Files
ARTEX-chixuweihu/skills/api-recon/scripts/test_user_agent.py
T

125 lines
5.9 KiB
Python

"""Offline regressions: python3 -m unittest discover -s skills/api-recon/scripts."""
import contextlib
import http.server
import importlib.util
import os
from pathlib import Path
import re
import subprocess
import sys
import tempfile
import threading
import unittest
from unittest.mock import patch
SCRIPTS = Path(__file__).resolve().parent
# Keep the offline fixtures independent of the runner's outbound/recording proxy.
DIRECT_ENV = {"no_proxy": "*", "NO_PROXY": "*"}
def load_script(name):
spec = importlib.util.spec_from_file_location(name, SCRIPTS / f"{name}.py")
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
@contextlib.contextmanager
def capture_server():
seen = []
class Handler(http.server.BaseHTTPRequestHandler):
def do_GET(self):
seen.append((self.path, self.headers.get("User-Agent"), self.headers.get("Cookie")))
if self.path == "/start":
self.send_response(302)
self.send_header("Location", "/page")
self.end_headers()
return
self.send_response(200)
self.send_header("Content-Type", "text/html")
self.end_headers()
self.wfile.write(b'<h1>Page</h1><script src="/app.js"></script><form action="/submit"></form>')
def log_message(self, *args):
pass
with http.server.ThreadingHTTPServer(("127.0.0.1", 0), Handler) as server:
thread = threading.Thread(target=server.serve_forever)
thread.start()
try:
yield f"http://127.0.0.1:{server.server_port}", seen
finally:
server.shutdown()
thread.join()
class UserAgentTests(unittest.TestCase):
def assert_identity(self, seen, expected, samples):
self.assertTrue(seen)
if expected == "random":
self.assertIn(seen[0][1], samples)
expected = seen[0][1]
self.assertTrue(all(ua == expected for _, ua, _ in seen), seen)
def test_random_selection_and_explicit_override(self):
go_source = (SCRIPTS.parents[2] / "internal/httpidentity/useragent.go").read_text()
go_pool = tuple(re.findall(r'^\s*"(Mozilla/5\.0 [^"]+)",$', go_source, re.MULTILINE))
self.assertEqual(len(go_pool), 20)
self.assertEqual(len(set(go_pool)), 20)
for name in ("harvest_static", "spider_mpa"):
module = load_script(name)
self.assertEqual(module.USER_AGENTS, go_pool)
for sample in module.USER_AGENTS:
with self.subTest(script=name, sample=sample):
with patch.dict(os.environ, {"ARTEX_HTTP_USER_AGENT": ""}), patch.object(module.secrets, "choice", return_value=sample) as choose:
self.assertEqual(module.user_agent(), sample)
choose.assert_called_once_with(module.USER_AGENTS)
with patch.dict(os.environ, {"ARTEX_HTTP_USER_AGENT": "Configured-UA"}), patch.object(module.secrets, "choice") as choose:
self.assertEqual(module.user_agent(), "Configured-UA")
self.assertEqual(module.user_agent("Override-UA"), "Override-UA")
self.assertEqual(module.user_agent(""), "")
choose.assert_not_called()
def test_fetch_and_redirect(self):
for name in ("harvest_static", "spider_mpa"):
module = load_script(name)
for value, expected in (("", "random"), (" Captured-UA/1.0 ", "Captured-UA/1.0"),
("ok\r\nX-Injected: yes", "random"), ("客户端", "random")):
with self.subTest(script=name, value=value), capture_server() as (base, seen):
with patch.dict(os.environ, {**DIRECT_ENV, "ARTEX_HTTP_USER_AGENT": value}):
if name == "harvest_static":
body, status = module.fetch(base + "/start")
self.assertEqual(status, 200)
else:
body, _ = module.fetch(base + "/start", "session=sample")
self.assertTrue(all(cookie == "session=sample" for _, _, cookie in seen))
self.assertIn("Page", body)
self.assertEqual([path for path, _, _ in seen], ["/start", "/page"])
self.assert_identity(seen, expected, module.USER_AGENTS)
def test_cli_precedence_and_outputs(self):
for name in ("harvest_static", "spider_mpa"):
module = load_script(name)
for env_ua, flags, expected in (("", [], "random"),
("Environment-UA/1.0", [], "Environment-UA/1.0"),
("Environment-UA/1.0", ["--user-agent", "Override-UA/1.0"], "Override-UA/1.0"),
("Environment-UA/1.0", ["--user-agent", ""], None)):
with self.subTest(script=name, flags=flags), capture_server() as (base, seen):
with tempfile.TemporaryDirectory() as outdir:
env = dict(os.environ, **DIRECT_ENV, ARTEX_HTTP_USER_AGENT=env_ua)
command = [sys.executable, str(SCRIPTS / f"{name}.py"), base + "/start", outdir] + flags
if name == "spider_mpa":
command += ["--max", "1", "--delay", "0"]
result = subprocess.run(command, env=env, capture_output=True, text=True, timeout=15)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertGreaterEqual(len(seen), 2)
self.assert_identity(seen, expected, module.USER_AGENTS)
artifact = "api_static.txt" if name == "harvest_static" else "forms.txt"
self.assertTrue((Path(outdir) / artifact).exists())
if __name__ == "__main__":
unittest.main()