Last active
December 19, 2018 20:22
-
-
Save jimywork/b4ece478f14910faba05ba44ae735988 to your computer and use it in GitHub Desktop.
Does an analysis of the data and checks if the site was pwned
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 python3 | |
# -*- coding: utf-8 -*- | |
import requests | |
from bs4 import BeautifulSoup | |
import json | |
def pwned(date=2018, limit=999): | |
"""Does an analysis of the data and checks if the site was pwned""" | |
retval = [] | |
headers = { | |
'User-Agent': "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36" | |
} | |
try: | |
request = requests.get('https://breachlevelindex.com/data-breach-database.php?range={}'.format(date), | |
headers=headers, timeout=1) | |
soup = BeautifulSoup(request.text, 'html.parser') | |
for row in soup.findAll('tr', limit=10)[1:]: | |
elements = [element.text.strip() for element in row.findAll('td')] | |
#elements = [column for column in columns if column] | |
if len(elements) != 9: | |
print("") | |
data = { | |
"rank": elements[0], | |
"org": elements[1], | |
"records": elements[2], | |
"date": elements[3], | |
"type": elements[4], | |
"source": elements[5], | |
"location": elements[6], | |
"industry": elements[7], | |
"risk": elements[8] | |
} | |
organization = data['org'] | |
try: | |
data["haveibeenpwned"] = requests.get('https://haveibeenpwned.com/api/v2/breach/{}'.format(organization.lower()),headers=headers, timeout=1).json() | |
except Exception as e: | |
data["haveibeenpwned"] = None | |
retval.append(data) | |
except requests.exceptions.RequestException as error: | |
print("{}".format(error)) | |
return retval | |
if __name__ == '__main__': | |
pwneds = pwned(date=2018, limit=10) | |
for i, pwned in enumerate(pwneds) : | |
if pwned['haveibeenpwned'] != None: | |
print(json.dumps(pwned, indent=4, sort_keys=True)) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment