def tor_web_crawler(index, link, ip_address):
"""
This function is a web crawler for collection of traffic traces and saving those traces to pcap files.
:param index: current trace of the link
:param link: webpage address from where traffic is to be collected
:param ip_address: ip-addres of the machine from which traffic is to be collected
:param timeout: duration upto which traffic information needs to be collected
:param pkt_count: number of packets to be collected for a particular trace
:return:
"""
# Extracting domain name for saving trace separately
url = link
lnk = tldextract.extract(url)
domain_name = lnk.domain + '.' + lnk.suffix
# print('Processing trace for domain name crawl : ', domain_name)
# interface = 'enp0s31f6'
# interface = 'any'
interface = 'eth0'
cap = DesiredCapabilities().FIREFOX
cap["marionette"] = True # optional
# driver = TorBrowserDriver(TBB_PATH)
try:
driver = TorBrowserDriver(TBB_PATH)
# saving the pcapfiles
PP = PACP_PATH + '/' + domain_name
# saving the screen shots
SS = SCREEN_SHOT + '/' + domain_name
driver.get(url)
except wde as e:
print('Browser crashed:')
print(e)
print('Trying again in 10 seconds ...')
time.sleep(10)
driver = driver
print('Success!\n')
except Exception as e:
raise Exception(e)
if not os.path.isdir(PP):
print('Creating directory for saving capture files (pcap) ...')
os.makedirs(PP)
else:
pass
if not os.path.isdir(SS):
print('Creating directory for saving screenshots ...')
os.makedirs(SS)
else:
pass
# command to be executed for capturing the trace
# command = "sudo tcpdump -i " + str(interface) + " -n host " + str(ip_address) + " -c " + str(pkt_count) + " -w " + PP + "/" + domain_name + "_" + str(index) + ".pcap "
command = "sudo timeout 60 tcpdump -i " + str(
interface) + " -n host " + str(
ip_address) + " -w " + PP + "/" + domain_name + "_" + str(
index) + ".pcap"
print('Capture trace ...')
capture = subprocess.Popen(command, shell=True)
# time.sleep(1)
capture.wait()
print('Traffic trace captured and saved successfully.')
# save the screenshot
driver.save_screenshot(SS + '/' + domain_name + '-' + str(index) + '.png')
print('Screen shot of the webpage saved successfully.')
driver.quit()
#!/usr/bin/env python3
from tbselenium.tbdriver import TorBrowserDriver
import time
from sys import argv, exit
tbpath = "tor-browser_en-US"
if len(argv) == 1:
file = "good-onions.txt"
else:
file = argv[1]
with open(file, "r") as f:
pages = f.read().split("\n")
driver = TorBrowserDriver(tbpath)
driver.set_page_load_timeout(90)
for page in pages:
if len(page) == 0:
continue
try:
driver.load_url("http://{}".format(page))
driver.save_screenshot('shots/{}.png'.format(page))
except Exception as e:
print("Failed", page)
driver.quit()
exit(0)
