darknet-lantern/scripts/uptimechecker.py
2025-02-03 09:02:26 +01:00

190 lines
6.7 KiB
Python

import os,pwd,re
import csv
import requests
import json
import pandas as pd
import glob
#apt install python3-pandas python3-requests python3-socks
def main():
print('[+] ONION UPTIME CHECKER')
# TODO get the instance name and exit if its not there
rootpath='/srv/darknet-lantern/'
urlpath=pwd.getpwuid(os.getuid()).pw_dir+"/.darknet_participant_url"
#print(urlpath)
# check if ~/.darknet_participant_url exists,
# if exists, instance= the content of ~/.darknet_participant_url (which is the url: such as uptime.nowherejez...onion)
isitvalid="n"
while isitvalid != "y":
if os.path.isfile(urlpath):
with open(urlpath) as f:
instance = f.read().rstrip()
# check if the instance URL domain is valid
#print(urlpath,instance)
if IsOnionValid(instance):
print("[+] Instance Name:",instance,IsOnionValid(instance))
isitvalid="y"
else:
print('[-] Invalid instance name in ~/.darknet_participant_url:', instance)
return False
else:
print("[-] Instance path doesn't exist yet, run darknet_exploration.py to set it up" )
return False
#i=input("continue?")
proxies = {
'http': 'socks5h://127.0.0.1:9050',
'https': 'socks5h://127.0.0.1:9050'
}
instancepath=rootpath+'www/participants/'+instance+'/'
csvfiles2check=['verified.csv','unverified.csv','webring-participants.csv']
csvfiles2sortcat=['verified.csv','unverified.csv']
#for csvfile in glob.glob("/srv/darknet-lantern/www/links/*.csv"):
for csvfilename in csvfiles2check:
csvfile = instancepath+csvfilename
print('[+] Reading the CSV File:', csvfile)
df = pd.read_csv(csvfile)
print(df[['Name','URL']])
print('[+] Checking if each .onion link is reachable:')
#for i in range(df.index.stop):
for i in df.index:
print("[+] Editing the uptime score")
#if empty, set to 100
if pd.isnull(df.at[i,"Score"]):
df.at[i,"Score"] = 100
print(i)
#print(df.at[i,"URL"])
url=df.at[i,"URL"]
try:
index1 = url.find("http://")
index2 = url.find("https://")
if index1 == -1 and index2 == -1:
url = "http://"+url
status = requests.get(url,proxies=proxies, timeout=5).status_code
print('[+]',url,status)
if status != 502:
print(url,"✔️")
df.at[i,"Status"]="✔️"
#if uptime <100 do +1 to the value
if df.at[i,"Score"] < 100:
df.at[i,"Score"] = df.at[i,"Score"] + 1
else:
print(url,"")
df.at[i,"Status"]=""
#if uptime >0 do -1 to the value
if df.at[i,"Score"] > 0:
df.at[i,"Score"] = df.at[i,"Score"] - 1
except requests.ConnectionError as e:
#print(e)
print(url,"")
df.at[i,"Status"]=""
#if uptime >0 do -1 to the value
if df.at[i,"Score"] > 0:
df.at[i,"Score"] = df.at[i,"Score"] - 1
except requests.exceptions.ReadTimeout as e:
#print(e)
print(url,"")
df.at[i,"Status"]=""
#if uptime >0 do -1 to the value
if df.at[i,"Score"] > 0:
df.at[i,"Score"] = df.at[i,"Score"] - 1
#sort by category if you are verified/unverified.csv
if csvfilename in csvfiles2sortcat:
df2 = df.sort_values(by=["Category","Name"], ascending=[True,True])
else:
df2 = df.sort_values(by="Score", ascending=False)
df2.to_csv(csvfile, index=False)
#print(df2)
def IsUrlValid(url:str)->bool:
"""
Check if url is valid both dark net end clearnet.
"""
# check if the characters are only [a-zA-Z0-9.:/] with maximum 128 chars max?
# check that it is only http(s)://wordA.wordB or http(s)://WordC.WordB.WordC, (onion or not), clearnet is fine too (double check if those are fine!)
# if OK return True
#if not : return False
pattern = re.compile("^[A-Za-z0-9:/.]+$")
url = str(url)
if url.endswith('.onion'):
return IsOnionValid(url)
else:
if not url.__contains__('.'):
#print("No (DOT) in clearnet url")
return False
if pattern.fullmatch(url) is None:
#print('Url contains invalid chars')
return False
return True
def IsOnionValid(url: str)-> bool:
"""
Checks if the domain(param) is a valid onion domain and return True else False.
"""
# check if the characters are only [a-zA-Z0-9.] with maximum 128 chars max?
# check that it is only url.onion or subdomain.url.onion,
# if OK return True
#if not : return False
try:
pattern = re.compile("^[A-Za-z0-9.]+(\.onion)?$")
url = url.strip().removesuffix('/')
if url.startswith('http://'):
#print('URL starts with http')
# Removes the http://
domain = url.split('/')[2]
if pattern.fullmatch(domain) is not None:
if len(domain.split('.')) > 3:
n_subdomians = len(domain.split('.'))
# Checks if there is more than 1 subdomain. "subdomain.url.onion" only
#print(f"This domain have more than one subdomain. There are {n_subdomians} subdomains")
return False
else:
if len(domain) < 62:
#print("Domain length is less than 62.")
return False
return True
elif pattern.fullmatch(domain) is None:
#print("Domain contains invalid character.")
#print(domain)
return False
else:
#print("Domain not valid")
return False
else:
#TODO : edit the url to make sure it has http:// at the beginning, in case if it's missing? (problem is that it only returns true or false)
#print("URL doesn't start http")
if pattern.fullmatch(url) is not None:
if len(url.split('.')) > 3:
n_subdomians = len(url.split('.'))
# Checks if there is more than 1 subdomain. "subdomain.url.onion" only
#print(f"This domain have more than one subdomain. There are {n_subdomians - 1} subdomains")
return False
else:
if len(url) < 62:
#print("Domain length is less than 62.")
return False
return True
elif pattern.fullmatch(url) is None:
#print("Domain contains invalid character.")
#print(url)
return False
else:
#print("Domain not valid")
return False
except Exception as e:
print(f"Error: {e}")
if __name__ == '__main__':
main()