Last active
February 29, 2020 09:05
-
-
Save 0xInfection/dff5a57d113c292b2ba7e3348bd91434 to your computer and use it in GitHub Desktop.
Use this script to sort out URLs from the wayback machine. :)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
# | |
# Written by: 0xInfection | |
# Context: https://twitter.com/har1sec/status/1183987309445820416 | |
# Problem: https://gist.github.com/harisec/bff0ac7ad2e90da7e82297d945c63ef1 | |
import optparse, sys | |
from urllib.parse import urlparse | |
narr = [] | |
fina = [] | |
def sameStrings(barr): | |
final_list = [] | |
for num in barr: | |
if num not in final_list: | |
final_list.append(num) | |
return final_list | |
def parseUrl(url='http://yahoo.com/magazine/view.html?keyword=&byto=title'): | |
o = urlparse(url) | |
s='?' | |
for i in o.query.split('&'): | |
if o.query.split('&').index(i) != 0: | |
s += '&' + i.split('=')[0] + '=' | |
else: | |
s += i.split('=')[0] + '=' | |
b = o.netloc + o.path + o.params + s | |
return(b) | |
def main(): | |
lackofart = ''' | |
U R L S O R T E R | |
''' | |
print(lackofart) | |
parser = optparse.OptionParser(usage='python wsort.py -f url_list.txt') | |
parser.add_option('-f', '--file', dest='file_loc', help='Path of text file containing list of URLs.') | |
parser.add_option('-l', '--list', dest='list', action='store_true', default=False, | |
help='List all URLs within the file supplied by user.') | |
parser.add_option('-o', '--output', dest='out', default=False, | |
help='Name of the file where to write output URLs.') | |
options, arg = parser.parse_args() | |
if not options.file_loc: | |
print('[-] You must supply a filename with list of URLs with `python wsort.py -f <filename>`.') | |
quit() | |
arr = open(options.file_loc).read().splitlines() | |
if options.list: | |
print('[+] Input URLs:') | |
for i in arr: | |
print(i) | |
arr = open(options.file_loc).read().splitlines() | |
for m in arr: | |
d = parseUrl(url=m) | |
narr.append(d) | |
ss = sameStrings(narr) | |
for i in ss: | |
for j in range(0, len(arr)): | |
if (i.split('=')[0] in arr[j] and | |
urlparse('http://'+i.split('=')[0]).netloc == urlparse(arr[j]).netloc): | |
fina.append(arr[j]) | |
break | |
print('[+] Sorted list:') | |
for i in fina: | |
print(i) | |
if options.out: | |
# If output directory is mentioned... | |
try: | |
f = open(options.out, 'w+') | |
for i in fina: | |
f.write(i+'\n') | |
f.close() | |
print('[+] URLs written to %s' % options.out) | |
except FileExistsError: | |
print('[-] File already exists.') | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment