def __init__(self):
"""
For URL parsing refer to RFC 2396
http://www.ietf.org/rfc/rfc2396.txt
For the url http://a.b.c.d.e.f.g/1.html?param=1#Tag the client will try these possible strings:
a.b.c.d.e.f.g/1.html?param=1#Tag
a.b.c.d.e.f.g/1.html?param=1
a.b.c.d.e.f.g/1.html
a.b.c.d.e.f.g/
c.d.e.f.g/1.html?param=1#Tag
c.d.e.f.g/1.html?param=1
c.d.e.f.g/1.html
c.d.e.f.g/
d.e.f.g/1.html?param=1#Tag
d.e.f.g/1.html?param=1
d.e.f.g/1.html
d.e.f.g/
e.f.g/1.html?param=1#Tag
e.f.g/1.html?param=1
e.f.g/1.html
e.f.g/
f.g/1.html?param=1#Tag
f.g/1.html?param=1
f.g/1.html
f.g/
Refer to http://code.google.com/apis/safebrowsing/ for more details.
"""
self.backend = DbObj().backend
class Google_Blacklist(object):
"""
Google Blacklist class that is used to fetch and prepare hashes to be
stored in the database.
"""
def __init__(self,badware_type="malware"):
"""
The constructor initializes the module.
"""
self.backend = DbObj().backend
self.url = self._get_URL()
badware_dict = {"malware": "M","black": "B"}
self.badware_type = badware_type
if not badware_type in badware_dict:
raise KeyError("Invalid Badware Type")
self.badware_code = badware_dict[badware_type]
self.remove_row_regexp = re.compile("^-\w+")
def _get_URL(self):
return URL
def fetch_data(self):
version = self.backend.get_version(self.badware_type)
st = string.Template(self.url)
if not version:
# Start the version number from the beginning
self.version_number = "1:-1"
else:
self.version_number = version
self.final_url = st.safe_substitute(key = self.backend.api_key,
badware_type = self.badware_type,
version = self.version_number)
self.fetch_url_pointer = urllib2.urlopen(self.final_url)
self.url_hashes_data = self.fetch_url_pointer.readlines()
if self.url_hashes_data == []:
# No data, so no point checking version
# number. This case might be because of
# throttling or no updates available.
return 0
rows_to_delete = {}
rows_to_insert = {}
for url_hash in self.url_hashes_data[1:-1]:
if self.remove_row_regexp.match(url_hash):
rows_to_delete.update({url_hash.strip(): self.badware_code})
else:
cleaned_url_hash = url_hash.strip()
if cleaned_url_hash and cleaned_url_hash != "\n":
rows_to_insert.update({cleaned_url_hash[1:]: self.badware_code})
self.backend.delete_rows(rows_to_delete)
version_number_rx = re.compile("\d\.\d+").search(self.url_hashes_data[0])
new_version_number = ":".join(version_number_rx.group().split("."))
if self.version_number == "1:-1":
self.version_number = new_version_number
self.backend.insert_version_row(self.badware_type, self.version_number)
else:
self.backend.update_version_row(self.badware_type, new_version_number, self.version_number)
self.backend.insert_rows(rows_to_insert)
return 0
def __init__(self, badware_type="malware"):
"""
The constructor initializes the module.
"""
self.backend = DbObj().backend
self.url = self._get_URL()
badware_dict = {"malware": "M", "black": "B"}
self.badware_type = badware_type
if not badware_type in badware_dict:
raise KeyError("Invalid Badware Type")
self.badware_code = badware_dict[badware_type]
self.remove_row_regexp = re.compile("^-\w+")
def __init__(self):
"""
For URL parsing refer to RFC 2396
http://www.ietf.org/rfc/rfc2396.txt
For the url http://a.b.c.d.e.f.g/1.html?param=1#Tag the client will try these possible strings:
a.b.c.d.e.f.g/1.html?param=1#Tag
a.b.c.d.e.f.g/1.html?param=1
a.b.c.d.e.f.g/1.html
a.b.c.d.e.f.g/
c.d.e.f.g/1.html?param=1#Tag
c.d.e.f.g/1.html?param=1
c.d.e.f.g/1.html
c.d.e.f.g/
d.e.f.g/1.html?param=1#Tag
d.e.f.g/1.html?param=1
d.e.f.g/1.html
d.e.f.g/
e.f.g/1.html?param=1#Tag
e.f.g/1.html?param=1
e.f.g/1.html
e.f.g/
f.g/1.html?param=1#Tag
f.g/1.html?param=1
f.g/1.html
f.g/
Refer to http://code.google.com/apis/safebrowsing/ for more details.
