey, 5)
            (n, name, t) = EnumValue(netKey, 4)
            macAddr = val2addr(addr)
            netName = name
            print '[+] ' + netName + '  ' + macAddr
            wiglePrint(username, password, macAddr)
            CloseKey(netKey)
        except:
            break

# 通过wigle查找Mac地址对应的经纬度
def wiglePrint(username, password, netid):
    browser = mechanize.Browser()
    browser.open('http://wigle.net')
    reqData = urllib.urlencode({'credential_0': username, 'credential_1': password})
    browser.open('https://wigle.net/gps/gps/main/login', reqData)
    params = {}
    params['netid'] = netid
    reqParams = urllib.urlencode(params)
    respURL = 'http://wigle.net/gps/gps/main/confirmquery/'
    resp = browser.open(respURL, reqParams).read()
    mapLat = 'N/A'
    mapLon = 'N/A'
    rLat = re.findall(r'maplat=.*\&', resp)
    if rLat:
        mapLat = rLat[0].split('&')[0].split('=')[1]
    rLon = re.findall(r'maplon=.*\&', resp)
    if rLon:
        mapLon = rLon[0].split
    print '[-] Lat: ' + mapLat + ', Lon: ' + mapLon

def main():
    parser = optparse.OptionParser('usage %prog ' + '-u <wigle username> -p <wigle password>')
    parser.add_option('-u', dest='username', type='string', help='specify wigle password')
    parser.add_option('-p', dest='password', type='string', help='specify wigle username')
    (options, args) = parser.parse_args()
    username = options.username
    password = options.password
    if username == None or password == None:
        print parser.usage
        exit(0)
    else:
        printNets(username, password)

if __name__ == '__main__':
    main()

调用方式：winreg2.py -u root -p 123123

 

2、用Python恢复被删入回收站中的内容：

使用OS模块寻找被删除的文件/文件夹：

Windows系统中的回收站是一个专门用来存放被删除文件的特殊文件夹。

子目录中的字符串表示的是用户的SID，对应机器里一个唯一的用户账户。

c:\$RECYCLE.BIN>cd c:/$Recycle.Bin

c:\$RECYCLE.BIN>dir /a
 驱动器 C 中的卷是 OS
 卷的序列号是 C0CB-3113

 c:\$RECYCLE.BIN 的目录

2018/05/13  12:18    <DIR>          .
2018/05/13  12:18    <DIR>          ..
2018/05/13  12:18    <DIR>          S-1-5-18
2018/05/13  11:45    <DIR>          S-1-5-21-2810393101-2068805519-295658952-1001
               0 个文件              0 字节
               4 个目录 85,724,626,944 可用字节

寻找被删除的文件/文件夹的函数：

#!/usr/bin/python
#coding=utf-8
import os

# 逐一测试回收站的目录是否存在，并返回第一个找到的回收站目录
def returnDir():
    dirs=['C:\\Recycler\\', 'C:\\Recycled\\', 'C:\\$Recycle.Bin\\']
    for recycleDir in dirs:
        if os.path.isdir(recycleDir):
            return recycleDir
    return None

用Python把SID和用户名关联起来：

可以使用Windows注册表把SID转换成一个准确的用户名。

以管理员权限运行cmd并输入命令：

reg query "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Windows NT\CurrentVersion\ProfileList\S-1-5-21-2595130515-3345905091-1839164762-1000" /s

代码如下：

#!/usr/bin/python
#coding=utf-8
import os
import optparse
from _winreg import *

# 逐一测试回收站的目录是否存在，并返回第一个找到的回收站目录
def returnDir():
    dirs=['C:\\Recycler\\', 'C:\\Recycled\\', 'C:\\$Recycle.Bin\\']
    for recycleDir in dirs:
        if os.path.isdir(recycleDir):
            return recycleDir
    return None

# 操作注册表来获取相应目录属主的用户名
def sid2user(sid):
    try:
        key = OpenKey(HKEY_LOCAL_MACHINE, "SOFTWARE\Microsoft\Windows NT\CurrentVersion\ProfileList" + '\\' + sid)
        (value, type) = QueryValueEx(key, 'ProfileImagePath')
        user = value.split('\\')[-1]
        return user
    except:
        return sid

def findRecycled(recycleDir):
    dirList = os.listdir(recycleDir)
    for sid in dirList:
        files = os.listdir(recycleDir + sid)
        user = sid2user(sid)
        print '\n[*] Listing Files For User: ' + str(user)
        for file in files:
            print '[+] Found File: ' + str(file)

def main():
    recycledDir = returnDir()
    findRecycled(recycledDir)

if __name__ == '__main__':
    main()

调用方式：recyclebin.py

3、元数据：

使用PyPDF解析PDF文件中的元数据：

pyPdf是管理PDF文档的第三方Python库，在Kali中是已经默认安装了的就不需要再去下载安装。

#!/usr/bin/python
#coding=utf-8
import pyPdf
import optparse
from pyPdf import PdfFileReader

# 使用getDocumentInfo()函数提取PDF文档所有的元数据
def printMeta(fileName):
    pdfFile = PdfFileReader(file(fileName, 'rb'))
    docInfo = pdfFile.getDocumentInfo()
    print "[*] PDF MeataData For: " + str(fileName)
    for meraItem in docInfo:
        print "[+] " + meraItem + ": " + docInfo[meraItem]

def main():
    parser = optparse.OptionParser("[*]Usage: python pdfread.py -F <PDF file name>")
    parser.add_option('-F', dest='fileName', type='string', help='specify PDF file name')
    (options, args) = parser.parse_args()
    fileName = options.fileName
    if fileName == None:
        print parser.usage
        exit(0)
    else:
        printMeta(fileName)

if __name__ == '__main__':
    main()

解析一个PDF文件的调用方式：python pdfread.py -F *.pdf

理解Exif元数据：

Exif，即exchange image file format交换图像文件格式，定义了如何存储图像和音频文件的标准。

用BeautifulSoup下载图片：

import urllib2
from bs4 import BeautifulSoup as BS
from os.path import basename
from urlparse import urlsplit

# 通过BeautifulSoup查找URL中所有的img标签
def findImages(url):
    print '[+] Finding images on ' + url
    urlContent = urllib2.urlopen(url).read()
    soup = BS(urlContent, 'lxml')
    imgTags = soup.findAll('img')
    return imgTags

# 通过img标签的src属性的值来获取图片URL下载图片
def downloadImage(imgTag):
    try:
        print '[+] Dowloading image...'
        imgSrc = imgTag['src']
        imgContent = urllib2.urlopen(imgSrc).read()
        imgFileName = basename(urlsplit(imgSrc)[2])
        imgFile = open(imgFileName, 'wb')
        imgFile.write(imgContent)
        imgFile.close()
        return imgFileName
    except:
        return ' '

用Python的图像处理库读取图片中的Exif元数据：

这里使用到Python的图形处理库PIL，在Kali中默认安装了。

这里查看下载图片的元数据中是否含有Exif标签“GPSInfo”，若存在则输出存在信息。

#!/usr/bin/python
#coding=utf-8
import optparse
from PIL import Image
from PIL.ExifTags import TAGS
import urllib2
from bs4 import BeautifulSoup as BS
from os.path import basename
from urlparse import urlsplit

# 通过BeautifulSoup查找URL中所有的img标签
def findImages(url):
    print '[+] Finding images on ' + url
    urlContent = urllib2.urlopen(url).read()
    soup = BS(urlContent, 'lxml')
    imgTags = soup.findAll('img')
    return imgTags

