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

Cleaned stuff & Added flexibility + second level domains

Browse source
This commit is contained in:
isterix 2020-07-24 01:37:47 +02:00
parent c509637865
commit 451cc10561
4 changed files with 52 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

29
Python/index.py
View file

@ -6,7 +6,7 @@ import urllib.request
def main_loop():
json_object = []
for i in range(times):
url = url_generator(domains, log)
url = url_generator()
try:
response = urllib.request.urlopen(url)
print(url + " exists!")
@ -14,35 +14,34 @@ def main_loop():
except Exception as e:
if "[Errno 11001]" in str(e): continue
print(url + " exists!")
err_code = str(e)[str(e).index("[") + 1:str(e).index("]")] if "[" in str(e) and "]" in str(e) else "NONE FOUND"
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("\\", "") + '"}')
f.write(str(json_object).replace("'", ""))
f.write(str(json_object).replace("'", "").replace("\\", ""))
f.close()
print("Finished at " + str(datetime.datetime.now().time())[0:5].replace(":", "h") + "m")
def url_generator(domains, log):
def url_generator():
result = mode[random.randint(0, len(mode) - 1)] + "://"
characters = "abcdefghijklmnopqrstuvwxyz0123456789"
url_length = random.randint(2, 30)
url_length = random.randint(mini, maxi)
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)]
if log: print(result)
return result
times = sys.argv[sys.argv.index('-t') + 1] if '-t' in sys.argv else 3000
try:
times = int(times)
except:
print("-t argument expected a number!")
sys.exit()
domains = sys.argv[sys.argv.index('-d') + 1] if '-d' in sys.argv else ['.co', '.com', '.net', '.edu', '.gov', '.cn', '.org', '.cc']
times = int(sys.argv[sys.argv.index('-t') + 1]) if '-t' in sys.argv else 3000
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']
mode = sys.argv[sys.argv.index('-m') + 1].split(",") if '-m' in sys.argv else ['http']
log = '-l' in sys.argv
mini = int(sys.argv[sys.argv.index('-MIN') + 1]) if '-MIN' in sys.argv else 2
maxi = 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!
second = int(sys.argv[sys.argv.index('-s') + 1]) if '-s' in sys.argv else 1
print("\nI am going to look for images through " + str(times) + " random URLs with the following domains: " + str(domains))
print("These URLs use the following protocols: " + str(mode))
print("Started at " + str(datetime.datetime.now().time())[0:5].replace(":", "h") + "m")
print("\nI am going to look for websites through " + str(times) + " random URLs (min length " + str(mini) + " and max length " + str(maxi) + ") with the following domains: " + str(domains))
print("These URLs will use the protocols " + str(mode) + " 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")
f = open("PY_report_" + str(datetime.datetime.now().strftime("%d%H%M")) + ".json", "a+")
main_loop()