def load_suffix_list(cache_dir="./cache"):
cached_psl = cache_single("public-suffix-list.txt", cache_dir=cache_dir)
if os.path.exists(cached_psl):
logging.debug("Using cached Public Suffix List...")
with codecs.open(cached_psl, encoding='utf-8') as psl_file:
suffixes = publicsuffix.PublicSuffixList(psl_file)
content = psl_file.readlines()
else:
# File does not exist, download current list and cache it at given location.
logging.debug("Downloading the Public Suffix List...")
try:
cache_file = publicsuffix.fetch()
except URLError as err:
logging.warning("Unable to download the Public Suffix List...")
logging.debug("{}".format(err))
return None, None
content = cache_file.readlines()
suffixes = publicsuffix.PublicSuffixList(content)
# Cache for later.
write(''.join(content), cached_psl)
return suffixes, content
def __init__(self, queue_name: str, routing_keys: Sequence[str]):
"""Initialize the consumer, including the public suffix list."""
super().__init__(queue_name, routing_keys)
# download the public suffix list (would be good to add caching here)
psl_file = publicsuffix.fetch()
self.public_suffix_list = publicsuffix.PublicSuffixList(psl_file)
def test_empty_list(self):
psl = publicsuffix.PublicSuffixList([])
assert 'com' == psl.get_public_suffix('com')
assert 'com' == psl.get_public_suffix('COM')
assert 'com' == psl.get_public_suffix('.com')
assert 'com' == psl.get_public_suffix('a.example.com')
def test_get_public_suffix_from_list_with_unicode(self):
psl = publicsuffix.PublicSuffixList([u('\u0440\u0444')])
assert u('\u0440\u0444') == psl.get_public_suffix(u('\u0440\u0444'))
assert u('example.\u0440\u0444') == psl.get_public_suffix(u('example.\u0440\u0444'))
assert u('example.\u0440\u0444') == psl.get_public_suffix(u('a.example.\u0440\u0444'))
assert u('example.\u0440\u0444') == psl.get_public_suffix(u('a.a.example.\u0440\u0444'))
def __init__(self, consumer_group: str, source_streams: Sequence[str]):
"""Initialize the consumer, including the public suffix list."""
super().__init__(consumer_group, source_streams)
# download the public suffix list (would be good to add caching here)
psl_file = publicsuffix.fetch()
self.public_suffix_list = publicsuffix.PublicSuffixList(psl_file)
def get_psl():
"""
Gets the Public Suffix List - either new, or cached in the CWD for 24 hours
Returns
-------
PublicSuffixList: An instance of PublicSuffixList loaded with a cached or updated list
"""
def download_psl():
fresh_psl = publicsuffix.fetch()
with open(PublicSuffixListFilename, 'w', encoding='utf-8') as fresh_psl_file:
fresh_psl_file.write(fresh_psl.read())
# Download the psl if necessary
if not PublicSuffixListReadOnly:
if not path.exists(PublicSuffixListFilename):
download_psl()
else:
psl_age = datetime.now() - datetime.fromtimestamp(stat(PublicSuffixListFilename).st_mtime)
if psl_age > timedelta(hours=24):
download_psl()
with open(PublicSuffixListFilename, encoding='utf-8') as psl_file:
psl = publicsuffix.PublicSuffixList(psl_file)
return psl
def test_basic(self):
psl = publicsuffix.PublicSuffixList(['com'])
assert 'example.com' == psl.get_public_suffix('a.example.com')
assert 'example.com' == psl.get_public_suffix('a.a.example.com')
assert 'example.com' == psl.get_public_suffix('a.a.a.example.com')
assert 'example.com' == psl.get_public_suffix('A.example.com')
assert 'example.com' == psl.get_public_suffix('.a.a.example.com')
def trunc_tracker(rawtracker):
urlres = urlparse(rawtracker)
urlinfo = (urlres.netloc.split(":"))
if urlinfo[0] == '':
return 'NONE'
else:
domainret = publicsuffix.PublicSuffixList().get_public_suffix(urlinfo[0])
log.debug('trunc_tracker returning domain name {} from string {}'.format(domainret,rawtracker))
return domainret
def test_get_public_suffix_from_list_with_exception_rule(self):
psl = publicsuffix.PublicSuffixList(['*.example.com', '!b.example.com'])
assert 'a.example.com' == psl.get_public_suffix('a.example.com')
assert 'a.a.example.com' == psl.get_public_suffix('a.a.example.com')
assert 'a.a.example.com' == psl.get_public_suffix('a.a.a.example.com')
assert 'a.a.example.com' == psl.get_public_suffix('a.a.a.a.example.com')
assert 'b.example.com' == psl.get_public_suffix('b.example.com')
assert 'b.example.com' == psl.get_public_suffix('b.b.example.com')
assert 'b.example.com' == psl.get_public_suffix('b.b.b.example.com')
assert 'b.example.com' == psl.get_public_suffix('b.b.b.b.example.com')
def get_base_domain(domain):
"""
Gets the base domain name for the given domain
.. note::
Results are based on a list of public domain suffixes at
https://publicsuffix.org/list/public_suffix_list.dat.
This file is saved to the current working directory,
where it is used as a cache file for 24 hours.
Args:
domain (str): A domain or subdomain
Returns:
str: The base domain of the given domain
"""
psl_path = ".public_suffix_list.dat"
def download_psl():
url = "https://publicsuffix.org/list/public_suffix_list.dat"
# Use a browser-like user agent string to bypass some proxy blocks
headers = {"User-Agent": USER_AGENT}
fresh_psl = requests.get(url, headers=headers).text
with open(psl_path, "w", encoding="utf-8") as fresh_psl_file:
fresh_psl_file.write(fresh_psl)
if not os.path.exists(psl_path):
download_psl()
else:
psl_age = datetime.now() - datetime.fromtimestamp(
os.stat(psl_path).st_mtime)
if psl_age > timedelta(hours=24):
try:
download_psl()
except Exception as error:
logger.warning(
"Failed to download an updated PSL {0}".format(error))
with open(psl_path, encoding="utf-8") as psl_file:
psl = publicsuffix.PublicSuffixList(psl_file)
return psl.get_public_suffix(domain)
def domain_from_host(host):
'''Return the domain part of a host.
@type host: string
@param host: the host to extract the domain from
@rtype: string
@return: the extracted domain
'''
if publicsuffix:
global publicsuffixlist
if publicsuffixlist is None:
publicsuffixlist = publicsuffix.PublicSuffixList()
domain = publicsuffixlist.get_public_suffix(host)
else:
d = host.split('.')
if len(d) > 1:
domain = '%s.%s' % (d[-2], d[-1])
else:
domain = host
return domain
def __init__(self):
self.psl = publicsuffix.PublicSuffixList()
def test_fetch_amd_get_public_suffix(self):
f = publicsuffix.fetch()
psl = publicsuffix.PublicSuffixList(f)
assert 'example.com' == psl.get_public_suffix('www.example.com')
assert u('www.\u9999\u6e2f') == psl.get_public_suffix(u('www.\u9999\u6e2f'))
def test_fqdn(self):
psl = publicsuffix.PublicSuffixList(['com'])
assert 'example.com' == psl.get_public_suffix('example.com.')
import sqlite3
import re
import urlparse
import publicsuffix
if (len(sys.argv) != 2 or not os.path.isfile(sys.argv[1])):
print "Usage: python make_pages_public_suffixes.py FOURTHPARTY_DB"
sys.exit()
dbFileName = sys.argv[1]
dbConnection = sqlite3.connect(dbFileName)
dbConnection.row_factory = sqlite3.Row
dbCursor = dbConnection.cursor()
ipRegex = re.compile(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}")
psl = publicsuffix.PublicSuffixList()
dbCursor.execute("ALTER TABLE pages ADD public_suffix TEXT")
dbCursor.execute("SELECT id, location FROM pages")
pagesRows = dbCursor.fetchall()
for pagesRow in pagesRows:
pageID = pagesRow['id']
pageURL = pagesRow['location']
pageHostName = urlparse.urlparse(pageURL).hostname
if pageHostName:
if ipRegex.match(pageHostName):
pagePublicSuffix = pageHostName
else:
pagePublicSuffix = psl.get_public_suffix(pageHostName)
dbCursor.execute("UPDATE pages SET public_suffix=? WHERE id=?",
(pagePublicSuffix, pageID))
def url_public_suffix(self):
global _psl
if _psl is None:
_psl = publicsuffix.PublicSuffixList()
return _psl.get_public_suffix(self.url_domain)
def test_with_full_publicsuffix_org_list(self):
psl = publicsuffix.PublicSuffixList()
# Mixed case.
assert 'com' == psl.get_public_suffix('COM')
assert 'example.com' == psl.get_public_suffix('example.COM')
assert 'example.com' == psl.get_public_suffix('WwW.example.COM')
# Leading dot.
assert 'com' == psl.get_public_suffix('.com')
assert 'example' == psl.get_public_suffix('.example')
assert 'example.com' == psl.get_public_suffix('.example.com')
assert 'example' == psl.get_public_suffix('.example.example')
# Unlisted TLD.
assert 'example' == psl.get_public_suffix('example')
assert 'example' == psl.get_public_suffix('example.example')
assert 'example' == psl.get_public_suffix('b.example.example')
assert 'example' == psl.get_public_suffix('a.b.example.example')
# Listed, but non-Internet, TLD.
assert 'local' == psl.get_public_suffix('local')
assert 'local' == psl.get_public_suffix('example.local')
assert 'local' == psl.get_public_suffix('b.example.local')
assert 'local' == psl.get_public_suffix('a.b.example.local')
# TLD with only one rule.
assert 'biz' == psl.get_public_suffix('biz')
assert 'domain.biz' == psl.get_public_suffix('domain.biz')
assert 'domain.biz' == psl.get_public_suffix('b.domain.biz')
assert 'domain.biz' == psl.get_public_suffix('a.b.domain.biz')
# TLD with some two-level rules.
assert 'com' == psl.get_public_suffix('com')
assert 'example.com' == psl.get_public_suffix('example.com')
assert 'example.com' == psl.get_public_suffix('b.example.com')
assert 'example.com' == psl.get_public_suffix('a.b.example.com')
assert 'uk.com' == psl.get_public_suffix('uk.com')
assert 'example.uk.com' == psl.get_public_suffix('example.uk.com')
assert 'example.uk.com' == psl.get_public_suffix('b.example.uk.com')
assert 'example.uk.com' == psl.get_public_suffix('a.b.example.uk.com')
assert 'test.ac' == psl.get_public_suffix('test.ac')
# TLD with only one wildcard rule.
assert 'cy' == psl.get_public_suffix('cy')
assert 'c.cy' == psl.get_public_suffix('c.cy')
assert 'b.c.cy' == psl.get_public_suffix('b.c.cy')
assert 'b.c.cy' == psl.get_public_suffix('a.b.c.cy')
# More complex TLD.
assert 'jp' == psl.get_public_suffix('jp')
assert 'test.jp' == psl.get_public_suffix('test.jp')
assert 'test.jp' == psl.get_public_suffix('www.test.jp')
assert 'ac.jp' == psl.get_public_suffix('ac.jp')
assert 'test.ac.jp' == psl.get_public_suffix('test.ac.jp')
assert 'test.ac.jp' == psl.get_public_suffix('www.test.ac.jp')
assert 'kobe.jp' == psl.get_public_suffix('kobe.jp')
assert 'c.kobe.jp' == psl.get_public_suffix('c.kobe.jp')
assert 'b.c.kobe.jp' == psl.get_public_suffix('b.c.kobe.jp')
assert 'b.c.kobe.jp' == psl.get_public_suffix('a.b.c.kobe.jp')
# Exception rule.
assert 'city.kobe.jp' == psl.get_public_suffix('city.kobe.jp')
assert 'city.kobe.jp' == psl.get_public_suffix('www.city.kobe.jp')
# US K12.
assert 'us' == psl.get_public_suffix('us')
assert 'test.us' == psl.get_public_suffix('test.us')
assert 'test.us' == psl.get_public_suffix('www.test.us')
assert 'ak.us' == psl.get_public_suffix('ak.us')
assert 'test.ak.us' == psl.get_public_suffix('test.ak.us')
assert 'test.ak.us' == psl.get_public_suffix('www.test.ak.us')
assert 'k12.ak.us' == psl.get_public_suffix('k12.ak.us')
assert 'test.k12.ak.us' == psl.get_public_suffix('test.k12.ak.us')
assert 'test.k12.ak.us' == psl.get_public_suffix('www.test.k12.ak.us')
