Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merge pull request #18 from DedSecInside/dev_1.0 #20

Merged
merged 1 commit into from
Jun 29, 2017
Merged

Merge pull request #18 from DedSecInside/dev_1.0 #20

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 21 additions & 10 deletions modules/getweblinks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,29 +6,40 @@
import bs4

"""Get all onion links from the website"""
def getLinks(soup):
def getLinks(soup,ext):
_soup_instance = bs4.BeautifulSoup
extensions = ['.onion','.onion/']
extensions = []
if ext:
for e in ext:
extensions.append(e)
if isinstance(type(soup), type(_soup_instance)):
websites = []
for link in soup.find_all('a'):
web_link = link.get('href')
if web_link != None:
if 'http' in web_link:
for extension in extensions:
if web_link.endswith(extension):
websites.append(web_link)
if ('http' in web_link or 'https' in web_link):
if ext:
for exten in extensions:
if web_link.endswith(exten):
websites.append(web_link)
else:
websites.append(web_link)
else:
pass
"""Pretty print output as below"""
print ('')
print (bcolors.OKGREEN+'Websites Found - '+bcolors.ENDC+str(len(websites)))
print ('-------------------------------')
for web in websites:
if (urllib.request.urlopen(web).getcode() == 200):
print (web)
else :
print(bcolors.On_Red+web +bcolors.ENDC)
flag=1
try:
urllib.request.urlopen(web)
except urllib.error.HTTPError as e:
if e.code:
print(bcolors.On_Red+web+bcolors.ENDC)
flag=0
if flag:
print(web)
return websites
else:
raise('Method parameter is not of instance bs4.BeautifulSoup')
7 changes: 4 additions & 3 deletions tests/test_getweblinks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,12 +13,13 @@ class getLinksTestCase(unittest.TestCase):

def setUp(self):
self.held, sys.stdout = sys.stdout, StringIO()
self.maxDiff=None

def test_print_links(self):
#data = "\nWebsites Found - 7\n-------------------------------\nhttp://ads.wsrs.net/www/delivery/ck.php?n=MyIP856a6b4\nhttp://ads.wsrs.net/www/delivery/ck.php?n=MyIPbf5d683\nhttp://aff.ironsocket.com/SH7L\nhttp://aff.ironsocket.com/SH7L\nhttp://ads.wsrs.net/www/delivery/ck.php?n=MyIPdb5f512\nhttp://wsrs.net/\nhttp://cmsgear.com/\n"
data = "\n"+bcolors.OKGREEN+"Websites Found - "+bcolors.ENDC+"0\n-------------------------------\n"

getweblinks.getLinks(soup)
data = "\n"+bcolors.OKGREEN+"Websites Found - "+bcolors.ENDC+"1\n-------------------------------\nhttp://cmsgear.com/\n"
ext = ['.com/']
getweblinks.getLinks(soup,ext)
self.assertEqual(sys.stdout.getvalue(),data)


Expand Down
24 changes: 19 additions & 5 deletions torBot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ def header():
print( " / /_/ __ \/ __ \/ /_ ____/_ __/ ")
print( " / __/ / / / /_/ / __ \/ __ \/ / ")
print( " / /_/ /_/ / _, _/ /_/ / /_/ / / ")
print( " \__/\____/_/ |_/_.___/\____/_/ V 0.0.3")
print( " \__/\____/_/ |_/_.___/\____/_/ V 1.0.0")
print(bcolors.FAIL+bcolors.On_Black)
print("#######################################################")
print("# TorBot - A python Tor Crawler #")
Expand All @@ -74,12 +74,26 @@ def header():


def main():
header()
parser = argparse.ArgumentParser()
parser.add_argument("-q","--quiet",action="store_true")
parser.add_argument("-u","--url",help="Specifiy a website link to crawl")
parser.add_argument("-m","--mail",action="store_true", help="Get e-mail addresses from the crawled sites.")
parser.add_argument("-e","--extension",action='append',dest='extension',default=[],help="Specifiy additional website extensions to the list(.com or .org etc)")
args = parser.parse_args()
if args.quiet == 0:
header()
print ("Tor Ip Address :")
link = args.url
ext = 0
ext = args.extension
a = readPage("https://check.torproject.org/",1)
b = readPage("http://torlinkbgs6aabns.onion/")
getMails(b)
getLinks(b)
if link:
b = readPage(link)
else:
b = readPage("http://torlinkbgs6aabns.onion/")
if args.mail:
getMails(b)
getLinks(b,ext)
print ("\n\n")
return 0

Expand Down