# 通过img标签的src属性的值来获取图片URL下载图片
def downloadImage(imgTag):
    try:
        print '[+] Dowloading image...'
        imgSrc = imgTag['src']
        imgContent = urllib2.urlopen(imgSrc).read()
        imgFileName = basename(urlsplit(imgSrc)[2])
        imgFile = open(imgFileName, 'wb')
        imgFile.write(imgContent)
        imgFile.close()
        return imgFileName
    except:
        return ' '

# 获取图像文件的元数据，并寻找是否存在Exif标签“GPSInfo”
def testForExif(imgFileName):
    try:
        exifData = {}
        imgFile = Image.open(imgFileName)
        info = imgFile._getexif()
        if info:
            for (tag, value) in info.items():
                decoded = TAGS.get(tag, tag)
                exifData[decoded] = value
            exifGPS = exifData['GPSInfo']
            if exifGPS:
                print '[*] ' + imgFileName + ' contains GPS MetaData'
    except:
        pass

def main():
    parser = optparse.OptionParser('[*]Usage: python Exif.py -u <target url>')
    parser.add_option('-u', dest='url', type='string', help='specify url address')
    (options, args) = parser.parse_args()
    url = options.url
    if url == None:
        print parser.usage
        exit(0)
    else:
        imgTags = findImages(url)
        for imgTag in imgTags:
            imgFileName = downloadImage(imgTag)
            testForExif(imgFileName)

if __name__ == '__main__':
    main()

书中样例的网址为https://www.flickr.com/photos/dvids/4999001925/sizes/o

调用方式：python Exif.py -u https://www.flickr.com/photos/dvids/4999001925/sizes/o

4、用Python分析应用程序的使用记录：

使用Python和SQLite3自动查询Skype的数据库：

这里没有下载Skype聊天程序，感兴趣的自己下载测试即可。

#!/usr/bin/python
#coding=utf-8
import sqlite3
import optparse
import os

# 连接main.db数据库，申请游标，执行SQL语句并返回结果
def printProfile(skypeDB):
    conn = sqlite3.connect(skypeDB)
    c = conn.cursor()
    c.execute("SELECT fullname, skypename, city, country, datetime(profile_timestamp,'unixepoch') FROM Accounts;")

    for row in c:
        print '[*] -- Found Account --'
        print '[+] User           : '+str(row[0])
        print '[+] Skype Username : '+str(row[1])
        print '[+] Location       : '+str(row[2])+','+str(row[3])
        print '[+] Profile Date   : '+str(row[4])

# 获取联系人的相关信息
def printContacts(skypeDB):
    conn = sqlite3.connect(skypeDB)
    c = conn.cursor()
    c.execute("SELECT displayname, skypename, city, country, phone_mobile, birthday FROM Contacts;")

    for row in c:
        print '\n[*] -- Found Contact --'
        print '[+] User           : ' + str(row[0])
        print '[+] Skype Username : ' + str(row[1])

        if str(row[2]) != '' and str(row[2]) != 'None':
            print '[+] Location       : ' + str(row[2]) + ',' + str(row[3])
        if str(row[4]) != 'None':
            print '[+] Mobile Number  : ' + str(row[4])
        if str(row[5]) != 'None':
            print '[+] Birthday       : ' + str(row[5])

def printCallLog(skypeDB):
    conn = sqlite3.connect(skypeDB)
    c = conn.cursor()
    c.execute("SELECT datetime(begin_timestamp,'unixepoch'), identity FROM calls, conversations WHERE calls.conv_dbid = conversations.id;")
    print '\n[*] -- Found Calls --'

    for row in c:
        print '[+] Time: ' + str(row[0]) + ' | Partner: ' + str(row[1])

def printMessages(skypeDB):
    conn = sqlite3.connect(skypeDB)
    c = conn.cursor()
    c.execute("SELECT datetime(timestamp,'unixepoch'), dialog_partner, author, body_xml FROM Messages;")
    print '\n[*] -- Found Messages --'

    for row in c:
        try:
            if 'partlist' not in str(row[3]):
                if str(row[1]) != str(row[2]):
                    msgDirection = 'To ' + str(row[1]) + ': '
                else:
                    msgDirection = 'From ' + str(row[2]) + ' : '
                print 'Time: ' + str(row[0]) + ' ' + msgDirection + str(row[3])
        except:
            pass

def main():
    parser = optparse.OptionParser("[*]Usage: python skype.py -p <skype profile path> ")
    parser.add_option('-p', dest='pathName', type='string', help='specify skype profile path')
    (options, args) = parser.parse_args()
    pathName = options.pathName
    if pathName == None:
        print parser.usage
        exit(0)
    elif os.path.isdir(pathName) == False:
        print '[!] Path Does Not Exist: ' + pathName
        exit(0)
    else:
        skypeDB = os.path.join(pathName, 'main.db')
        if os.path.isfile(skypeDB):
            printProfile(skypeDB)
            printContacts(skypeDB)
            printCallLog(skypeDB)
            printMessages(skypeDB)
        else:
            print '[!] Skype Database ' + 'does not exist: ' + skpeDB

if __name__ == '__main__':
    main()

这里直接用该书作者提供的数据包进行测试：

调用方式：python Exif.py -p C:\\skype_profile

用Python解析火狐浏览器的SQLite3数据库：

在Windows7以上的系统中，Firefox的sqlite文件保存在类似如下的目录中：

C:\Users\win7\AppData\Roaming\Mozilla\Firefox\Profiles\8eogekr4.default

主要关注这几个文件：cookie.sqlite、places.sqlite、downloads.sqlite

然而在最近新的几个版本的Firefox中已经没有downloads.sqlite这个文件了，具体换成哪个文件可以自己去研究查看一下即可。

#!/usr/bin/python
#coding=utf-8
import re
import optparse
import os
import sqlite3

# 解析打印downloads.sqlite文件的内容，输出浏览器下载的相关信息
def printDownloads(downloadDB):
    conn = sqlite3.connect(downloadDB)
    c = conn.cursor()
    c.execute('SELECT name, source, datetime(endTime/1000000, \'unixepoch\') FROM moz_downloads;')
    print '\n[*] --- Files Downloaded --- '
    for row in c:
        print '[+] File: ' + str(row[0]) + ' from source: ' + str(row[1]) + ' at: ' + str(row[2])

# 解析打印cookies.sqlite文件的内容，输出cookie相关信息
def printCookies(cookiesDB):
    try:
        conn = sqlite3.connect(cookiesDB)
        c = conn.cursor()
        c.execute('SELECT host, name, value FROM moz_cookies')

        print '\n[*] -- Found Cookies --'
        for row in c:
            host = str(row[0])
            name = str(row[1])
            value = str(row[2])
            print '[+] Host: ' + host + ', Cookie: ' + name + ', Value: ' + value
    except Exception, e:
        if 'encrypted' in str(e):
            print '\n[*] Error reading your cookies database.'
            print '[*] Upgrade your Python-Sqlite3 Library'

# 解析打印places.sqlite文件的内容，输出历史记录
def printHistory(placesDB):
    try:
        conn = sqlite3.connect(placesDB)
        c = conn.cursor()
        c.execute("select url, datetime(visit_date/1000000, 'unixepoch') from moz_places, moz_historyvisits where visit_count > 0 and moz_places.id==moz_historyvisits.place_id;")

        print '\n[*] -- Found History --'
        for row in c:
            url = str(row[0])
            date = str(row[1])
            print '[+] ' + date + ' - Visited: ' + url
    except Exception, e:
        if 'encrypted' in str(e):
            print '\n[*] Error reading your places database.'
            print '[*] Upgrade your Python-Sqlite3 Library'
            exit(0)

# 解析打印places.sqlite文件的内容，输出百度的搜索记录
def printBaidu(placesDB):
    conn = sqlite3.connect(placesDB)
    c = conn.cursor()
    c.execute("select url, datetime(visit_date/1000000, 'unixepoch') from moz_places, moz_historyvisits where visit_count > 0 and moz_places.id==moz_historyvisits.place_id;")

    print '\n[*] -- Found Baidu --'
    for row in c:
        url = str(row[0])
        date = str(row[1])
        if 'baidu' in url.lower():
            r = re.findall(r'wd=.*?\&', url)
            if r:
                search=r[0].split('&')[0]
                search=search.replace('wd=', '').replace('+', ' ')
                print '[+] '+date+' - Searched For: ' + search

def main():
    parser = optparse.OptionParser("[*]Usage: firefoxParse.py -p <firefox profile path> ")
    parser.add_option('-p', dest='pathName', type='string', help='specify skype profile path')
    (options, args) = parser.parse_args()
    pathName = options.pathName
    if pathName == None:
        print parser.usage
        exit(0)
    elif os.path.isdir(pathName) == False:
        print '[!] Path Does Not Exist: ' + pathName
        exit(0)
    else:
        downloadDB = os.path.join(pathName, 'downloads.sqlite')
        if os.path.isfile(downloadDB):
            printDownloads(downloadDB)
        else:
            print '[!] Downloads Db does not exist: '+downloadDB

        cookiesDB = os.path.join(pathName, 'cookies.sqlite')
        if os.path.isfile(cookiesDB):
            pass
            printCookies(cookiesDB)
        else:
            print '[!] Cookies Db does not exist:' + cookiesDB

        placesDB = os.path.join(pathName, 'places.sqlite')
        if os.path.isfile(placesDB):
            printHistory(placesDB)
            printBaidu(placesDB)
        else:
            print '[!] PlacesDb does not exist: ' + placesDB

if __name__ == '__main__':
    main()

上述脚本对原本的脚本进行了一点修改，修改的地方是对查找Google搜索记录部分改为对查找Baidu搜索记录，这样在国内更普遍使用~

调用方式：python firefoxParse.py -p C:\Users\win7\AppData\Roaming\Mozilla\Firefox\Profiles\8eogekr4.default

除了downloads.sqlite文件找不到外，其他的文件都正常解析内容了。在查找搜索内容部分，若为中文等字符则显示为编码的形式。

5、用Python调查iTunes的手机备份：

没有iPhone  :-)     ，有的自己测试一下吧 。

#!/usr/bin/python
#coding=utf-8
import os
import sqlite3
import optparse

def isMessageTable(iphoneDB):
    try:
        conn = sqlite3.connect(iphoneDB)
        c = conn.cursor()
        c.execute('SELECT tbl_name FROM sqlite_master WHERE type==\"table\";')
        for row in c:
            if 'message' in str(row):
            return True
    except:
            return False

def printMessage(msgDB):
    try:
        conn = sqlite3.connect(msgDB)
        c = conn.cursor()
        c.execute('select datetime(date,\'unixepoch\'), address, text from message WHERE address>0;')
        for row in c:
            date = str(row[0])
            addr = str(row[1])
            text = row[2]
            print '\n[+] Date: '+date+', Addr: '+addr + ' Message: ' + text
    except:
        pass

def main():
    parser = optparse.OptionParser("[*]Usage: python iphoneParse.py -p <iPhone Backup Directory> ")
    parser.add_option('-p', dest='pathName', type='string',help='specify skype profile path')
    (options, args) = parser.parse_args()
    pathName = options.pathName
    if pathName == None:
        print parser.usage
        exit(0)
    else:
        dirList = os.listdir(pathName)
        for fileName in dirList:
            iphoneDB = os.path.join(pathName, fileName)
            if isMessageTable(iphoneDB):
                try:
                    print '\n[*] --- Found Messages ---'
                    printMessage(iphoneDB)
                except:
                    pass

if __name__ == '__main__':
    main()