def main():
#Attribute the URL about to analyse to this variable:
url = 'http://www.soc.napier.ac.uk/~40009856/CW/'
#Fetched data from the URL is attributed to this variable:
page = webpage_get.wget(url)
#Directory where to download retrieved data is attributed to this variable:
downdir = r'C:\Retrieved_files'
#File containing the known bad files:
badfiles = 'badfiles.txt'
#Get the current working directory to pass it as argument
curr_dir = os.getcwd()
#Dictionary used to create the rainbow to compare the retrieved hashes with
dictionary = 'dictionary.txt'
webpage_getlinks.print_links(page,url) #Call the print_links() function from the webpage_getlinks module
webpage_getdata.print_images(page,url) #Call the print_images() function from the webpage_getdata module
webpage_getdata.print_docs(page,url) #Call the print_docs() function from the webpage_getdata module
webpage_getdata.print_email(page) #Call the print_email() function from the webpage_getdata module
webpage_getdata.print_phones(page,url) #Call the print_phones() function from the webpage_getdata module
webpage_getdata.print_hashes(page,url) #Call the print_hashes() function from the webpage_getdata module
# for Hash in hashes_sorted: dict_crack.dict_attack(Hash)
webpage_getdata.recover_hashes(dictionary) #Call recover_hashes(), which calls the dict_attack() function from the hashes_crack module
# using the contents of the hashes_sorted variable as parameter
webpage_getdata.download_files(downdir) #Call the download_files() function from the webpage_getdata module
forensic_analysis.files_sig(downdir) #Call files_sig() from the forensic_analysis module, which calls the check_sig() function
# from the file_type module
forensic_analysis.badfiles_check(badfiles,downdir,curr_dir) #Call badfiles_check() from the forensic_analysis module, which calls the get_hash() function
# from the file_hash module
forensic_analysis.same_files(downdir) #Call the same_files() function from the forensic_analysis module
def file_get(txt):
'''Finds png, jpeg, .docx and gif files from a webpage'''
fileFound = [] #Creates list to store found files on webpage
web = wget(
txt) #Finds files in webpage, finds jpgs, gifs, bmp, php and docx
image = re.findall(r"\<(img\ssrc.*.jpg)", web)
gif = re.findall(r"\<(img\ssrc.*.gif)", web)
doc = re.findall(r"\<(a\shref.*.docx)", web)
php = re.findall(r"\<(a\shref.*.php)", web)
bmp = re.findall(r"\<(img\ssrc.*.bmp)", web)
fileFound = fileFound + image + gif + doc + php + bmp #Empty lists to hold cleaned items and completed files
lstCleansed = [] #List to hold found files of their html tags
fileList = [] #List to hold cleaned files plus their url
for item in fileFound:
#remove tags, clean output
raw = re.sub(r'img\ssrc="|a\shref="', "", item) #Remove html tags
#append cleaned item to list
lstCleansed.append(raw)
#Add cleaned files to lstCleaned list
#add url to filename with not present, allows for download from web
if "https" not in doc and "http" not in raw: #If file url not present, add the file url, otherwise add found fileurl
complete = txt + "/" + raw
fileList.append(complete)
else:
fileList.append(raw)
return fileList
def main():
# temp testing url argument
sys.argv.append('http://www.napier.ac.uk/Pages/home.aspx')
# Check args
if len(sys.argv) != 2:
print '[-] Usage: webpage_getlinks URL'
return
# Get the web page
page = webpage_get.wget(sys.argv[1])
# Get the links
print_links(page)
def main():
#testing url argument
#Uncomment line below to run this script from python shell
sys.argv.append('http://www.soc.napier.ac.uk/~cs342/CSN08115/cw_webpage/index.html')
#Check args
if len(sys.argv) != 2:
print '[-] Usage: webpage_getlinks working-URL'
return
#Get webpage
page = webpage_get.wget(sys.argv[1])
#Get links
print_links(page)
def hash_get(txt):
'''Find hash within a webpage or file'''
pwd = [] #Create empty list to store hashes
try:
web = wget(txt)
match = re.findall(
r"[a-fA-F\d]{32}",
web) #Find hashes using regex of any word, any number of length 32
except:
match = re.findall(r"[a-fA-F\d]{32}", open(txt, "r").read())
match = set(match) #Remove the duplicates
match = list(match)
pwd = pwd + match
return pwd
def main():
# temp testing url argument
url = r'http://www.napier.ac.uk'
sys.argv.append(url)
# Check args
if len(sys.argv) != 2:
print('[-] Usage: webpage_getlinks URL')
return
# Get the web page
page = webpage_get.wget(sys.argv[1])
# Get the links
print_links(page, url)
def phone_get(txt):
'''Finds phone numbers within a webpage or file'''
phone = [] #Create list to store found phone numbers
try:
p = wget(txt)
match = re.findall(
r"\+44\(\d\)\d{3}\s?\d{3}\s?\d{4}", p
) #Matches phone numbers based on +44(0)123 123 1234 or +44(0)1234567891
except:
match = re.findall(r"\+44\(\d\)\d{3}\s?\d{3}\s?\d{4}",
open(txt, "r").read())
match = set(match) #Removes duplicates
match = list(match)
phone = phone + match
return phone
def main():
#testing url argument
#Comment out line below to run this script from cmd line
sys.argv.append('http://www.soc.napier.ac.uk/~cs342/CSN08115/cw_webpage/index.html')
#Check args
if len(sys.argv) != 2:
print '[-] Usage: getwebinfo working-URL'
return
#Get webpage
page = webpage_get.wget(sys.argv[1])
#Create empty list
file_list = []
#Get info
getinfo(page, file_list)
def main():
#testing url argument
#Uncomment line below to run this script from python shell
#sys.argv.append('http://www.soc.napier.ac.uk/~cs342/CSN08115/cw_webpage/index.html')
#Check args
if len(sys.argv) != 2:
print '[-] Usage: webpage_getfiles working-URL'
return
#Get webpage
page = webpage_get.wget(sys.argv[1])
#Create empty list
file_list = []
#Get links
#Passes file_list into both functions
print_files(page, file_list)
check_file_hash(page, file_list)
def main():
# Checks the amount of arguments provided.
if len(sys.argv) != 3: #if the length is not = to 3 print the message
print('[-] Usage:Scraper.py "URL" "Folder"')
return
dwd_dir = sys.argv[2] #Varible that is taken for the name of the directory
url = sys.argv[1] #Varible that is taken to get the url
page = wget(url) #Varaible used to call wget function to get the page.
print("\n")
print("---------- Getting all the HyperLinks-----------")
print_links(page) #Gets all the links from the webpage
print("\n")
print("---------- Getting all the Images-----------")
print_images(page) #Gets all the Images from the webpage
print("\n")
print("---------- Getting all the Documents-----------")
print_docs(page) #Gets all the Documents from the webpage
print("\n")
print("---------- Getting all the phonemumbers-----------")
print_phonenumbers(page) #Gets all the Phonenumbers from the webpage.
print("\n")
print("---------- Getting all the emails-----------")
print_emails(page) #Gets all the emails from the webpage.
print("\n")
print("---------- Getting all Mailto email-----------")
print_mailto(page) #Gets all the mailto emails from the webpage.
print("\n")
print("---------- Getting and Trying to Crack all Hashes-----------")
print_hashes(
page) #Gets all the hashes and tries to crack them from the webpage.
print("\n")
print(
"---------- Getting and Trying to Download all the Images-----------")
download_images(page, url,
dwd_dir) #Downlaod all the Images from the webpage.
print("\n")
print(
"---------- Getting and Trying to Download all the Documents-----------"
)
download_documents(page, url,
dwd_dir) #Downlaod all the Documents from the webpage.
def main():
#Attribute the URL about to analyse to this variable:
url = 'http://www.soc.napier.ac.uk/~40009856/CW/'
#url = 'http://www.blankwebsite.com/'
#Fetched data from the URL is attributed to this variable:
page = webpage_get.wget(url)
#Directory where to download retrieved data is attributed to this variable:
downdir = r'C:\Retrieved_files'
#Dictionary used to create the rainbow to compare the retrieved hashes with
dictionary = 'dictionary.txt'
print_images(page, url) #Call the print_images() function
print_docs(page, url) #Call the print_docs() function
print_email(page) #Call the print_email() function
print_phones(page, url) #Call the print_phones() function
print_hashes(page, url) #Call the print_hashes() function
recover_hashes(
dictionary
) #Call recover_hashes(), which calls the dict_attack() function from the hashes_crack module
# using the contents of the hashes_sorted variable as parameter
download_files(downdir) #Call download_files() function
