scan.py

# Scans all possible combinations of the variable 'characterList' and then evaluates
# if there is a valid website associated with the domain
from itertools import chain, combinations
import requests


def createLink(iterable):
    s = list(iterable)
    return chain.from_iterable(combinations(s, r) for r in range(len(s)+1))


characterList = 'abcdefghi'
tempLink = list(map(''.join, createLink(characterList)))

logFile = open("log.txt", 'a')


protocol = 'http://'
extension = '.com'
# urls include: protocol (https://, http://, ftp://, smb://, etc.) + domainname (google, golca,
#  bing, etc.) + domain extension (.com, .org, .net, .uk, etc.)

link = [protocol + domain + extension for domain in tempLink]
del link[0]  # deletes the first and blank object in the array
print(link)

linkLength = len(link)
for i in range(linkLength):
    try:
        response = requests.get(link[i])
        print(link[i])
        print("URL is valid and exists on the internet \n")
        iteration = str(i)
        logFile.write("URL " + link[i] + " is valid and responds with a 200 code \n")
        logFile.write("Iteration: " + iteration + ". \n")
    except requests.ConnectionError as exception:
        print("URL does not exist on the Internet")
logFile.close