def scan(self, chunk):
body = chunk.lower()
result = MatchResult()
active_phrases = []
for char in body:
# First advance activated phrases
for phrase in active_phrases:
phrase.advance(char)
if phrase.matched():
result.matched = True
result.category = self.category
phrase_string = ''
for word in phrase.phrase.words:
phrase_string += word + ", "
result.criteria = phrase_string[:-2]
return result
elif not phrase.active():
# Remove from active list
active_phrases.remove(phrase)
# Now activate any inactive phrases that match this character
if char in self.phrase_list:
for phrase in self.phrase_list[char]:
is_active = False
for scan_phrase in active_phrases:
if scan_phrase.phrase == phrase:
is_active = True
if not is_active:
# Add to active phrases
scan_phrase = ScanPhrase(phrase)
scan_phrase.advance(char)
active_phrases.append(scan_phrase)
# No match
return result
def scan(self, chunk):
body = chunk.lower()
result = MatchResult()
active_phrases = []
for char in body:
# First advance activated phrases
for phrase in active_phrases:
phrase.advance(char)
if phrase.matched():
result.matched = True
result.category = self.category
phrase_string = ''
for word in phrase.phrase.words:
phrase_string += word + ", "
result.criteria = phrase_string[:-2]
return result
elif not phrase.active():
# Remove from active list
active_phrases.remove(phrase)
# Now activate any inactive phrases that match this character
if char in self.phrase_list:
for phrase in self.phrase_list[char]:
is_active = False
for scan_phrase in active_phrases:
if scan_phrase.phrase == phrase:
is_active = True
if not is_active:
# Add to active phrases
scan_phrase = ScanPhrase(phrase)
scan_phrase.advance(char)
active_phrases.append(scan_phrase)
# No match
return result
def scan(self, r):
result = MatchResult()
hosts = None
if 'host' in r.enc_req_headers:
hosts = r.enc_req_headers['host']
elif 'host' in r.enc_res_headers:
hosts = r.enc_res_headers['host']
if hosts == None:
# No host in headers
return result
for host in hosts:
req_host_parts = host.split('.')
req_host_parts.reverse()
for banned_host in self.host_list:
banned_host_parts = banned_host.split('.')
banned_host_parts.reverse()
if len(banned_host_parts) > len(req_host_parts):
# req host is not a subdomain of banned host
continue
matched = True
for i in range(0, len(banned_host_parts)):
if banned_host_parts[i] != req_host_parts[i]:
# No match
matched = False
if matched:
result.matched = True
result.category = self.category
result.criteria = host
return result
# No match
return result
def scan(self, r):
result = MatchResult()
hosts = None
if 'host' in r.enc_req_headers:
hosts = r.enc_req_headers['host']
elif 'host' in r.enc_res_headers:
hosts = r.enc_res_headers['host']
if hosts == None:
# No host in headers
return result
for host in hosts:
req_host_parts = host.split('.')
req_host_parts.reverse()
for banned_host in self.host_list:
banned_host_parts = banned_host.split('.')
banned_host_parts.reverse()
if len(banned_host_parts) > len(req_host_parts):
# req host is not a subdomain of banned host
continue
matched = True
for i in range(0, len(banned_host_parts)):
if banned_host_parts[i] != req_host_parts[i]:
# No match
matched = False
if matched:
result.matched = True
result.category = self.category
result.criteria = host
return result
# No match
return result
def scan(self, r):
result = MatchResult()
url = r.enc_req[1]
for banned_url in self.url_list:
if banned_url in url:
result.matched = True
result.category = self.category
result.criteria = banned_url
return result
# No match
return result
def scan(self, r):
result = MatchResult()
url = r.enc_req[1]
for banned_url in self.url_list:
if banned_url in url:
result.matched = True
result.category = self.category
result.criteria = banned_url
return result
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1].lower()
for regex in self.regex_list:
match = re.search(regex, url)
if match != None:
result.matched = True
result.category = self.category
result.criteria = regex
return result
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1].lower()
path = urlparse.urlparse(url).path
parts = os.path.splitext(path)
ext = parts[len(parts) - 1]
if ext in self.extension_list:
result.matched = True
result.category = self.category
result.criteria = ext
return result
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1].lower()
path = urlparse.urlparse(url).path
parts = os.path.splitext(path)
ext = parts[len(parts) - 1]
if ext in self.extension_list:
result.matched = True
result.category = self.category
result.criteria = ext
return result
# No match
return result
def scan(self, response):
result = MatchResult()
if not 'content-type' in response.enc_res_headers:
# No mimetype in response
return result
mime_types = response.enc_res_headers['content-type']
for mime_type in mime_types:
if mime_type.strip() in self.mimetype_list:
result.matched = True
result.category = self.category
result.criteria = mime_type
return result
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1]
vid_id = ''
is_youtube = False
if 'host' in request.enc_req_headers:
for host in request.enc_req_headers['host']:
if 'youtube' in host or 'ytimg' in host:
is_youtube = True
if not is_youtube:
return result
m = re.search('watch\?v=(.){11}', url)
if m != None:
vid_id = url[m.start(0):m.end(0)][-11:]
m = re.search('v/(.){11}', url)
if m != None:
vid_id = url[m.start(0):m.end(0)][-11:]
m = re.search('vi/(.){11}', url)
if m != None:
vid_id = url[m.start(0):m.end(0)][-11:]
if vid_id == '':
# No youtube url present
return result
# Check cache
if vid_id in self.clean_cache:
self.clean_cache[vid_id] += 1
return result
# Get info on youtube video
data = urllib2.urlopen('http://gdata.youtube.com/feeds/api/videos/' +
vid_id + '?v=2&alt=json').read().lower()
for regex in self.regex_list:
match = re.search(regex, data)
if match != None:
result.matched = True
result.category = self.category
result.criteria = regex
return result
# Clean video; add to cache
if len(self.clean_cache) == MAX_CACHE_SIZE:
min_cache_key = min(self.clean_cache, key=self.clean_cache.get)
del self.clean_cache[min_cache_key]
if not vid_id in self.clean_cache:
self.clean_cache[vid_id] = 1
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1]
ext_start = url.find('.')
