def parse_status_codes(self, raw_status_codes):
status_codes = []
for status_code in raw_status_codes.split(","):
try:
if "-" in status_code:
status_codes.extend(get_range(status_code))
else:
status_codes.append(int(status_code.strip()))
except ValueError:
print("Invalid status code or status code range: {0}".format(status_code))
exit(1)
return uniq(status_codes)
def parse_status_codes(self, str_):
if not str_:
return []
status_codes = []
for status_code in str_.split(","):
try:
if "-" in status_code:
s, e = status_code.strip().split("-")
status_codes.extend(range(int(s), int(e) + 1))
else:
status_codes.append(int(status_code.strip()))
except ValueError:
print("Invalid status code or status code range: {0}".format(
status_code))
exit(1)
return uniq(status_codes)
def generate(self):
reext = re.compile(EXTENSION_KEY, re.IGNORECASE)
result = []
# Enable to use multiple dictionaries at once
for dict_file in self.dictionary_files:
for line in uniq(dict_file.get_lines()):
# Skip comments
if line.startswith("#"):
continue
if line.startswith("/"):
line = line[1:]
if self._no_extension:
line = line[0] + line[1:].split(".")[0]
# Skip dummy paths
if line == ".":
continue
# Skip if the path contains excluded extensions
if self._exclude_extensions and (any(
("." + extension in line
for extension in self._exclude_extensions))):
continue
# Classic dirsearch wordlist processing (with %EXT% keyword)
if EXTENSION_KEY in line.lower():
for extension in self._extensions:
newline = reext.sub(extension, line)
result.append(newline)
# If forced extensions is used and the path is not a directory ... (terminated by /)
# process line like a forced extension.
elif self._force_extensions and not line.rstrip().endswith(
"/") and "." not in line:
for extension in self._extensions:
result.append(line + "." + extension)
result.append(line)
result.append(line + "/")
# Append line unmodified.
else:
if not self._only_selected or any([
line.endswith("." + extension)
for extension in self.extensions
]):
result.append(line)
# Re-add dictionary with prefixes
result.extend([
pref + path for path in result for pref in self._prefixes
if not path.startswith(pref)
])
# Re-add dictionary with suffixes
result.extend([
path + suff for path in result for suff in self._suffixes
if not path.endswith(("/", suff))
])
if self.lowercase:
self.entries = (entry.lower() for entry in uniq(result))
elif self.uppercase:
self.entries = (entry.upper() for entry in uniq(result))
elif self.capitalization:
self.entries = (entry.capitalize() for entry in uniq(result))
else:
self.entries = tuple(uniq(result))
del result
def __init__(self, script_path):
self.script_path = script_path
self.parse_config()
options = self.parse_arguments()
self.quiet = options.quiet
self.full_url = options.full_url
self.url_list = []
self.raw_file = None
if options.url:
self.url_list = [options.url]
elif options.url_list:
file = self.access_file(options.url_list, "file contains URLs")
self.url_list = list(file.get_lines())
elif options.cidr:
self.url_list = iprange(options.cidr)
elif options.stdin_urls:
self.url_list = sys.stdin.read().splitlines()
if options.raw_file:
self.access_file(options.raw_file, "file with raw request")
self.raw_file = options.raw_file
elif not len(self.url_list):
print("URL target is missing, try using -u <url>")
exit(1)
self.url_list = uniq(self.url_list)
if not options.extensions and not options.no_extension:
print("WARNING: No extension was specified!")
if options.no_extension:
options.extensions = str()
for dict_file in options.wordlist.split(","):
self.access_file(dict_file, "wordlist")
if options.proxy_list:
file = self.access_file(options.proxy_list, "proxylist file")
self.proxylist = file.read().splitlines()
options.request_by_hostname = True
elif options.proxy:
self.proxy = options.proxy
options.request_by_hostname = True
else:
self.proxy = None
if options.replay_proxy:
self.replay_proxy = options.replay_proxy
options.request_by_hostname = True
else:
self.replay_proxy = None
self.headers = {}
if options.header_list:
try:
file = self.access_file(options.header_list, "header list file")
self.headers.update(
HeadersParser(file.read()).headers
)
except Exception as e:
print("Error in headers file: " + str(e))
exit(1)
if options.headers:
try:
self.headers.update(
HeadersParser(options.headers).headers
)
except Exception:
print("Invalid headers")
exit(1)
if options.extensions == "*":
self.extensions = [
"php", "jsp", "asp", "aspx", "do", "action", "cgi",
"pl", "html", "htm", "js", "json", "tar.gz", "bak"
]
elif options.extensions == "banner.txt":
print("A weird extension was provided: 'banner.txt'. Please do not use * as the extension or enclose it in double quotes")
exit(0)
else:
self.extensions = uniq([extension.lstrip(' .') for extension in options.extensions.split(",")])
if options.exclude_extensions:
self.exclude_extensions = uniq(
[exclude_extension.lstrip(' .') for exclude_extension in options.exclude_extensions.split(",")]
)
else:
self.exclude_extensions = []
self.useragent = options.useragent
self.use_random_agents = options.use_random_agents
self.cookie = options.cookie
if options.threads_count < 1:
print("Threads number must be greater than zero")
exit(1)
self.threads_count = options.threads_count
if options.include_status_codes:
self.include_status_codes = self.parse_status_codes(options.include_status_codes)
else:
self.include_status_codes = []
if options.exclude_status_codes:
self.exclude_status_codes = self.parse_status_codes(options.exclude_status_codes)
else:
self.exclude_status_codes = []
if options.recursion_status_codes:
self.recursion_status_codes = self.parse_status_codes(options.recursion_status_codes)
else:
self.recursion_status_codes = []
if options.exclude_sizes:
try:
self.exclude_sizes = uniq([
exclude_size.strip().upper() if exclude_size else None
for exclude_size in options.exclude_sizes.split(",")
])
except ValueError:
self.exclude_sizes = []
else:
self.exclude_sizes = []
if options.exclude_texts:
try:
self.exclude_texts = uniq([
exclude_text.strip() if exclude_text else None
for exclude_text in options.exclude_texts.split(",")
])
except ValueError:
self.exclude_texts = []
else:
self.exclude_texts = []
if options.exclude_regexps:
try:
self.exclude_regexps = uniq([
exclude_regexp.strip() if exclude_regexp else None
for exclude_regexp in options.exclude_regexps.split(",")
])
except ValueError:
self.exclude_regexps = []
else:
self.exclude_regexps = []
if options.exclude_redirects:
try:
self.exclude_redirects = uniq([
exclude_redirect.strip() if exclude_redirect else None
for exclude_redirect in options.exclude_redirects.split(",")
])
except ValueError:
self.exclude_redirects = []
else:
self.exclude_redirects = []
self.prefixes = uniq([prefix.strip() for prefix in options.prefixes.split(",")]) if options.prefixes else []
self.suffixes = uniq([suffix.strip() for suffix in options.suffixes.split(",")]) if options.suffixes else []
if options.wordlist:
self.wordlist = uniq([wordlist.strip() for wordlist in options.wordlist.split(",")])
else:
print("No wordlist was provided, try using -w <wordlist>")
exit(1)
self.lowercase = options.lowercase
self.uppercase = options.uppercase
self.capitalization = options.capitalization
self.force_extensions = options.force_extensions
self.data = options.data
self.exclude_response = options.exclude_response
self.color = options.color
self.delay = options.delay
self.timeout = options.timeout
self.ip = options.ip
self.max_retries = options.max_retries
self.recursive = options.recursive
self.deep_recursive = options.deep_recursive
self.force_recursive = options.force_recursive
self.minimum_response_size = options.minimum_response_size
self.maximum_response_size = options.maximum_response_size
self.no_extension = options.no_extension
self.only_selected = options.only_selected
self.output_file = options.output_file
self.output_format = options.output_format
self.scan_subdirs = []
if options.scan_subdirs:
for subdir in options.scan_subdirs.split(","):
subdir = subdir.strip(" ")
if subdir.startswith("/"):
subdir = subdir[1:]
if not subdir.endswith("/"):
subdir += "/"
self.scan_subdirs.append(subdir)
self.exclude_subdirs = []
if options.exclude_subdirs:
for subdir in options.exclude_subdirs.split(","):
subdir = subdir.strip(" ")
if subdir.startswith("/"):
subdir = subdir[1:]
if not subdir.endswith("/"):
subdir += "/"
self.exclude_subdirs.append(subdir)
if options.skip_on_status:
self.skip_on_status = self.parse_status_codes(options.skip_on_status)
else:
self.skip_on_status = []
if options.auth and options.auth_type and (
options.auth_type not in ["basic", "digest", "bearer", "ntlm"]
):
print("'{0}' is not in available authentication types: basic, digest, bearer, ntlm".format(options.auth_type))
exit(1)
elif options.auth and not options.auth_type:
print("Please select the authentication type with --auth-type")
exit(1)
elif options.auth_type and not options.auth:
print("No authentication credential found")
exit(1)
if len(set(self.extensions).intersection(self.exclude_extensions)):
print("Exclude extension list can not contain any extension that has already in the extension list")
exit(1)
self.auth_type = options.auth_type
self.auth = options.auth
self.redirect = options.follow_redirects
self.httpmethod = options.httpmethod
self.scheme = options.scheme
self.request_by_hostname = options.request_by_hostname
self.exit_on_error = options.exit_on_error
self.maxrate = options.maxrate
self.maxtime = options.maxtime
self.recursion_depth = options.recursion_depth
if self.scheme not in ["http", "https"]:
print("Invalid URI scheme: {0}".format(self.scheme))
exit(1)
if self.output_format and self.output_format not in ["simple", "plain", "json", "xml", "md", "csv", "html"]:
print("Select one of the following output formats: simple, plain, json, xml, md, csv, html")
exit(1)
def generate(self):
reext = re.compile(r"\%ext\%", re.IGNORECASE)
result = []
# Enable to use multiple dictionaries at once
for dict_file in self.dictionary_files:
for line in uniq(dict_file.get_lines(), filt=True):
# Skip comments
if line.startswith("#"):
continue
if line.startswith("/"):
line = line[1:]
if self._no_extension:
line = line[0] + line[1:].split(".")[0]
# Skip dummy paths
if line == ".":
continue
# Skip if the path contains excluded extensions
if self._exclude_extensions and (any([
"." + extension in line
for extension in self._exclude_extensions
])):
continue
# Classic dirsearch wordlist processing (with %EXT% keyword)
if "%ext%" in line.lower():
for extension in self._extensions:
newline = reext.sub(extension, line)
result.append(newline)
# If forced extensions is used and the path is not a directory ... (terminated by /)
# process line like a forced extension.
elif self._force_extensions and not line.rstrip().endswith(
"/") and "." not in line:
for extension in self._extensions:
result.append(line + "." + extension)
result.append(line)
result.append(line + "/")
# Append line unmodified.
else:
if not self._only_selected or any([
line.endswith("." + extension)
for extension in self.extensions
]):
result.append(line)
# Some custom changes
for entry in uniq(result):
entries = [entry]
for pref in self._prefixes:
if not entry.startswith(pref):
entries.append(pref + entry)
for suff in self._suffixes:
if not entry.endswith("/") and not entry.endswith(suff):
entries.append(entry + suff)
if self.lowercase:
self.entries.extend(lowercase(entries))
elif self.uppercase:
self.entries.extend(uppercase(entries))
elif self.capitalization:
self.entries.extend(capitalize(entries))
else:
self.entries.extend(entries)
del result
def __init__(self):
options = self.parse_config(arguments_parser())
self.__dict__.update(options.__dict__)
self.httpmethod = self.httpmethod.upper()
self.url_list = []
if options.url:
self.url_list = [options.url]
elif options.url_list:
file = self.access_file(options.url_list, "file contains URLs")
self.url_list = file.get_lines()
elif options.cidr:
self.url_list = iprange(options.cidr)
elif options.stdin_urls:
self.url_list = sys.stdin.read().splitlines(0)
if options.raw_file:
self.access_file(options.raw_file, "file with raw request")
elif not len(self.url_list):
print("URL target is missing, try using -u <url>")
exit(1)
self.url_list = uniq(self.url_list)
if not options.extensions and not options.no_extension:
print("WARNING: No extension was specified!")
for dict_file in options.wordlist.split(","):
self.access_file(dict_file, "wordlist")
if options.threads_count < 1:
print("Threads number must be greater than zero")
exit(1)
if options.proxy_list:
file = self.access_file(options.proxy_list, "proxylist file")
self.proxylist = file.get_lines()
if self.proxy or self.proxylist or self.replay_proxy:
self.request_by_hostname = True
self.headers = {}
if options.header_list:
try:
file = self.access_file(options.header_list,
"header list file")
self.headers.update(HeadersParser(file.read()).headers)
except Exception as e:
print("Error in headers file: " + str(e))
exit(1)
if options.headers:
try:
self.headers.update(HeadersParser(options.headers).headers)
except Exception:
print("Invalid headers")
exit(1)
if options.extensions == "*":
self.extensions = COMMON_EXTENSIONS
elif options.extensions == "banner.txt":
print(
"A weird extension was provided: 'banner.txt'. Please do not use * as the extension or enclose it in double quotes"
)
exit(0)
if options.no_extension:
self.extensions = ""
self.include_status_codes = self.parse_status_codes(
options.include_status_codes)
self.exclude_status_codes = self.parse_status_codes(
options.exclude_status_codes)
self.recursion_status_codes = self.parse_status_codes(
options.recursion_status_codes)
self.skip_on_status = self.parse_status_codes(options.skip_on_status)
self.prefixes = uniq(
[prefix.strip() for prefix in self.prefixes.split(",")])
self.suffixes = uniq(
[suffix.strip() for suffix in self.suffixes.split(",")])
self.extensions = uniq([
extension.lstrip(' .')
for extension in options.extensions.split(",")
])
self.exclude_extensions = uniq([
exclude_extension.lstrip(' .')
for exclude_extension in options.exclude_extensions.split(",")
])
self.exclude_sizes = uniq([
exclude_size.strip().upper()
for exclude_size in options.exclude_sizes.split(",")
])
self.exclude_texts = uniq([
exclude_text.strip()
for exclude_text in options.exclude_texts.split(",")
])
self.exclude_regexps = uniq([
exclude_regexp.strip()
for exclude_regexp in options.exclude_regexps.split(",")
])
self.exclude_redirects = uniq([
exclude_redirect.strip()
for exclude_redirect in options.exclude_redirects.split(",")
])
self.scan_subdirs = [
subdir.strip().ljust(len(subdir) + 1, "/").lstrip("/")
for subdir in options.scan_subdirs.split(",")
]
self.exclude_subdirs = [
subdir.strip().ljust(len(subdir) + 1, "/").lstrip("/")
for subdir in options.exclude_subdirs.split(",")
]
if not options.wordlist:
print("No wordlist was provided, try using -w <wordlist>")
exit(1)
self.wordlist = uniq(
[wordlist.strip() for wordlist in options.wordlist.split(",")])
if options.auth and not options.auth_type:
print("Please select the authentication type with --auth-type")
exit(1)
elif options.auth_type and not options.auth:
print("No authentication credential found")
exit(1)
elif options.auth and options.auth_type not in AUTHENTICATION_TYPES:
print("'{}' is not in available authentication types: {}".format(
options.auth_type, ", ".join(AUTHENTICATION_TYPES)))
exit(1)
if len(set(self.extensions).intersection(self.exclude_extensions)):
print(
"Exclude extension list can not contain any extension that has already in the extension list"
)
exit(1)
if self.output_format and self.output_format not in list(
OUTPUT_FORMATS):
print("Select one of the following output formats: {}".format(
", ".join(OUTPUT_FORMATS)))
exit(1)
