def doprocess(argv):
filelimit = 50
word = "local"
localanalysis = "no"
failedfiles = []
emails = []
if len(sys.argv) < 3:
usage()
try:
opts, args = getopt.getopt(argv, "l:d:f:h:n:t:o:")
except getopt.GetoptError:
usage()
for opt, arg in opts:
if opt == '-d':
word = arg
elif opt == '-t':
filetypes = []
if arg.count(",") != 0:
filetypes = arg.split(",")
else:
filetypes.append(arg)
print filetypes
elif opt == '-l':
limit = int(arg)
elif opt == '-h':
localanalysis = arg
elif opt == '-n':
filelimit = int(arg)
elif opt == '-o':
dir = arg
elif opt == '-f':
outhtml = arg
if os.path.exists(dir):
pass
else:
os.mkdir(dir)
if localanalysis == "no":
print "\n[-] Starting online search..."
for filetype in filetypes:
print "\n[-] Searching for " + filetype + " files, with a limit of " + str(
limit)
search = googlesearch.search_google(word, limit, start, filetype)
search.process_files()
files = search.get_files()
print "Results: " + str(len(files)) + " files found"
print "Starting to download " + str(filelimit) + " of them:"
print "----------------------------------------\n"
counter = 1
for x in files:
if counter <= filelimit:
print "[" + str(counter) + "/" + str(filelimit) + "] " + x
getfile = downloader.downloader(x, dir)
getfile.down()
filename = getfile.name()
if filename != "":
if filetype == "pdf":
test = metadataPDF.metapdf(dir + "/" + filename,
password)
elif filetype == "doc" or filetype == "ppt" or filetype == "xls":
test = metadataMSOffice.metaMs2k(dir + "/" +
filename)
if os.name == "posix":
testex = metadataExtractor.metaExtractor(
dir + "/" + filename)
elif filetype == "docx" or filetype == "pptx" or filetype == "xlsx":
test = metadataMSOfficeXML.metaInfoMS(dir + "/" +
filename)
res = test.getData()
if res == "ok":
raw = test.getRaw()
users = test.getUsers()
paths = test.getPaths()
soft = test.getSoftware()
email = []
if filetype == "pdf" or filetype == "docx":
res = test.getTexts()
if res == "ok":
email = test.getEmails()
for em in email:
emails.append(em)
else:
email = []
failedfiles.append(x + ":" + str(res))
respack = [x, users, paths, soft, raw, email]
all.append(respack)
else:
failedfiles.append(x + ":" + str(res))
print "\t [x] Error in the parsing process" #A error in the parsing process
else:
pass
counter += 1
else:
print "[-] Starting local analysis in directory " + dir
dirList = os.listdir(dir)
print dirList
for filename in dirList:
if filename != "":
filetype = str(filename.split(".")[-1])
if filetype == "pdf":
test = metadataPDF.metapdf(dir + "/" + filename, password)
elif filetype == "doc" or filetype == "ppt" or filetype == "xls":
print "doc"
test = metadataMSOffice.metaMs2k(dir + "/" + filename)
if os.name == "posix":
testex = metadataExtractor.metaExtractor(dir + "/" +
filename)
elif filetype == "docx" or filetype == "pptx" or filetype == "xlsx":
test = metadataMSOfficeXML.metaInfoMS(dir + "/" + filename)
res = test.getData()
if res == "ok":
raw = test.getRaw()
users = test.getUsers()
paths = test.getPaths()
soft = test.getSoftware()
if (filetype == "doc" or filetype == "xls"
or filetype == "ppt") and os.name == "posix":
testex.runExtract()
testex.getData()
paths.extend(testex.getPaths())
respack = [filename, users, paths, soft, raw, email]
all.append(respack)
else:
failedfiles.append(filename + ":" + str(res))
print "[x] Error in the parsing process" # A error in the parsing process
if filetype == "docx" or filetype == "pdf":
res = test.getTexts()
if res == "ok":
email = test.getEmails()
for x in email:
emails.append(x)
else:
failedfiles(filename + ":" + str(res))
else:
print "pass"
else:
pass
print "processing"
proc = processor.processor(all)
userlist = proc.sort_users()
softlist = proc.sort_software()
pathlist = proc.sort_paths()
try:
html = htmlExport.htmlExport(userlist, softlist, pathlist, all,
outhtml, dir, failedfiles, word, emails)
save = html.writehtml()
except Exception, e:
print e
print "Error creating the file"
def post(self, target):
filelimit = 50
word = "local"
localanalysis = "no"
failedfiles = []
emails = []
'''
if len(sys.argv) < 3:
usage()
try:
opts, args = getopt.getopt(argv, "l:d:f:h:n:t:o:")
except getopt.GetoptError:
usage()
'''
opts = [('-d', target), ('-t', 'pdf,doc'), ('-l', '200'), ('-n', '50'),
('-o', 'downloadfiles'), ('-f', 'resultsss.html')]
for opt, arg in opts:
if opt == '-d':
word = target
elif opt == '-t':
filetypes = []
if arg.count(",") != 0:
filetypes = arg.split(",")
else:
filetypes.append(arg)
print filetypes
elif opt == '-l':
limit = int(arg)
elif opt == '-h':
localanalysis = arg
elif opt == '-n':
filelimit = int(arg)
elif opt == '-o':
dir = arg
elif opt == '-f':
outhtml = arg
if os.path.exists(dir):
pass
else:
os.mkdir(dir)
if localanalysis == "no":
print "\n[-] Starting online search..."
for filetype in filetypes:
print "\n[-] Searching for " + filetype + " files, with a limit of " + str(
limit)
try:
search = googlesearch.search_google(
word, limit, start, filetype)
search.process_files()
files = search.get_files()
print "Results: " + str(len(files)) + " files found"
print "Starting to download " + str(
filelimit) + " of them:"
print "----------------------------------------\n"
counter = 1
for x in files:
if counter <= filelimit:
print "[" + str(counter) + "/" + str(
filelimit) + "] " + x
getfile = downloader.downloader(x, dir)
getfile.down()
filename = getfile.name()
if filename != "":
if filetype == "pdf":
test = metadataPDF.metapdf(
dir + "/" + filename, password)
elif filetype == "doc" or filetype == "ppt" or filetype == "xls":
test = metadataMSOffice.metaMs2k(dir +
"/" +
filename)
if os.name == "posix":
testex = metadataExtractor.metaExtractor(
dir + "/" + filename)
elif filetype == "docx" or filetype == "pptx" or filetype == "xlsx":
test = metadataMSOfficeXML.metaInfoMS(
dir + "/" + filename)
res = test.getData()
if res == "ok":
raw = test.getRaw()
users = test.getUsers()
paths = test.getPaths()
soft = test.getSoftware()
email = []
if filetype == "pdf" or filetype == "docx":
res = test.getTexts()
if res == "ok":
email = test.getEmails()
for em in email:
emails.append(em)
else:
email = []
failedfiles.append(x + ":" +
str(res))
respack = [
x, users, paths, soft, raw, email
]
all.append(respack)
else:
failedfiles.append(x + ":" + str(res))
print "\t [x] Error in the parsing process" #A error in the parsing process
else:
pass
counter += 1
except socket.error, ex:
print ex
def doprocess(argv):
filelimit = 50
word = "local"
localanalysis = "no"
failedfiles = []
emails = []
if len(sys.argv) < 3:
usage()
try:
opts, args = getopt.getopt(argv, "l:d:f:h:n:t:o:")
except getopt.GetoptError:
usage()
for opt, arg in opts:
if opt == '-d':
word = arg
elif opt == '-t':
filetypes = []
if arg.count(",") != 0:
filetypes = arg.split(",")
else:
filetypes.append(arg)
print filetypes
elif opt == '-l':
limit = int(arg)
elif opt == '-h':
localanalysis = arg
elif opt == '-n':
filelimit = int(arg)
elif opt == '-o':
dir = arg
elif opt == '-f':
outhtml = arg
if os.path.exists(dir):
pass
else:
os.mkdir(dir)
if localanalysis == "no":
print "\n[-] Starting online search..."
for filetype in filetypes:
print "\n[-] Searching for "+ filetype + " files, with a limit of " + str(limit)
search = googlesearch.search_google(word, limit, start, filetype)
search.process_files()
files = search.get_files()
print "Results: " + str(len(files)) + " files found"
print "Starting to download " + str(filelimit) + " of them:"
print "----------------------------------------\n"
counter = 1
for x in files:
if counter <= filelimit:
print "[" + str(counter) + "/" + str(filelimit) + "] " + x
getfile = downloader.downloader(x, dir)
getfile.down()
filename = getfile.name()
if filename != "":
if filetype == "pdf":
test = metadataPDF.metapdf(dir + "/" + filename, password)
elif filetype == "doc" or filetype == "ppt" or filetype == "xls":
test = metadataMSOffice.metaMs2k(dir + "/" + filename)
if os.name == "posix":
testex = metadataExtractor.metaExtractor(dir + "/" + filename)
elif filetype == "docx" or filetype == "pptx" or filetype == "xlsx":
test = metadataMSOfficeXML.metaInfoMS(dir + "/" + filename)
res = test.getData()
if res == "ok":
raw = test.getRaw()
users = test.getUsers()
paths = test.getPaths()
soft = test.getSoftware()
email = []
if filetype == "pdf" or filetype == "docx":
res = test.getTexts()
if res == "ok":
email = test.getEmails()
for em in email:
emails.append(em)
else:
email = []
failedfiles.append(x + ":" + str(res))
respack=[x, users, paths, soft, raw, email]
all.append(respack)
else:
failedfiles.append(x + ":" + str(res))
print "\t [x] Error in the parsing process" #A error in the parsing process
else:
pass
counter += 1
else:
print "[-] Starting local analysis in directory " + dir
dirList = os.listdir(dir)
print dirList
for filename in dirList:
if filename != "":
filetype = str(filename.split(".")[-1])
if filetype == "pdf":
test = metadataPDF.metapdf(dir + "/" + filename, password)
elif filetype == "doc" or filetype == "ppt" or filetype == "xls":
print "doc"
test = metadataMSOffice.metaMs2k(dir + "/" + filename)
if os.name == "posix":
testex = metadataExtractor.metaExtractor(dir + "/" + filename)
elif filetype == "docx" or filetype == "pptx" or filetype == "xlsx":
test = metadataMSOfficeXML.metaInfoMS(dir + "/" + filename)
res = test.getData()
if res == "ok":
raw = test.getRaw()
users = test.getUsers()
paths = test.getPaths()
soft = test.getSoftware()
if (filetype == "doc" or filetype == "xls" or filetype == "ppt") and os.name=="posix":
testex.runExtract()
testex.getData()
paths.extend(testex.getPaths())
respack = [filename, users, paths, soft, raw, email]
all.append(respack)
else:
failedfiles.append(filename + ":" + str(res))
print "[x] Error in the parsing process" # A error in the parsing process
if filetype == "docx" or filetype == "pdf":
res = test.getTexts()
if res == "ok":
email = test.getEmails()
for x in email:
emails.append(x)
else:
failedfiles(filename + ":" + str(res))
else:
print "pass"
else:
pass
print "processing"
proc = processor.processor(all)
userlist = proc.sort_users()
softlist = proc.sort_software()
pathlist = proc.sort_paths()
try:
html = htmlExport.htmlExport(userlist, softlist, pathlist, all, outhtml, dir, failedfiles, word, emails)
save = html.writehtml()
except Exception, e:
print e
print "Error creating the file"
def doprocess(argv):
localanalysis= "no"
if len(sys.argv) < 3:
usage()
try:
opts,args = getopt.getopt(argv,"l:d:f:h:n:t:o:")
except getopt.GetoptError:
usage()
for opt,arg in opts:
if opt == '-d':
word = arg
elif opt == '-t':
filetypes=[]
if arg.count(",") != 0:
filetypes = arg.split(",")
else:
filetypes.append(arg)
print filetypes
elif opt == '-l':
limit = int(arg)
elif opt == '-h':
localanalysis=arg
elif opt == '-n':
filelimit = int(arg)
elif opt == '-o':
dir = arg
elif opt == '-f':
outhtml = arg
if os.path.exists(dir):
pass
else:
os.mkdir(dir)
if localanalysis == "no":
print "[-] Starting online search..."
for filetype in filetypes:
print "\n[-] Searching for "+filetype+ " files, with a limit of " + str(limit)
search=googlesearch.search_google(word,limit,start,filetype)
search.process_files()
files=search.get_files()
print "Results: " + str(len(files)) + " files found"
print "Starting to download "+ str(filelimit) + " of them.."
print "----------------------------------------------------\n"
counter=0
for x in files:
if counter <= filelimit:
print "["+str(counter+1)+"/"+str(filelimit)+"] " + x
getfile=downloader.downloader(x,dir)
getfile.down()
filename=getfile.name()
try:
if filename !="":
if filetype == "pdf":
test=metadataPDF.metapdf(dir+"/"+filename,password)
elif filetype == "doc" or filetype == "ppt" or filetype == "xls":
test=metadataMSOffice.metaMs2k(dir+"/"+filename)
if os.name=="posix":
testex=metadataExtractor.metaExtractor(dir+"/"+filename)
elif filetype == "docx" or filetype == "pptx" or filetype == "xlsx":
test=metadataMSOfficeXML.metaInfoMS(dir+"/"+filename)
res=test.getData()
if res=="ok":
raw=test.getRaw()
users=test.getUsers()
paths=test.getPaths()
soft=test.getSoftware()
if (filetype == "doc" or filetype == "xls" or filetype == "ppt") and os.name=="posix":
testex.runExtract()
testex.getData()
paths.extend(testex.getPaths())
respack=[x,users,paths,soft,raw]
all.append(respack)
else:
print "error" #A error in the parsing process
else:
print "pass"
except Exception, e:
print("ERROR: "+str(e))
counter+=1
