Remove Proxy List Support

While doing the restructuring, I am testing in more depth as I change the code. And, I am trying to grok how the proxy options work. Specifically, how the proxy list works. Or, does not work.

There is code in the main function that randomly selects proxies from a list, but it does not actually use the result. This was noticed in #292. It looks like the only place where the proxy list is used is when there is a proxy error during get_response()...in that case a new random proxy is chosen. But, there is no care taken to ensure that we do not get the same proxy that just errored out. It seems like problematic proxies should be blacklisted if there is that type of failure.

Moreover, there is a check earlier in the code that does not allow the proxy list and proxy command line option to be used simultaneously. So, I can see no way that the proxy list has any functionality: if you do define the proxy list, then there is no way to kick off the general request with a proxy.

I also noticed that the recursive get_response() call does not pass its return tuples back up the call chain. The existing code would never get any good from the switchover to an alternate proxy (even if the other problems mentioned above were resolved).

For now, I am removing the support.  This feature may be looked at after the restructuring is done.
pull/350/head
Christopher K. Hoadley 5 years ago
parent 9e8e1a5aa4
commit 6114ca263d

@ -1,89 +0,0 @@
import csv
import requests
import time
from collections import namedtuple
from colorama import Fore, Style
def load_proxies_from_csv(path_to_list):
"""
A function which loads proxies from a .csv file, to a list.
Inputs: path to .csv file which contains proxies, described by fields: 'ip', 'port', 'protocol'.
Outputs: list containing proxies stored in named tuples.
"""
Proxy = namedtuple('Proxy', ['ip', 'port', 'protocol'])
with open(path_to_list, 'r') as csv_file:
csv_reader = csv.DictReader(csv_file)
proxies = [Proxy(line['ip'],line['port'],line['protocol']) for line in csv_reader]
return proxies
def check_proxy(proxy_ip, proxy_port, protocol):
"""
A function which test the proxy by attempting
to make a request to the designated website.
We use 'wikipedia.org' as a test, since we can test the proxy anonymity
by check if the returning 'X-Client-IP' header matches the proxy ip.
"""
full_proxy = f'{protocol}://{proxy_ip}:{proxy_port}'
proxies = {'http': full_proxy, 'https': full_proxy}
try:
r = requests.get('https://www.wikipedia.org',proxies=proxies, timeout=4)
return_proxy = r.headers['X-Client-IP']
if proxy_ip==return_proxy:
return True
else:
return False
except Exception:
return False
def check_proxy_list(proxy_list, max_proxies=None):
"""
A function which takes in one mandatory argument -> a proxy list in
the format returned by the function 'load_proxies_from_csv'.
It also takes an optional argument 'max_proxies', if the user wishes to
cap the number of validated proxies.
Each proxy is tested by the check_proxy function. Since each test is done on
'wikipedia.org', in order to be considerate to Wikipedia servers, we are not using any async modules,
but are sending successive requests each separated by at least 1 sec.
Outputs: list containing proxies stored in named tuples.
"""
print((Style.BRIGHT + Fore.GREEN + "[" +
Fore.YELLOW + "*" +
Fore.GREEN + "] Started checking proxies."))
working_proxies = []
# If the user has limited the number of proxies we need,
# the function will stop when the working_proxies
# loads the max number of requested proxies.
if max_proxies != None:
for proxy in proxy_list:
if len(working_proxies) < max_proxies:
time.sleep(1)
if check_proxy(proxy.ip,proxy.port,proxy.protocol) == True:
working_proxies.append(proxy)
else:
break
else:
for proxy in proxy_list:
time.sleep(1)
if check_proxy(proxy.ip,proxy.port,proxy.protocol) == True:
working_proxies.append(proxy)
if len(working_proxies) > 0:
print((Style.BRIGHT + Fore.GREEN + "[" +
Fore.YELLOW + "*" +
Fore.GREEN + "] Finished checking proxies."))
return working_proxies
else:
raise Exception("Found no working proxies.")

@ -23,15 +23,11 @@ from colorama import Fore, Style, init
from requests_futures.sessions import FuturesSession
from torrequest import TorRequest
from load_proxies import load_proxies_from_csv, check_proxy_list
module_name = "Sherlock: Find Usernames Across Social Networks"
__version__ = "0.10.0"
global proxy_list
proxy_list = []
class SherlockFuturesSession(FuturesSession):
def request(self, method, url, hooks={}, *args, **kwargs):
@ -154,9 +150,8 @@ def print_invalid(social_network, msg, color=True):
print(f"[-] {social_network} {msg}")
def get_response(request_future, error_type, social_network, verbose=False, retry_no=None, color=True):
def get_response(request_future, error_type, social_network, verbose=False, color=True):
global proxy_list
try:
rsp = request_future.result()
@ -164,18 +159,8 @@ def get_response(request_future, error_type, social_network, verbose=False, retr
return rsp, error_type, rsp.elapsed
except requests.exceptions.HTTPError as errh:
print_error(errh, "HTTP Error:", social_network, verbose, color)
# In case our proxy fails, we retry with another proxy.
except requests.exceptions.ProxyError as errp:
if retry_no>0 and len(proxy_list)>0:
#Selecting the new proxy.
new_proxy = random.choice(proxy_list)
new_proxy = f'{new_proxy.protocol}://{new_proxy.ip}:{new_proxy.port}'
print(f'Retrying with {new_proxy}')
request_future.proxy = {'http':new_proxy,'https':new_proxy}
get_response(request_future,error_type, social_network, verbose,retry_no=retry_no-1, color=color)
else:
print_error(errp, "Proxy error:", social_network, verbose, color)
print_error(errp, "Proxy error:", social_network, verbose, color)
except requests.exceptions.ConnectionError as errc:
print_error(errc, "Error Connecting:", social_network, verbose, color)
except requests.exceptions.Timeout as errt:
@ -353,7 +338,6 @@ def sherlock(username, site_data, verbose=False, tor=False, unique_tor=False,
error_type=error_type,
social_network=social_network,
verbose=verbose,
retry_no=3,
color=color)
# Attempt to get request information
@ -495,16 +479,6 @@ def main():
parser.add_argument("--json", "-j", metavar="JSON_FILE",
dest="json_file", default="resources/data.json",
help="Load data from a JSON file or an online, valid, JSON file.")
parser.add_argument("--proxy_list", "-pl", metavar='PROXY_LIST',
action="store", dest="proxy_list", default=None,
help="Make requests over a proxy randomly chosen from a list generated from a .csv file."
)
parser.add_argument("--check_proxies", "-cp", metavar='CHECK_PROXY',
action="store", dest="check_prox", default=None,
help="To be used with the '--proxy_list' parameter. "
"The script will check if the proxies supplied in the .csv file are working and anonymous."
"Put 0 for no limit on successfully checked proxies, or another number to institute a limit."
)
parser.add_argument("--timeout",
action="store", metavar='TIMEOUT',
dest="timeout", type=timeout_check, default=None,
@ -532,40 +506,13 @@ def main():
# Argument check
# TODO regex check on args.proxy
if args.tor and (args.proxy != None or args.proxy_list != None):
raise Exception("Tor and Proxy cannot be set in the meantime.")
# Proxy argument check.
# Does not necessarily need to throw an error,
# since we could join the single proxy with the ones generated from the .csv,
# but it seems unnecessarily complex at this time.
if args.proxy != None and args.proxy_list != None:
raise Exception("A single proxy cannot be used along with proxy list.")
if args.tor and (args.proxy != None):
raise Exception("Tor and Proxy cannot be set at the same time.")
# Make prompts
if args.proxy != None:
print("Using the proxy: " + args.proxy)
global proxy_list
if args.proxy_list != None:
print_info("Loading proxies from", args.proxy_list, not args.color)
proxy_list = load_proxies_from_csv(args.proxy_list)
# Checking if proxies should be checked for anonymity.
if args.check_prox != None and args.proxy_list != None:
try:
limit = int(args.check_prox)
if limit == 0:
proxy_list = check_proxy_list(proxy_list)
elif limit > 0:
proxy_list = check_proxy_list(proxy_list, limit)
else:
raise ValueError
except ValueError:
raise Exception("Parameter --check_proxies/-cp must be a positive integer.")
if args.tor or args.unique_tor:
print("Using Tor to make requests")
print("Warning: some websites might refuse connecting over Tor, so note that using this option might increase connection errors.")
@ -661,14 +608,6 @@ def main():
else:
file = open(username + ".txt", "w", encoding="utf-8")
# We try to ad a random member of the 'proxy_list' var as the proxy of the request.
# If we can't access the list or it is empty, we proceed with args.proxy as the proxy.
try:
random_proxy = random.choice(proxy_list)
proxy = f'{random_proxy.protocol}://{random_proxy.ip}:{random_proxy.port}'
except (NameError, IndexError):
proxy = args.proxy
results = sherlock(username,
site_data,
verbose=args.verbose,

Loading…
Cancel
Save