if ext_start == -1:
# No extension
return result
extension = url[ext_start:]
while ext_start != -1:
extension = extension[ext_start+1:]
ext_start = extension[1:].find('.')
if extension in self.extension_list:
result.matched = True
result.category = self.category
result.criteria = extension
return result
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1]
vid_id = ''
is_youtube=False
if 'host' in request.enc_req_headers:
for host in request.enc_req_headers['host']:
if 'youtube' in host or 'ytimg' in host:
is_youtube=True
if not is_youtube:
return result
m = re.search('watch\?v=(.){11}', url)
if m != None:
vid_id = url[m.start(0):m.end(0)][-11:]
m = re.search('v/(.){11}', url)
if m != None:
vid_id = url[m.start(0):m.end(0)][-11:]
m = re.search('vi/(.){11}', url)
if m != None:
vid_id = url[m.start(0):m.end(0)][-11:]
if vid_id == '':
# No youtube url present
return result
# Check cache
if vid_id in self.clean_cache:
self.clean_cache[vid_id] += 1
return result
# Get info on youtube video
data = urllib2.urlopen('http://gdata.youtube.com/feeds/api/videos/'+vid_id+'?v=2&alt=json').read().lower()
for regex in self.regex_list:
match = re.search(regex, data)
if match != None:
result.matched = True
result.category = self.category
result.criteria = regex
return result
# Clean video; add to cache
if len(self.clean_cache) == MAX_CACHE_SIZE:
min_cache_key = min(self.clean_cache, key=self.clean_cache.get)
del self.clean_cache[min_cache_key]
if not vid_id in self.clean_cache:
self.clean_cache[vid_id] = 1
# No match
return result
def scan(self, r):
result = MatchResult()
hosts = None
if 'host' in r.enc_req_headers:
hosts = r.enc_req_headers['host']
elif 'host' in r.enc_res_headers:
hosts = r.enc_res_headers['host']
if hosts == None:
# No host in headers
return result
for host in hosts:
for allowed_host in self.host_list:
if allowed_host.strip() in host.strip():
result.matched = True
result.category = self.category
result.criteria = host
return result
# No match
return result
def scan(self, chunk):
body = chunk.lower()
result = MatchResult()
phraseCounts = {}
for word in self.wordMap.sorted:
if re.search(word, body):
for phrase in self.wordMap.words[word]:
if not phrase in phraseCounts:
phraseCounts[phrase] = 1
else:
phraseCounts[phrase] += 1
if phraseCounts[phrase] == len(phrase.words):
result.matched = True
result.category = self.category
phrase_string = ''
for word in phrase.words:
phrase_string += word + ', '
result.criteria = phrase_string[:-2]
# No match
return result
def scan(self, chunk):
body = chunk.lower()
result = MatchResult()
phraseCounts = {}
for word in self.wordMap.sorted:
if re.search(word, body):
for phrase in self.wordMap.words[word]:
if not phrase in phraseCounts:
phraseCounts[phrase] = 1
else:
phraseCounts[phrase] += 1
if phraseCounts[phrase] == len(phrase.words):
result.matched = True
result.category = self.category
phrase_string = ''
for word in phrase.words:
phrase_string += word + ', '
result.criteria = phrase_string[:-2]
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1]
headers = None
if len(request.enc_res_headers) > 0:
# This is a respmod
headers = request.enc_res_headers
else:
# This is a reqmod
headers = request.enc_req_headers
for regex in self.regex_list:
for h in headers:
for v in headers:
header_line = h + ': ' + v
match = re.search(regex, url)
if match != None:
result.matched = True
result.category = self.category
result.criteria = regex
return result
# No match
return result
def scan(self, request):
result = MatchResult()
url = request.enc_req[1]
headers = None
if len(request.enc_res_headers) > 0:
# This is a respmod
headers = request.enc_res_headers
else:
# This is a reqmod
headers = request.enc_req_headers
for regex in self.regex_list:
for h in headers:
for v in headers:
header_line = h + ': ' + v
match = re.search(regex, url)
if match != None:
result.matched = True
result.category = self.category
result.criteria = regex
return result
# No match
return result