"""
self.backend = DbObj().backend
def __init__(self,badware_type="malware"):
"""
The constructor initializes the module.
"""
self.backend = DbObj().backend
self.url = self._get_URL()
badware_dict = {"malware": "M","black": "B"}
self.badware_type = badware_type
if not badware_type in badware_dict:
raise KeyError("Invalid Badware Type")
self.badware_code = badware_dict[badware_type]
self.remove_row_regexp = re.compile("^-\w+")
class Google_Blacklist(object):
"""
Google Blacklist class that is used to fetch and prepare hashes to be
stored in the database.
"""
def __init__(self, badware_type="malware"):
"""
The constructor initializes the module.
"""
self.backend = DbObj().backend
self.url = self._get_URL()
badware_dict = {"malware": "M", "black": "B"}
self.badware_type = badware_type
if not badware_type in badware_dict:
raise KeyError("Invalid Badware Type")
self.badware_code = badware_dict[badware_type]
self.remove_row_regexp = re.compile("^-\w+")
def _get_URL(self):
return URL
def fetch_data(self):
version = self.backend.get_version(self.badware_type)
st = string.Template(self.url)
if not version:
# Start the version number from the beginning
self.version_number = "1:-1"
else:
self.version_number = version
self.final_url = st.safe_substitute(key=self.backend.api_key,
badware_type=self.badware_type,
version=self.version_number)
self.fetch_url_pointer = urllib2.urlopen(self.final_url)
self.url_hashes_data = self.fetch_url_pointer.readlines()
if self.url_hashes_data == []:
# No data, so no point checking version
# number. This case might be because of
# throttling or no updates available.
return 0
rows_to_delete = {}
rows_to_insert = {}
for url_hash in self.url_hashes_data[1:-1]:
if self.remove_row_regexp.match(url_hash):
rows_to_delete.update({url_hash.strip(): self.badware_code})
else:
cleaned_url_hash = url_hash.strip()
if cleaned_url_hash and cleaned_url_hash != "\n":
rows_to_insert.update(
{cleaned_url_hash[1:]: self.badware_code})
self.backend.delete_rows(rows_to_delete)
version_number_rx = re.compile("\d\.\d+").search(
self.url_hashes_data[0])
new_version_number = ":".join(version_number_rx.group().split("."))
if self.version_number == "1:-1":
self.version_number = new_version_number
self.backend.insert_version_row(self.badware_type,
self.version_number)
else:
self.backend.update_version_row(self.badware_type,
new_version_number,
self.version_number)
self.backend.insert_rows(rows_to_insert)
return 0
class Lookup(object):
def __init__(self):
"""
For URL parsing refer to RFC 2396
http://www.ietf.org/rfc/rfc2396.txt
For the url http://a.b.c.d.e.f.g/1.html?param=1#Tag the client will try these possible strings:
a.b.c.d.e.f.g/1.html?param=1#Tag
a.b.c.d.e.f.g/1.html?param=1
a.b.c.d.e.f.g/1.html
a.b.c.d.e.f.g/
c.d.e.f.g/1.html?param=1#Tag
c.d.e.f.g/1.html?param=1
c.d.e.f.g/1.html
c.d.e.f.g/
d.e.f.g/1.html?param=1#Tag
d.e.f.g/1.html?param=1
d.e.f.g/1.html
d.e.f.g/
e.f.g/1.html?param=1#Tag
e.f.g/1.html?param=1
e.f.g/1.html
e.f.g/
f.g/1.html?param=1#Tag
f.g/1.html?param=1
f.g/1.html
f.g/
Refer to http://code.google.com/apis/safebrowsing/ for more details.
"""
self.backend = DbObj().backend
def lookup_by_url(self, url):
"""
Lookup Method by URL.
"""
self.url = url.lower()
# Break URL into components
url_components = url_re.match(self.url).groups()
# Prepare the lookup list as given in the main docstring.
self.lookup_list = set()
hostname = url_components[3]
hostname_comp = hostname.split(".")
if not hostname_comp:
raise AttributeError("Invalid URL.")
for i in xrange(len(hostname_comp) - 1):
filtered_hostname_comp = ".".join(hostname_comp[i:])
self.lookup_list.add(filtered_hostname_comp + "/")
if url_components[4]:
path = url_components[4].split('/')
for j in xrange(len(path) + 1):
filtered_paths = '/'.join(path[:j])
if not '.' in filtered_paths:
self.lookup_list.add(filtered_hostname_comp +
"%s/" % filtered_paths)
self.lookup_list.add(filtered_hostname_comp +
url_components[4])
if url_components[5]:
self.lookup_list.add(filtered_hostname_comp +
''.join(url_components[4:6]))
if url_components[7]:
self.lookup_list.add(filtered_hostname_comp +
''.join(url_components[4:6]) +
url_components[7])
# Prepare the MD5 hash list for lookups.
md5_hash_list = []
for url_comp in self.lookup_list:
md5_hash_list.append(md5(url_comp).hexdigest())
return self.backend.lookup_by_md5(md5_hash_list)
# A helper function. Currently unused
def lookup_by_md5(self, md5_hash):
"""
Lookup by MD5 hash.
"""
return self.backend.lookup_by_md5([
md5_hash,
])
class Lookup(object):
def __init__(self):
"""
For URL parsing refer to RFC 2396
http://www.ietf.org/rfc/rfc2396.txt
For the url http://a.b.c.d.e.f.g/1.html?param=1#Tag the client will try these possible strings:
a.b.c.d.e.f.g/1.html?param=1#Tag
a.b.c.d.e.f.g/1.html?param=1
a.b.c.d.e.f.g/1.html
a.b.c.d.e.f.g/
c.d.e.f.g/1.html?param=1#Tag
c.d.e.f.g/1.html?param=1
c.d.e.f.g/1.html
c.d.e.f.g/
d.e.f.g/1.html?param=1#Tag
d.e.f.g/1.html?param=1
d.e.f.g/1.html
d.e.f.g/
e.f.g/1.html?param=1#Tag
e.f.g/1.html?param=1
e.f.g/1.html
e.f.g/
f.g/1.html?param=1#Tag
f.g/1.html?param=1
f.g/1.html
f.g/
Refer to http://code.google.com/apis/safebrowsing/ for more details.
"""
self.backend = DbObj().backend
def lookup_by_url(self, url):
"""
Lookup Method by URL.
"""
self.url = url.lower()
# Break URL into components
url_components = url_re.match(self.url).groups()
# Prepare the lookup list as given in the main docstring.
self.lookup_list = set()
hostname = url_components[3]
hostname_comp = hostname.split(".")
if not hostname_comp:
raise AttributeError("Invalid URL.")
for i in xrange(len(hostname_comp) - 1):
filtered_hostname_comp = ".".join(hostname_comp[i:])
self.lookup_list.add(filtered_hostname_comp + "/")
if url_components[4]:
path = url_components[4].split('/')
for j in xrange(len(path) + 1):
filtered_paths = '/'.join(path[:j])
if not '.' in filtered_paths:
self.lookup_list.add(filtered_hostname_comp + "%s/" %filtered_paths)
self.lookup_list.add(filtered_hostname_comp + url_components[4])
if url_components[5]:
self.lookup_list.add(filtered_hostname_comp + ''.join(url_components[4:6]))
if url_components[7]:
self.lookup_list.add(filtered_hostname_comp + ''.join(url_components[4:6]) + url_components[7])
# Prepare the MD5 hash list for lookups.
md5_hash_list = []
for url_comp in self.lookup_list:
md5_hash_list.append(md5(url_comp).hexdigest())
return self.backend.lookup_by_md5(md5_hash_list)
# A helper function. Currently unused
def lookup_by_md5(self, md5_hash):
"""
Lookup by MD5 hash.
"""
return self.backend.lookup_by_md5([md5_hash, ])
