Created
December 4, 2020 20:59
-
-
Save whiler/0499baab5db78eb70286fcc4200f4b1a to your computer and use it in GitHub Desktop.
get domains from adblock rules in Python
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 ipaddress | |
import re | |
HEAD = re.compile('^(\|\|?)?(https?://)?') | |
TAIL = re.compile('(/.*$)|(%2f.*$)|(%2F.*$)') | |
DOMAIN = re.compile('(\w[-\w]*(\.\w[-\w]*)+)') | |
WILDCARD = re.compile('^((\w*\*[-\w]*)?(\.))?(\w[-\w]*(\.\w[-\w]*)+)(\*)?') | |
def isip(s): | |
try: | |
ipaddress.ip_address(s) | |
except ValueError: | |
return False | |
return True | |
def adblockfilter(line): | |
line = line.strip() | |
if not line or line[0] in '![@': | |
return False | |
elif '/' == line[0] and '/' == line[-1]: | |
return False | |
return True | |
def adblock2domains(content): | |
it = filter(lambda domain: not isip(domain), | |
map(lambda line: WILDCARD.search(line)[4], | |
filter(DOMAIN.search, | |
map(lambda line: TAIL.sub('', line), | |
map(lambda line: HEAD.sub('', line), | |
filter(adblockfilter, | |
content.splitlines())))))) | |
return set(it) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment