Last active
March 9, 2019 11:44
-
-
Save PaulSec/edaad503e96d970c7650240d95c5486f to your computer and use it in GitHub Desktop.
Python utility for https://findsubdomains.com/
This file contains hidden or 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
import requests | |
import sys | |
from bs4 import BeautifulSoup | |
import json | |
import re | |
def sanitize_data(data): | |
return data.replace('\r\n', '').replace('\n', '').replace(' ', '').replace(' ', '') | |
if len(sys.argv) < 2: | |
print("Usage: python findsubdomains.py <domain>") | |
sys.exit(-1) | |
domain = sys.argv[1] | |
url = "https://findsubdomains.com/subdomains-of/{}".format(domain) | |
req = requests.get(url) | |
########################### | |
#### Statistics part | |
########################### | |
stats = {} | |
for line in req.content.split('\n'): | |
if "window.aggreateInfo['countries']" in line: | |
json_text = re.search(r'window.aggreateInfo\[\'countries\'\]\s\=\s(.+)', line, flags=re.DOTALL | re.MULTILINE).group(1)[:-1] | |
countries = json.loads(json_text) | |
stats['countries'] = countries | |
elif "window.aggreateInfo['ip']" in line: | |
json_text = re.search(r'window.aggreateInfo\[\'ip\'\]\s\=\s(.+)', line, flags=re.DOTALL | re.MULTILINE).group(1)[:-1] | |
ip_addresses = json.loads(json_text) | |
stats['ip_addresses'] = ip_addresses | |
elif "window.aggreateInfo['asblocks']" in line: | |
json_text = re.search(r'window.aggreateInfo\[\'asblocks\'\]\s\=\s(.+)', line, flags=re.DOTALL | re.MULTILINE).group(1)[:-1] | |
asblocks = json.loads(json_text) | |
stats['asblocks'] = asblocks | |
########################### | |
#### Domains enumeration part | |
########################### | |
soup = BeautifulSoup(req.content, 'html.parser') | |
data = [] | |
rows = soup.findAll('tr') | |
for row in rows: | |
tmp_data = {} | |
try: | |
domain = row.find('td')['title'] | |
tds = row.findAll('td') | |
domain = row.find('td')['title'] | |
tds = row.findAll('td') | |
try: | |
ip = tds[1].find('a').text | |
except: | |
ip = '' | |
try: | |
osh = tds[2].find('a').text.replace(' ', '') | |
except: | |
osh = '' | |
try: | |
region = tds[3].find('div', attrs={'class': 'geo-description'}).text | |
except: | |
region = '' | |
try: | |
asn = sanitize_data(tds[4].text) | |
except: | |
asn = '' | |
try: | |
organization = sanitize_data(tds[5].find('div').text) | |
except: | |
organization = '' | |
tmp_data['ip'] = ip | |
tmp_data['osh'] = osh | |
tmp_data['region'] = region | |
tmp_data['asn'] = asn | |
tmp_data['organization'] = organization | |
tmp_data['domain'] = domain | |
data.append(tmp_data) | |
except Exception as err: | |
pass | |
########################### | |
#### Subnets part | |
########################### | |
subnet = soup.find('div', attrs={'class': 'subnets-list-body'}) | |
uls = subnet.findAll('ul', attrs={'class': 'js-subnets-list-branch'}) | |
res = {} | |
for ul in uls: | |
ip = sanitize_data(ul.find('div', attrs={'class': 'ip'}).text) | |
qty = sanitize_data(ul.find('div', attrs={'class': 'qty'}).text) | |
lis = ul.findAll('li', attrs={'class': 'subnets-list-item'}) | |
for li in lis: | |
domain = sanitize_data(li.find('div', attrs={'class': 'js-domain-name'}).text) | |
if ip not in res: | |
res[ip] = {"qty": qty, "domains": []} | |
if domain not in res[ip]['domains']: | |
res[ip]['domains'].append(domain) | |
final_res = {'statistics': stats, 'subnets': res, 'dns': data} | |
print(json.dumps(final_res)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment