Taevas/Website-Finder
Taevas/Website-Finder
0
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Make use of defaults.json (except C# for now)

Browse source
This commit is contained in:
Taevas 2022-12-12 21:03:40 +01:00
parent a8bda4704a
commit 8656fd134f
6 changed files with 102 additions and 68 deletions
Download patch file Download diff file Expand all files Collapse all files

38
Python/index.py
View file

@ -2,6 +2,7 @@ import sys
import random
import datetime
import requests
import json
from requests.packages.urllib3.exceptions import InsecureRequestWarning
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
@ -16,13 +17,14 @@ def main_loop():
json_object.append('{"website_url":"' + url + '","response_type":"SUCCESS","response_code":"' + str(response.status_code) + '","response_details":"' + str(response.reason) + '"}')
except Exception as e: # Exception should always be ConnectionError (**usually** bad) or ReadTimeout (good)
# Exception handling seems to be a pain because most errors return ConnectionError, so ConnectionError in itself can mean the website exists OR the website does NOT exist
if "not known" not in str(e).lower() and "no address" not in str(e).lower():
err = str(e)
if "not known" not in err.lower() and "no address" not in err.lower():
print(url + " exists!")
err_code = str(e)[str(e).index("[") + 1:str(e).index("]")] if "[" in str(e) and "]" in str(e) else "NO CODE FOUND"
json_object.append('{"website_url":"' + url + '","response_type":"ERROR","response_code":"' + err_code + '","response_details":"' + str(e).replace("\\", "").replace('"', "") + '"}')
err_code = err[err.index("[")+1 : err.index("]")] if "[" in err and "]" in err else "NO CODE FOUND"
json_object.append('{"website_url":"' + url + '","response_type":"ERROR","response_code":"' + err_code + '","response_details":"' + err.replace("\\", "").replace('"', "") + '"}')
f.write(str(json_object).replace("'", "").replace("\\", ""))
f.close()
report_file.write(str(json_object).replace("'", "").replace("\\", ""))
report_file.close()
print("Finished at " + str(datetime.datetime.now().time())[0:5].replace(":", "h") + "m")
def url_generator(num_url, times):
@ -30,23 +32,25 @@ def url_generator(num_url, times):
characters = "abcdefghijklmnopqrstuvwxyz0123456789"
url_length = random.randint(min, max)
result += ''.join(random.choice(characters) for i in range(url_length))
result += domains[random.randint(0, len(domains) - 1)]
if random.randint(1, 100) <= second: result += domains[random.randint(0, len(domains) - 1)]
result += f".{domains[random.randint(0, len(domains) - 1)]}"
if random.randint(1, 100) <= second: result += ".%s"%(domains[random.randint(0, len(domains) - 1)])
if log: print(result + " (" + str(num_url + 1) + "/" + str(times) + ")")
return result
times = int(sys.argv[sys.argv.index('-t') + 1]) if '-t' in sys.argv else 3000
protocols = sys.argv[sys.argv.index('-p') + 1].split(",") if '-p' in sys.argv else ['http']
domains = sys.argv[sys.argv.index('-d') + 1].split(",") if '-d' in sys.argv else ['.co', '.com', '.net', '.edu', '.gov', '.cn', '.org', '.cc', '.us', '.mil', '.ac', '.it', '.de']
second = int(sys.argv[sys.argv.index('-s') + 1]) if '-s' in sys.argv else 1
log = '-l' in sys.argv
defaults = json.load(open("../defaults.json", "rb"))
times = int(sys.argv[sys.argv.index('-t') + 1]) if '-t' in sys.argv else defaults["times"]
protocols = sys.argv[sys.argv.index('-p') + 1].split(",") if '-p' in sys.argv else defaults["protocols"]
domains = sys.argv[sys.argv.index('-d') + 1].split(",") if '-d' in sys.argv else defaults["domains"]
second = int(sys.argv[sys.argv.index('-s') + 1]) if '-s' in sys.argv else defaults["second"]
log = True if '-l' in sys.argv else defaults["log"]
# lmao what if we literally get rid of two built-in functions
min = int(sys.argv[sys.argv.index('-min') + 1]) if '-min' in sys.argv else 2
max = int(sys.argv[sys.argv.index('-max') + 1]) if '-max' in sys.argv else 50 # Python cannot look for URLs longer than 50ish, so be careful!
min = int(sys.argv[sys.argv.index('-min') + 1]) if '-min' in sys.argv else defaults["min"]
max = int(sys.argv[sys.argv.index('-max') + 1]) if '-max' in sys.argv else defaults["max"] # Avoid >50
date = datetime.datetime.now()
print("\nI am going to look for websites through " + str(times) + " random URLs (min length " + str(min) + " and max length " + str(max) + ") with the following domains: " + str(domains))
print("These URLs will use the protocols " + str(protocols) + " and each of those URLs have " + str(second) + " in 100 chance to have a second level domain.")
print("Started at " + str(datetime.datetime.now().time())[0:5].replace(":", "h") + "m\n")
print("These URLs will use the protocols " + str(protocols) + " and each of those URLs have " + str(second) + " in 100 chance to have a second level domain")
print("Started at " + str(date.time())[0:5].replace(":", "h") + "m\n")
f = open("PY_report_" + str(datetime.datetime.now().strftime("%d%H%M")) + ".json", "a+")
report_file = open("PY_report_" + str(date.strftime("%d%H%M")) + ".json", "a+")
main_loop()