A quick python class, to find and identify a favicon for a given URL and calculating the favicon's murmur3 hash, which can be later used for favicon hash matching via services like Shodan

Centauri.py

# 
# This program is a utility used by myself that I have released
# to the public under the GPLv3 license
#
# Copyright (c) 2021 IlluminatiFish.
# 
# This program is free software: you can redistribute it and/or modify  
# it under the terms of the GNU General Public License as published by  
# the Free Software Foundation, version 3.
#
# This program is distributed in the hope that it will be useful, but 
# WITHOUT ANY WARRANTY; without even the implied warranty of 
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License 
# along with this program. If not, see http://www.gnu.org/licenses/.
#


import base64, mmh3, requests
from bs4 import BeautifulSoup

# Guess the refined method didn't work had to adjust and revert to a different method
def index(array, item):
	try:
		index_element = array.index(item)
		return index_element
	except ValueError:
		return -1


class Centauri:

	def __init__(self, url):
		self.url = url
		self.headers = {
			'User-Agent': 'Centauri/0.1-BETA',
			'Accept': '*/*'
		}


	def get_url(self):

		possible_icon_locations = []

		favicon_root_url = 'favicon.ico' if self.url.endswith('/') else '/favicon.ico'
		root = requests.get(self.url + favicon_root_url, headers=self.headers)

		if root.status_code == 200:
			possible_icon_locations.append(self.url + favicon_root_url)
			return possible_icon_locations[0]

		response = requests.get(self.url, headers=self.headers)
		soup = BeautifulSoup(response.text, 'html.parser')

		for link_tag in soup.find_all('link'):
			relational_link_sub_tag = link_tag.get('rel')
			icon_exists = True

			if index(relational_link_sub_tag, 'icon') == -1:
				icon_exists = False

			if not icon_exists:
				continue

			icon_check = relational_link_sub_tag[index(relational_link_sub_tag, 'icon')] == 'icon'

			if 'icon' in relational_link_sub_tag and icon_check:

				href_link_sub_tag = link_tag.get('href')

				if href_link_sub_tag:

					if href_link_sub_tag.startswith('//'):
						location = self.url.split('//')[0] + href_link_sub_tag

					elif href_link_sub_tag.startswith('/'):

						if self.url.endswith('/'):
							location = self.url[:-1] + '/' + href_link_sub_tag.split('/', 1)[1]

						else:
							location = self.url + '/' + href_link_sub_tag.split('/', 1)[1]


					elif '/' in href_link_sub_tag:

						if href_link_sub_tag.startswith('http://') or href_link_sub_tag.startswith('https://'):
							location = href_link_sub_tag

						else:
							if self.url.endswith('/'):
								location = self.url[:-1] + '/' + href_link_sub_tag
							else:
								location = self.url + '/' + href_link_sub_tag

					possible_icon_locations.append(location)

		if len(possible_icon_locations) > 0:
			print('Possible Icons:', possible_icon_locations)
			return list(set(possible_icon_locations))[0]


	def get_hash(self, url):

		if not url:
			return None

		response = requests.get(url, headers=self.headers)
		favicon_b64_bytes = base64.encodebytes(response.content)
		favicon_murmur3_hash = mmh3.hash(favicon_b64_bytes)

		return favicon_murmur3_hash




url = ''

centauri = Centauri(url)
centauri_url = centauri.get_url()

print(centauri_url)

centauri_hash = centauri.get_hash(centauri_url)

print(centauri_hash)

# Amazon: 1941681276
# Facebook: -1321378357
# Twitter: -1831547740
# Microsoft: -2057558656
# Instagram: 1991136554
# Apple: -1498185948
# Paypal: 309020573
# Discord: -11132817