Last active
December 13, 2015 21:59
-
-
Save tommynyquist/4981623 to your computer and use it in GitHub Desktop.
Example fuzzy Public Suffix List matching
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
def parse(domain, psl): | |
fuzzy_hosts = ('www', 'mobile', 'm') | |
domain_parts = domain.split('.') | |
if domain_parts[0] in fuzzy_hosts: | |
domain_parts = domain_parts[1:] | |
if '.'.join(domain_parts[1:]) in psl: | |
return sorted(['.'.join(domain_parts)] + \ | |
['.'.join([fuzzy_host] + domain_parts) for fuzzy_host in fuzzy_hosts]) | |
else: | |
return sorted([domain]) | |
psl = ['org', 'co.uk'] | |
assert parse('chromium.org', psl) == ['chromium.org', 'm.chromium.org', 'mobile.chromium.org', 'www.chromium.org'] | |
assert parse('m.chromium.org', psl) == ['chromium.org', 'm.chromium.org', 'mobile.chromium.org', 'www.chromium.org'] | |
assert parse('mobile.chromium.org', psl) == ['chromium.org', 'm.chromium.org', 'mobile.chromium.org', 'www.chromium.org'] | |
assert parse('www.chromium.org', psl) == ['chromium.org', 'm.chromium.org', 'mobile.chromium.org', 'www.chromium.org'] | |
assert parse('dev.chromium.org', psl) == ['dev.chromium.org'] | |
assert parse('www.google.co.uk', psl) == ['google.co.uk', 'm.google.co.uk', 'mobile.google.co.uk', 'www.google.co.uk'] | |
assert parse('nothing.google.co.uk', psl) == ['nothing.google.co.uk'] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment