Created
February 19, 2024 20:25
-
-
Save AlexMili/24b5c6a1b85fcc5e83d593c49e721bfe to your computer and use it in GitHub Desktop.
Test all webappanalyzer patterns in Python
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
import glob | |
import re | |
import orjson as json | |
from tqdm import tqdm | |
good_keys: list[str] = [ | |
"cookies", | |
"dom", | |
"dns", | |
"js", | |
"headers", | |
"text", | |
"css", | |
"probe", | |
"robots", | |
"url", | |
"xhr", | |
"meta", | |
"scriptSrc", | |
"scripts", | |
"html", | |
] | |
confidence = re.compile("\\\\;confidence:[0-9]+") | |
def _clean_pattern(pattern: str) -> str: | |
pattern = re.sub(confidence, "", pattern) | |
pattern = pattern.replace("\\;version:\\1", "").replace("\\;version:\\2", "") | |
return pattern | |
def _compile_str(string: str): | |
re.compile(_clean_pattern(string)) | |
def _parse(data: str | list | dict) -> None: | |
if isinstance(data, str) is True: | |
_compile_str(data) | |
elif isinstance(data, list) is True: | |
for item in data: | |
_parse(data[item]) | |
elif isinstance(data, dict): | |
for k in data.keys(): | |
_parse(data[k]) | |
else: | |
pass | |
def test_compile_all_regex(): | |
errors: list[str] = [] | |
data: dict = {} | |
for file in tqdm(glob.glob("technologies/*.json")): | |
with open(file, "r") as fp: | |
tmp = json.loads(fp.read()) | |
data = data | tmp | |
for key in data: | |
for elt in data[key]: | |
if elt in good_keys: | |
try: | |
_compile_str(data[key][elt]) | |
except (TypeError, re.error): | |
errors.append(f"{key} - {elt}") | |
print(errors) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment