mirror of
https://github.com/CloakHQ/CloakBrowser.git
synced 2026-06-23 11:41:46 +02:00
feat: rewrite cloakserve as CDP multiplexer with per-connection fingerprint seeds
Spawns a separate Chrome process per unique fingerprint seed, all behind
a single port (9222). Clients specify seeds and fingerprint params via
query string on the CDP URL:
connect_over_cdp("http://host:9222?fingerprint=12345&timezone=Asia/Tokyo")
Supports all --fingerprint-* flags as query params, geoip=true for
auto timezone/locale from proxy IP, and proxy= for per-process proxies.
- Rewrite bin/cloakserve from 57-line wrapper to aiohttp CDP multiplexer
- Add ChromePool with per-seed process management and port allocation
- Bidirectional WebSocket proxy for CDP traffic
- URL rewriting for /json/version, /json/list, and WS paths
- Rename _build_args -> build_args, _maybe_resolve_geoip -> maybe_resolve_geoip
- Add aiohttp + websockets to serve optional deps
- Dockerfile installs .[serve] extras
- Add 20 unit tests for cloakserve (param parsing, CLI args, URL rewriting)
This commit is contained in:
+1
-1
@@ -20,7 +20,7 @@ WORKDIR /app
|
||||
# Python wrapper
|
||||
COPY pyproject.toml README.md LICENSE BINARY-LICENSE.md CHANGELOG.md ./
|
||||
COPY cloakbrowser/ cloakbrowser/
|
||||
RUN pip install --no-cache-dir .
|
||||
RUN pip install --no-cache-dir ".[serve]"
|
||||
|
||||
# JS wrapper
|
||||
COPY js/ js/
|
||||
|
||||
@@ -754,7 +754,28 @@ services:
|
||||
start_period: 10s
|
||||
```
|
||||
|
||||
Run multiple instances with different fingerprint seeds on different ports — each gets unique canvas noise, client rects, and other browser signals. Pass `--fingerprint=<seed>` in the command (e.g., `cloakserve --fingerprint=12345`).
|
||||
**Per-connection fingerprint seeds** — run multiple browser identities from a single container. Each unique seed spawns a separate Chrome process with its own fingerprint:
|
||||
|
||||
```python
|
||||
# Each seed gets unique canvas noise, client rects, and other browser signals
|
||||
b1 = pw.chromium.connect_over_cdp("http://localhost:9222?fingerprint=11111")
|
||||
b2 = pw.chromium.connect_over_cdp("http://localhost:9222?fingerprint=22222")
|
||||
|
||||
# Full identity control via query params
|
||||
b3 = pw.chromium.connect_over_cdp(
|
||||
"http://localhost:9222?fingerprint=33333"
|
||||
"&timezone=Asia/Tokyo&locale=ja-JP&platform=macos"
|
||||
"&hardware-concurrency=4&device-memory=8"
|
||||
)
|
||||
|
||||
# Auto-detect timezone/locale from proxy exit IP
|
||||
b4 = pw.chromium.connect_over_cdp(
|
||||
"http://localhost:9222?fingerprint=44444"
|
||||
"&proxy=http://proxy:8080&geoip=true"
|
||||
)
|
||||
```
|
||||
|
||||
Supported query params: `fingerprint`, `timezone`, `locale`, `platform`, `platform-version`, `brand`, `brand-version`, `gpu-vendor`, `gpu-renderer`, `hardware-concurrency`, `device-memory`, `screen-width`, `screen-height`, `proxy`, `geoip`. Same seed reuses the same process. No seed = shared default process (backward compatible).
|
||||
|
||||
**Persistent profiles** — mount a volume to keep cookies and sessions across container restarts:
|
||||
|
||||
|
||||
+543
-30
@@ -1,31 +1,51 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Launch stealth Chromium as a CDP server for remote connections.
|
||||
"""CDP multiplexer — per-connection fingerprint seeds for stealth Chromium.
|
||||
|
||||
Spawns a separate Chrome process per unique fingerprint seed, routing CDP
|
||||
connections through a single port. Each seed gets its own browser identity.
|
||||
|
||||
Usage:
|
||||
cloakserve # headless on port 9222
|
||||
cloakserve --headless=false # headed (uses Xvfb in Docker)
|
||||
cloakserve --proxy-server=host:port # with proxy
|
||||
cloakserve # default, backward compat
|
||||
cloakserve --port=9222 # custom port
|
||||
|
||||
Connect from host:
|
||||
playwright.chromium.connect_over_cdp("http://localhost:9222")
|
||||
Client:
|
||||
browser = pw.chromium.connect_over_cdp("http://host:9222?fingerprint=12345")
|
||||
browser = pw.chromium.connect_over_cdp(
|
||||
"http://host:9222?fingerprint=12345&timezone=America/New_York&locale=en-US"
|
||||
)
|
||||
"""
|
||||
import signal
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import random
|
||||
import shutil
|
||||
import socket
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from urllib.parse import parse_qs
|
||||
|
||||
from cloakbrowser.config import get_default_stealth_args
|
||||
import aiohttp
|
||||
from aiohttp import web
|
||||
|
||||
from cloakbrowser.browser import build_args, maybe_resolve_geoip
|
||||
from cloakbrowser.download import ensure_binary
|
||||
|
||||
PORT = 9222
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s %(levelname)s %(message)s",
|
||||
datefmt="%H:%M:%S",
|
||||
)
|
||||
logger = logging.getLogger("cloakserve")
|
||||
|
||||
binary = ensure_binary()
|
||||
|
||||
chrome_args = [
|
||||
binary,
|
||||
f"--remote-debugging-port={PORT}",
|
||||
"--remote-debugging-address=0.0.0.0",
|
||||
# Sane defaults for running Chrome directly (outside Playwright)
|
||||
# Args for running Chrome directly (outside Playwright).
|
||||
# Playwright normally adds its own version of these.
|
||||
BASE_CHROME_ARGS = [
|
||||
"--no-first-run",
|
||||
"--no-default-browser-check",
|
||||
"--disable-dev-shm-usage",
|
||||
@@ -33,24 +53,517 @@ chrome_args = [
|
||||
"--disable-popup-blocking",
|
||||
"--disable-background-networking",
|
||||
"--metrics-recording-only",
|
||||
# GPU blocklist bypass: Chromium blocks WebGL on software GPUs in
|
||||
# Docker/Xvfb. Without this, WebGL vendor/renderer spoofing fails. #58
|
||||
"--ignore-gpu-blocklist",
|
||||
] + get_default_stealth_args() + sys.argv[1:]
|
||||
]
|
||||
|
||||
chrome = subprocess.Popen(chrome_args)
|
||||
|
||||
time.sleep(2)
|
||||
|
||||
print(f"CloakBrowser CDP server ready on port {PORT}", flush=True)
|
||||
BASE_CDP_PORT = 5100
|
||||
|
||||
|
||||
def cleanup(sig, frame):
|
||||
chrome.terminate()
|
||||
sys.exit(0)
|
||||
# ---------------------------------------------------------------------------
|
||||
# ChromeProcess — one running Chrome instance
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@dataclass
|
||||
class ChromeProcess:
|
||||
seed: str
|
||||
process: subprocess.Popen
|
||||
cdp_port: int
|
||||
user_data_dir: str
|
||||
|
||||
|
||||
signal.signal(signal.SIGTERM, cleanup)
|
||||
signal.signal(signal.SIGINT, cleanup)
|
||||
# ---------------------------------------------------------------------------
|
||||
# ChromePool — manages multiple Chrome processes keyed by seed
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
chrome.wait()
|
||||
class ChromePool:
|
||||
def __init__(
|
||||
self,
|
||||
binary: str,
|
||||
global_args: list[str],
|
||||
headless: bool,
|
||||
):
|
||||
self._binary = binary
|
||||
self._global_args = global_args
|
||||
self._headless = headless
|
||||
self._processes: dict[str, ChromeProcess] = {}
|
||||
self._default: ChromeProcess | None = None
|
||||
self._locks: dict[str, asyncio.Lock] = {}
|
||||
self._next_port = BASE_CDP_PORT
|
||||
|
||||
def _get_lock(self, seed: str) -> asyncio.Lock:
|
||||
if seed not in self._locks:
|
||||
self._locks[seed] = asyncio.Lock()
|
||||
return self._locks[seed]
|
||||
|
||||
def _allocate_port(self) -> int:
|
||||
"""Find a free port starting from _next_port."""
|
||||
for _ in range(100):
|
||||
port = self._next_port
|
||||
self._next_port += 1
|
||||
try:
|
||||
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
|
||||
s.bind(("127.0.0.1", port))
|
||||
return port
|
||||
except OSError:
|
||||
continue
|
||||
raise RuntimeError("No free ports available for Chrome CDP")
|
||||
|
||||
async def get_or_launch(
|
||||
self,
|
||||
seed: str | None,
|
||||
extra_args: list[str] | None = None,
|
||||
timezone: str | None = None,
|
||||
locale: str | None = None,
|
||||
proxy: str | None = None,
|
||||
geoip: bool = False,
|
||||
) -> ChromeProcess:
|
||||
"""Get existing or launch new Chrome process for a seed."""
|
||||
# No seed = default shared process
|
||||
if seed is None:
|
||||
seed_key = "__default__"
|
||||
actual_seed = str(random.randint(10000, 99999))
|
||||
else:
|
||||
seed_key = seed
|
||||
actual_seed = seed
|
||||
|
||||
lock = self._get_lock(seed_key)
|
||||
async with lock:
|
||||
# Check if already running (including default fast-path)
|
||||
if seed_key in self._processes:
|
||||
proc = self._processes[seed_key]
|
||||
if proc.process.poll() is None:
|
||||
if any([extra_args, timezone, locale, proxy, geoip]):
|
||||
logger.warning(
|
||||
"Seed %s already running (port %d) — "
|
||||
"ignoring new params (first-launch wins)",
|
||||
seed_key, proc.cdp_port,
|
||||
)
|
||||
return proc
|
||||
# Dead — clean up
|
||||
await self._cleanup_process(seed_key)
|
||||
|
||||
# Resolve geoip if requested
|
||||
if geoip and proxy:
|
||||
timezone, locale = maybe_resolve_geoip(True, proxy, timezone, locale)
|
||||
|
||||
# Build Chrome args via shared logic
|
||||
fp_extra = [f"--fingerprint={actual_seed}"]
|
||||
if extra_args:
|
||||
fp_extra.extend(extra_args)
|
||||
if proxy:
|
||||
fp_extra.append(f"--proxy-server={proxy}")
|
||||
|
||||
chrome_args = build_args(
|
||||
stealth_args=True,
|
||||
extra_args=fp_extra,
|
||||
timezone=timezone,
|
||||
locale=locale,
|
||||
headless=self._headless,
|
||||
)
|
||||
|
||||
# Allocate port and user data dir
|
||||
port = self._allocate_port()
|
||||
user_data_dir = f"/tmp/cloakserve-{seed_key}"
|
||||
os.makedirs(user_data_dir, exist_ok=True)
|
||||
|
||||
full_args = (
|
||||
[self._binary]
|
||||
+ BASE_CHROME_ARGS
|
||||
+ chrome_args
|
||||
+ self._global_args
|
||||
+ [
|
||||
f"--remote-debugging-port={port}",
|
||||
"--remote-debugging-address=127.0.0.1",
|
||||
f"--user-data-dir={user_data_dir}",
|
||||
]
|
||||
)
|
||||
|
||||
logger.info("Launching Chrome (seed=%s, port=%d)", actual_seed, port)
|
||||
process = subprocess.Popen(
|
||||
full_args,
|
||||
stdout=subprocess.DEVNULL,
|
||||
)
|
||||
|
||||
# Wait for CDP to be ready
|
||||
if not await self._wait_for_cdp(port):
|
||||
process.kill()
|
||||
await asyncio.to_thread(process.wait, timeout=5)
|
||||
await asyncio.to_thread(shutil.rmtree, user_data_dir, True)
|
||||
raise web.HTTPBadGateway(
|
||||
text=json.dumps({"error": "Chrome failed to start"}),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
cp = ChromeProcess(
|
||||
seed=actual_seed,
|
||||
process=process,
|
||||
cdp_port=port,
|
||||
user_data_dir=user_data_dir,
|
||||
)
|
||||
self._processes[seed_key] = cp
|
||||
|
||||
if seed is None:
|
||||
self._default = cp
|
||||
|
||||
logger.info("Chrome ready (seed=%s, port=%d, pid=%d)", actual_seed, port, process.pid)
|
||||
return cp
|
||||
|
||||
async def _cleanup_process(self, key: str) -> None:
|
||||
"""Terminate a Chrome process and clean up."""
|
||||
proc = self._processes.pop(key, None)
|
||||
if not proc:
|
||||
return
|
||||
if proc.process.poll() is None:
|
||||
proc.process.terminate()
|
||||
try:
|
||||
await asyncio.to_thread(proc.process.wait, timeout=5)
|
||||
except subprocess.TimeoutExpired:
|
||||
proc.process.kill()
|
||||
# Clean up user data dir (can be slow for large profiles)
|
||||
await asyncio.to_thread(shutil.rmtree, proc.user_data_dir, True)
|
||||
if self._default is proc:
|
||||
self._default = None
|
||||
self._locks.pop(key, None)
|
||||
|
||||
async def shutdown(self) -> None:
|
||||
"""Terminate all Chrome processes."""
|
||||
for key in list(self._processes.keys()):
|
||||
await self._cleanup_process(key)
|
||||
logger.info("All Chrome processes terminated")
|
||||
|
||||
@staticmethod
|
||||
async def _wait_for_cdp(port: int, timeout: float = 10.0) -> bool:
|
||||
"""Poll Chrome's /json/version until ready."""
|
||||
deadline = time.monotonic() + timeout
|
||||
delay = 0.1
|
||||
session = aiohttp.ClientSession(
|
||||
timeout=aiohttp.ClientTimeout(total=1)
|
||||
)
|
||||
try:
|
||||
while time.monotonic() < deadline:
|
||||
try:
|
||||
async with session.get(
|
||||
f"http://127.0.0.1:{port}/json/version"
|
||||
) as resp:
|
||||
if resp.status == 200:
|
||||
return True
|
||||
except Exception:
|
||||
pass
|
||||
await asyncio.sleep(delay)
|
||||
delay = min(delay * 2, 1.0)
|
||||
return False
|
||||
finally:
|
||||
await session.close()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Query param parsing
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Params that need special handling (not simple --fingerprint-{name}= mapping)
|
||||
SPECIAL_PARAMS = {"fingerprint", "proxy", "geoip", "locale", "timezone"}
|
||||
|
||||
|
||||
def parse_connection_params(query_string: str) -> dict:
|
||||
"""Parse query params into connection config."""
|
||||
qs = parse_qs(query_string, keep_blank_values=False)
|
||||
|
||||
result: dict = {
|
||||
"seed": None,
|
||||
"timezone": None,
|
||||
"locale": None,
|
||||
"proxy": None,
|
||||
"geoip": False,
|
||||
"extra_args": [],
|
||||
}
|
||||
|
||||
for key, values in qs.items():
|
||||
val = values[0]
|
||||
if key == "fingerprint":
|
||||
result["seed"] = val
|
||||
elif key == "timezone":
|
||||
result["timezone"] = val
|
||||
elif key == "locale":
|
||||
result["locale"] = val
|
||||
elif key == "proxy":
|
||||
result["proxy"] = val
|
||||
elif key == "geoip":
|
||||
result["geoip"] = val.lower() in ("true", "1", "yes")
|
||||
elif key not in SPECIAL_PARAMS:
|
||||
# Generic fingerprint param: map to --fingerprint-{key}={val}
|
||||
result["extra_args"].append(f"--fingerprint-{key}={val}")
|
||||
|
||||
return result
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# HTTP handlers
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _ws_scheme(request: web.Request) -> str:
|
||||
"""Return 'wss' if client connected via HTTPS (e.g. TLS-terminating proxy), else 'ws'."""
|
||||
proto = request.headers.get("X-Forwarded-Proto", request.scheme)
|
||||
return "wss" if proto == "https" else "ws"
|
||||
|
||||
|
||||
async def handle_root(request: web.Request) -> web.Response:
|
||||
"""Health check / info."""
|
||||
pool: ChromePool = request.app["pool"]
|
||||
alive = sum(1 for p in pool._processes.values() if p.process.poll() is None)
|
||||
return web.json_response({
|
||||
"status": "ok",
|
||||
"processes": alive,
|
||||
})
|
||||
|
||||
|
||||
async def handle_json_version(request: web.Request) -> web.Response:
|
||||
"""Proxy /json/version with optional per-seed routing."""
|
||||
pool: ChromePool = request.app["pool"]
|
||||
params = parse_connection_params(request.query_string)
|
||||
|
||||
cp = await pool.get_or_launch(
|
||||
seed=params["seed"],
|
||||
extra_args=params["extra_args"] or None,
|
||||
timezone=params["timezone"],
|
||||
locale=params["locale"],
|
||||
proxy=params["proxy"],
|
||||
geoip=params["geoip"],
|
||||
)
|
||||
|
||||
try:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(
|
||||
f"http://127.0.0.1:{cp.cdp_port}/json/version",
|
||||
timeout=aiohttp.ClientTimeout(total=5),
|
||||
) as resp:
|
||||
data = await resp.json()
|
||||
except Exception as exc:
|
||||
logger.error("Failed to reach Chrome CDP (port %d): %s", cp.cdp_port, exc)
|
||||
return web.json_response({"error": "CDP endpoint unreachable"}, status=502)
|
||||
|
||||
# Rewrite webSocketDebuggerUrl to route through our multiplexer
|
||||
host = request.headers.get("Host", f"localhost:{request.app['port']}")
|
||||
seed_key = params["seed"]
|
||||
if seed_key:
|
||||
ws_path = f"fingerprint/{seed_key}/devtools/browser"
|
||||
else:
|
||||
ws_path = "devtools/browser"
|
||||
|
||||
# Extract the browser GUID from Chrome's original URL
|
||||
orig_ws = data.get("webSocketDebuggerUrl", "")
|
||||
guid = orig_ws.rsplit("/", 1)[-1] if "/devtools/" in orig_ws else ""
|
||||
|
||||
scheme = _ws_scheme(request)
|
||||
data["webSocketDebuggerUrl"] = f"{scheme}://{host}/{ws_path}/{guid}"
|
||||
return web.json_response(data)
|
||||
|
||||
|
||||
async def handle_json_list(request: web.Request) -> web.Response:
|
||||
"""Proxy /json/list with per-seed routing. Rewrites all entries."""
|
||||
pool: ChromePool = request.app["pool"]
|
||||
params = parse_connection_params(request.query_string)
|
||||
|
||||
cp = await pool.get_or_launch(
|
||||
seed=params["seed"],
|
||||
extra_args=params["extra_args"] or None,
|
||||
timezone=params["timezone"],
|
||||
locale=params["locale"],
|
||||
proxy=params["proxy"],
|
||||
geoip=params["geoip"],
|
||||
)
|
||||
|
||||
try:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.get(
|
||||
f"http://127.0.0.1:{cp.cdp_port}/json/list",
|
||||
timeout=aiohttp.ClientTimeout(total=5),
|
||||
) as resp:
|
||||
data = await resp.json()
|
||||
except Exception as exc:
|
||||
logger.error("Failed to reach Chrome CDP (port %d): %s", cp.cdp_port, exc)
|
||||
return web.json_response({"error": "CDP endpoint unreachable"}, status=502)
|
||||
|
||||
host = request.headers.get("Host", f"localhost:{request.app['port']}")
|
||||
scheme = _ws_scheme(request)
|
||||
seed_key = params["seed"]
|
||||
|
||||
for entry in data:
|
||||
if "webSocketDebuggerUrl" in entry:
|
||||
ws_tail = entry["webSocketDebuggerUrl"].split("/devtools/")[-1]
|
||||
if seed_key:
|
||||
entry["webSocketDebuggerUrl"] = (
|
||||
f"{scheme}://{host}/fingerprint/{seed_key}/devtools/{ws_tail}"
|
||||
)
|
||||
else:
|
||||
entry["webSocketDebuggerUrl"] = f"{scheme}://{host}/devtools/{ws_tail}"
|
||||
|
||||
return web.json_response(data)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# WebSocket proxy
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
async def proxy_cdp_websocket(
|
||||
client_ws: web.WebSocketResponse,
|
||||
target_url: str,
|
||||
label: str,
|
||||
) -> None:
|
||||
"""Bidirectional WebSocket proxy between client and Chrome CDP."""
|
||||
import websockets
|
||||
|
||||
try:
|
||||
async with websockets.connect(
|
||||
target_url, max_size=None, ping_interval=None, ping_timeout=None,
|
||||
) as cdp_ws:
|
||||
logger.info("%s: connected to %s", label, target_url)
|
||||
|
||||
async def client_to_cdp():
|
||||
try:
|
||||
async for msg in client_ws:
|
||||
if msg.type == aiohttp.WSMsgType.TEXT:
|
||||
await cdp_ws.send(msg.data)
|
||||
elif msg.type == aiohttp.WSMsgType.BINARY:
|
||||
await cdp_ws.send(msg.data)
|
||||
elif msg.type in (aiohttp.WSMsgType.CLOSE, aiohttp.WSMsgType.CLOSING, aiohttp.WSMsgType.CLOSED):
|
||||
break
|
||||
except Exception as exc:
|
||||
logger.debug("%s [c->cdp]: %s", label, exc)
|
||||
|
||||
async def cdp_to_client():
|
||||
try:
|
||||
async for msg in cdp_ws:
|
||||
if isinstance(msg, str):
|
||||
await client_ws.send_str(msg)
|
||||
else:
|
||||
await client_ws.send_bytes(msg)
|
||||
except Exception as exc:
|
||||
logger.debug("%s [cdp->c]: %s", label, exc)
|
||||
|
||||
c2d = asyncio.create_task(client_to_cdp(), name="c2d")
|
||||
d2c = asyncio.create_task(cdp_to_client(), name="d2c")
|
||||
done, pending = await asyncio.wait(
|
||||
[c2d, d2c], return_when=asyncio.FIRST_COMPLETED,
|
||||
)
|
||||
for task in pending:
|
||||
task.cancel()
|
||||
logger.info("%s: disconnected", label)
|
||||
|
||||
except Exception as exc:
|
||||
logger.error("%s error: %s", label, exc)
|
||||
|
||||
|
||||
async def handle_ws_default(request: web.Request) -> web.WebSocketResponse:
|
||||
"""WebSocket proxy for default (no-seed) Chrome: /devtools/{type}/{guid}"""
|
||||
pool: ChromePool = request.app["pool"]
|
||||
path = request.match_info.get("path", "")
|
||||
|
||||
cp = await pool.get_or_launch(seed=None)
|
||||
|
||||
ws = web.WebSocketResponse()
|
||||
await ws.prepare(request)
|
||||
|
||||
target_url = f"ws://127.0.0.1:{cp.cdp_port}/devtools/{path}"
|
||||
await proxy_cdp_websocket(ws, target_url, f"CDP default [{path}]")
|
||||
return ws
|
||||
|
||||
|
||||
async def handle_ws_seed(request: web.Request) -> web.WebSocketResponse:
|
||||
"""WebSocket proxy for seed-specific Chrome: /fingerprint/{seed}/devtools/{type}/{guid}"""
|
||||
pool: ChromePool = request.app["pool"]
|
||||
seed = request.match_info["seed"]
|
||||
path = request.match_info.get("path", "")
|
||||
|
||||
cp = await pool.get_or_launch(seed=seed)
|
||||
|
||||
ws = web.WebSocketResponse()
|
||||
await ws.prepare(request)
|
||||
|
||||
target_url = f"ws://127.0.0.1:{cp.cdp_port}/devtools/{path}"
|
||||
await proxy_cdp_websocket(ws, target_url, f"CDP seed={seed} [{path}]")
|
||||
return ws
|
||||
|
||||
|
||||
async def on_shutdown(app: web.Application) -> None:
|
||||
await app["pool"].shutdown()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# CLI arg parsing
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def parse_cli_args(argv: list[str]) -> tuple[dict, list[str]]:
|
||||
"""Parse cloakserve-specific args, return (config, passthrough_args)."""
|
||||
config = {
|
||||
"port": 9222,
|
||||
"headless": True,
|
||||
}
|
||||
passthrough = []
|
||||
# Flags consumed by cloakserve (not passed to Chrome)
|
||||
consumed_prefixes = (
|
||||
"--port=",
|
||||
"--remote-debugging-port=",
|
||||
"--remote-debugging-address=",
|
||||
)
|
||||
|
||||
for arg in argv:
|
||||
if arg.startswith("--port="):
|
||||
config["port"] = int(arg.split("=", 1)[1])
|
||||
elif arg == "--headless=false" or arg == "--headless=False":
|
||||
config["headless"] = False
|
||||
passthrough.append(arg)
|
||||
elif arg.startswith(consumed_prefixes):
|
||||
pass # Strip these silently
|
||||
else:
|
||||
passthrough.append(arg)
|
||||
|
||||
return config, passthrough
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Main
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def main() -> None:
|
||||
binary = ensure_binary()
|
||||
config, global_args = parse_cli_args(sys.argv[1:])
|
||||
|
||||
pool = ChromePool(
|
||||
binary=binary,
|
||||
global_args=global_args,
|
||||
headless=config["headless"],
|
||||
)
|
||||
|
||||
app = web.Application()
|
||||
app["pool"] = pool
|
||||
app["port"] = config["port"]
|
||||
|
||||
# Routes
|
||||
app.router.add_get("/", handle_root)
|
||||
app.router.add_get("/json/version", handle_json_version)
|
||||
app.router.add_get("/json/version/", handle_json_version)
|
||||
app.router.add_get("/json/list", handle_json_list)
|
||||
app.router.add_get("/json/list/", handle_json_list)
|
||||
app.router.add_get("/json", handle_json_list)
|
||||
app.router.add_get("/json/", handle_json_list)
|
||||
|
||||
# WebSocket routes — seed-specific (must be before default to match first)
|
||||
app.router.add_get("/fingerprint/{seed}/devtools/{path:.+}", handle_ws_seed)
|
||||
# WebSocket routes — default (no seed)
|
||||
app.router.add_get("/devtools/{path:.+}", handle_ws_default)
|
||||
|
||||
app.on_shutdown.append(on_shutdown)
|
||||
|
||||
port = config["port"]
|
||||
logger.info("CloakBrowser CDP multiplexer starting on port %d", port)
|
||||
logger.info(
|
||||
"Connect: playwright.chromium.connect_over_cdp("
|
||||
"\"http://localhost:%d?fingerprint=<seed>\")",
|
||||
port,
|
||||
)
|
||||
|
||||
web.run_app(app, host="0.0.0.0", port=port, print=None)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@@ -11,7 +11,7 @@ Usage:
|
||||
browser.close()
|
||||
"""
|
||||
|
||||
from .browser import launch, launch_async, launch_context, launch_persistent_context, launch_persistent_context_async, ProxySettings
|
||||
from .browser import launch, launch_async, launch_context, launch_persistent_context, launch_persistent_context_async, ProxySettings, build_args, maybe_resolve_geoip
|
||||
from .config import CHROMIUM_VERSION, get_default_stealth_args
|
||||
from .download import binary_info, check_for_update, clear_cache, ensure_binary
|
||||
from ._version import __version__
|
||||
@@ -40,6 +40,8 @@ __all__ = [
|
||||
"check_for_update",
|
||||
"CHROMIUM_VERSION",
|
||||
"get_default_stealth_args",
|
||||
"build_args",
|
||||
"maybe_resolve_geoip",
|
||||
"ProxySettings",
|
||||
"HumanConfig",
|
||||
"resolve_human_config",
|
||||
|
||||
+11
-11
@@ -101,8 +101,8 @@ def launch(
|
||||
sync_playwright = _import_sync_playwright(_resolve_backend(backend))
|
||||
|
||||
binary_path = ensure_binary()
|
||||
timezone, locale = _maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = _build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
timezone, locale = maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
|
||||
logger.debug("Launching stealth Chromium (headless=%s, args=%d)", headless, len(chrome_args))
|
||||
|
||||
@@ -186,8 +186,8 @@ async def launch_async( # noqa: C901
|
||||
async_playwright = _import_async_playwright(_resolve_backend(backend))
|
||||
|
||||
binary_path = ensure_binary()
|
||||
timezone, locale = _maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = _build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
timezone, locale = maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
|
||||
logger.debug("Launching stealth Chromium async (headless=%s, args=%d)", headless, len(chrome_args))
|
||||
|
||||
@@ -284,8 +284,8 @@ def launch_persistent_context(
|
||||
timezone = _resolve_timezone(timezone, kwargs)
|
||||
|
||||
binary_path = ensure_binary()
|
||||
timezone, locale = _maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = _build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
timezone, locale = maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
|
||||
logger.debug(
|
||||
"Launching persistent stealth Chromium (headless=%s, user_data_dir=%s)",
|
||||
@@ -399,8 +399,8 @@ async def launch_persistent_context_async(
|
||||
timezone = _resolve_timezone(timezone, kwargs)
|
||||
|
||||
binary_path = ensure_binary()
|
||||
timezone, locale = _maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = _build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
timezone, locale = maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
chrome_args = build_args(stealth_args, args, timezone=timezone, locale=locale, headless=headless)
|
||||
|
||||
logger.debug(
|
||||
"Launching persistent stealth Chromium async (headless=%s, user_data_dir=%s)",
|
||||
@@ -497,7 +497,7 @@ def launch_context(
|
||||
|
||||
# Resolve geoip BEFORE launch() to avoid double-resolution and ensure
|
||||
# resolved values flow to binary flags
|
||||
timezone, locale = _maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
timezone, locale = maybe_resolve_geoip(geoip, proxy, timezone, locale)
|
||||
# --fingerprint-timezone is process-wide (reads CommandLine in renderer),
|
||||
# so it applies to ALL contexts, not just the default one.
|
||||
# locale and timezone are set via binary flags only — no CDP emulation.
|
||||
@@ -590,7 +590,7 @@ def _ensure_proxy_scheme(proxy_url: str) -> str:
|
||||
return proxy_url if "://" in proxy_url else f"http://{proxy_url}"
|
||||
|
||||
|
||||
def _maybe_resolve_geoip(
|
||||
def maybe_resolve_geoip(
|
||||
geoip: bool,
|
||||
proxy: str | ProxySettings | None,
|
||||
timezone: str | None,
|
||||
@@ -614,7 +614,7 @@ def _maybe_resolve_geoip(
|
||||
return timezone, locale
|
||||
|
||||
|
||||
def _build_args(
|
||||
def build_args(
|
||||
stealth_args: bool,
|
||||
extra_args: list[str] | None,
|
||||
timezone: str | None = None,
|
||||
|
||||
@@ -56,6 +56,7 @@ dependencies = [
|
||||
[project.optional-dependencies]
|
||||
geoip = ["geoip2>=4.0"]
|
||||
patchright = ["patchright>=1.40"]
|
||||
serve = ["aiohttp>=3.9", "websockets>=12.0"]
|
||||
dev = ["pytest>=7.0", "pytest-asyncio>=0.23"]
|
||||
|
||||
[project.scripts]
|
||||
|
||||
+15
-15
@@ -1,24 +1,24 @@
|
||||
"""Unit tests for _build_args timezone/locale injection and timezone alias."""
|
||||
"""Unit tests for build_args timezone/locale injection and timezone alias."""
|
||||
|
||||
from cloakbrowser.browser import _build_args, _resolve_timezone
|
||||
from cloakbrowser.browser import build_args, _resolve_timezone
|
||||
|
||||
|
||||
def test_timezone_injected():
|
||||
"""--fingerprint-timezone flag should appear when timezone is set."""
|
||||
args = _build_args(stealth_args=True, extra_args=None, timezone="America/New_York")
|
||||
args = build_args(stealth_args=True, extra_args=None, timezone="America/New_York")
|
||||
assert "--fingerprint-timezone=America/New_York" in args
|
||||
|
||||
|
||||
def test_locale_injected():
|
||||
"""--lang and --fingerprint-locale flags should appear when locale is set."""
|
||||
args = _build_args(stealth_args=True, extra_args=None, locale="en-US")
|
||||
args = build_args(stealth_args=True, extra_args=None, locale="en-US")
|
||||
assert "--lang=en-US" in args
|
||||
assert "--fingerprint-locale=en-US" in args
|
||||
|
||||
|
||||
def test_both_injected():
|
||||
"""Both flags should appear when both are set."""
|
||||
args = _build_args(stealth_args=True, extra_args=None, timezone="Europe/Berlin", locale="de-DE")
|
||||
args = build_args(stealth_args=True, extra_args=None, timezone="Europe/Berlin", locale="de-DE")
|
||||
assert "--fingerprint-timezone=Europe/Berlin" in args
|
||||
assert "--lang=de-DE" in args
|
||||
assert "--fingerprint-locale=de-DE" in args
|
||||
@@ -26,7 +26,7 @@ def test_both_injected():
|
||||
|
||||
def test_timezone_independent_of_stealth_args():
|
||||
"""--fingerprint-timezone should be injected even when stealth_args=False."""
|
||||
args = _build_args(stealth_args=False, extra_args=None, timezone="America/New_York", locale="en-US")
|
||||
args = build_args(stealth_args=False, extra_args=None, timezone="America/New_York", locale="en-US")
|
||||
assert "--fingerprint-timezone=America/New_York" in args
|
||||
assert "--lang=en-US" in args
|
||||
assert "--fingerprint-locale=en-US" in args
|
||||
@@ -36,7 +36,7 @@ def test_timezone_independent_of_stealth_args():
|
||||
|
||||
def test_no_flags_when_not_set():
|
||||
"""No timezone/lang/fingerprint-locale flags when params are None."""
|
||||
args = _build_args(stealth_args=True, extra_args=None)
|
||||
args = build_args(stealth_args=True, extra_args=None)
|
||||
assert not any(a.startswith("--fingerprint-timezone=") for a in args)
|
||||
assert not any(a.startswith("--lang=") for a in args)
|
||||
assert not any(a.startswith("--fingerprint-locale=") for a in args)
|
||||
@@ -44,7 +44,7 @@ def test_no_flags_when_not_set():
|
||||
|
||||
def test_extra_args_preserved():
|
||||
"""Extra args should still be included alongside timezone/locale."""
|
||||
args = _build_args(stealth_args=True, extra_args=["--disable-gpu"], timezone="Asia/Tokyo", locale="ja-JP")
|
||||
args = build_args(stealth_args=True, extra_args=["--disable-gpu"], timezone="Asia/Tokyo", locale="ja-JP")
|
||||
assert "--disable-gpu" in args
|
||||
assert "--fingerprint-timezone=Asia/Tokyo" in args
|
||||
assert "--lang=ja-JP" in args
|
||||
@@ -90,7 +90,7 @@ def test_resolve_both_none():
|
||||
|
||||
def test_user_fingerprint_overrides_default():
|
||||
"""User --fingerprint should override the random default seed."""
|
||||
args = _build_args(stealth_args=True, extra_args=["--fingerprint=99887"])
|
||||
args = build_args(stealth_args=True, extra_args=["--fingerprint=99887"])
|
||||
fingerprint_args = [a for a in args if a.startswith("--fingerprint=")]
|
||||
assert len(fingerprint_args) == 1
|
||||
assert fingerprint_args[0] == "--fingerprint=99887"
|
||||
@@ -98,7 +98,7 @@ def test_user_fingerprint_overrides_default():
|
||||
|
||||
def test_user_platform_overrides_default():
|
||||
"""User --fingerprint-platform should override the default."""
|
||||
args = _build_args(stealth_args=True, extra_args=["--fingerprint-platform=linux"])
|
||||
args = build_args(stealth_args=True, extra_args=["--fingerprint-platform=linux"])
|
||||
platform_args = [a for a in args if a.startswith("--fingerprint-platform=")]
|
||||
assert len(platform_args) == 1
|
||||
assert platform_args[0] == "--fingerprint-platform=linux"
|
||||
@@ -106,7 +106,7 @@ def test_user_platform_overrides_default():
|
||||
|
||||
def test_timezone_param_overrides_user_arg():
|
||||
"""Dedicated timezone param should override user arg."""
|
||||
args = _build_args(
|
||||
args = build_args(
|
||||
stealth_args=True,
|
||||
extra_args=["--fingerprint-timezone=Europe/London"],
|
||||
timezone="America/New_York",
|
||||
@@ -118,7 +118,7 @@ def test_timezone_param_overrides_user_arg():
|
||||
|
||||
def test_locale_param_overrides_user_arg():
|
||||
"""Dedicated locale param should override user --lang and --fingerprint-locale args."""
|
||||
args = _build_args(
|
||||
args = build_args(
|
||||
stealth_args=True,
|
||||
extra_args=["--lang=de-DE", "--fingerprint-locale=de-DE"],
|
||||
locale="en-US",
|
||||
@@ -133,7 +133,7 @@ def test_locale_param_overrides_user_arg():
|
||||
|
||||
def test_no_duplicate_flags():
|
||||
"""No flag key should appear more than once in the output."""
|
||||
args = _build_args(
|
||||
args = build_args(
|
||||
stealth_args=True,
|
||||
extra_args=["--fingerprint=99887", "--fingerprint-timezone=UTC", "--lang=fr-FR"],
|
||||
timezone="Europe/Berlin",
|
||||
@@ -145,7 +145,7 @@ def test_no_duplicate_flags():
|
||||
|
||||
def test_non_value_flags_preserved():
|
||||
"""Flags without = should be preserved without dedup issues."""
|
||||
args = _build_args(stealth_args=True, extra_args=["--disable-gpu", "--no-zygote"])
|
||||
args = build_args(stealth_args=True, extra_args=["--disable-gpu", "--no-zygote"])
|
||||
assert "--disable-gpu" in args
|
||||
assert "--no-zygote" in args
|
||||
assert "--no-sandbox" in args
|
||||
@@ -156,5 +156,5 @@ def test_override_logs_debug(caplog):
|
||||
import logging
|
||||
|
||||
with caplog.at_level(logging.DEBUG, logger="cloakbrowser"):
|
||||
_build_args(stealth_args=True, extra_args=["--fingerprint=99887"])
|
||||
build_args(stealth_args=True, extra_args=["--fingerprint=99887"])
|
||||
assert any("--fingerprint=" in r.message and "99887" in r.message for r in caplog.records)
|
||||
|
||||
@@ -0,0 +1,171 @@
|
||||
"""Unit tests for cloakserve — parse_connection_params, parse_cli_args, URL rewriting."""
|
||||
|
||||
import importlib.machinery
|
||||
import importlib.util
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
aiohttp = pytest.importorskip("aiohttp", reason="cloakserve requires aiohttp (install with .[serve])")
|
||||
|
||||
# Load cloakserve as a module from bin/ (no .py extension).
|
||||
_bin_path = str(Path(__file__).resolve().parents[1] / "bin" / "cloakserve")
|
||||
_loader = importlib.machinery.SourceFileLoader("cloakserve", _bin_path)
|
||||
_spec = importlib.util.spec_from_file_location("cloakserve", _bin_path, loader=_loader)
|
||||
_mod = importlib.util.module_from_spec(_spec)
|
||||
sys.modules["cloakserve"] = _mod
|
||||
_loader.exec_module(_mod)
|
||||
|
||||
parse_connection_params = _mod.parse_connection_params
|
||||
parse_cli_args = _mod.parse_cli_args
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# parse_connection_params
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestParseConnectionParams:
|
||||
def test_empty_query(self):
|
||||
result = parse_connection_params("")
|
||||
assert result["seed"] is None
|
||||
assert result["extra_args"] == []
|
||||
|
||||
def test_fingerprint_seed(self):
|
||||
result = parse_connection_params("fingerprint=12345")
|
||||
assert result["seed"] == "12345"
|
||||
|
||||
def test_timezone_and_locale(self):
|
||||
result = parse_connection_params("fingerprint=1&timezone=Asia/Tokyo&locale=ja-JP")
|
||||
assert result["timezone"] == "Asia/Tokyo"
|
||||
assert result["locale"] == "ja-JP"
|
||||
|
||||
def test_proxy(self):
|
||||
result = parse_connection_params("proxy=http://proxy:8080")
|
||||
assert result["proxy"] == "http://proxy:8080"
|
||||
|
||||
def test_geoip_true_variants(self):
|
||||
for val in ("true", "1", "yes", "True", "YES"):
|
||||
result = parse_connection_params(f"geoip={val}")
|
||||
assert result["geoip"] is True, f"geoip={val} should be True"
|
||||
|
||||
def test_geoip_false(self):
|
||||
for val in ("false", "0", "no", "anything"):
|
||||
result = parse_connection_params(f"geoip={val}")
|
||||
assert result["geoip"] is False, f"geoip={val} should be False"
|
||||
|
||||
def test_generic_fingerprint_params(self):
|
||||
qs = "fingerprint=1&platform=windows&hardware-concurrency=8&gpu-vendor=NVIDIA"
|
||||
result = parse_connection_params(qs)
|
||||
assert "--fingerprint-platform=windows" in result["extra_args"]
|
||||
assert "--fingerprint-hardware-concurrency=8" in result["extra_args"]
|
||||
assert "--fingerprint-gpu-vendor=NVIDIA" in result["extra_args"]
|
||||
|
||||
def test_special_params_not_in_extra_args(self):
|
||||
qs = "fingerprint=1&timezone=UTC&locale=en-US&proxy=http://x:1&geoip=true"
|
||||
result = parse_connection_params(qs)
|
||||
assert result["extra_args"] == []
|
||||
|
||||
def test_multiple_values_takes_first(self):
|
||||
result = parse_connection_params("fingerprint=111&fingerprint=222")
|
||||
assert result["seed"] == "111"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# parse_cli_args
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestParseCliArgs:
|
||||
def test_defaults(self):
|
||||
config, passthrough = parse_cli_args([])
|
||||
assert config["port"] == 9222
|
||||
assert config["headless"] is True
|
||||
assert passthrough == []
|
||||
|
||||
def test_custom_port(self):
|
||||
config, _ = parse_cli_args(["--port=8080"])
|
||||
assert config["port"] == 8080
|
||||
|
||||
def test_headless_false(self):
|
||||
config, passthrough = parse_cli_args(["--headless=false"])
|
||||
assert config["headless"] is False
|
||||
# headless flag still passed through to Chrome
|
||||
assert "--headless=false" in passthrough
|
||||
|
||||
def test_strips_remote_debugging_flags(self):
|
||||
args = ["--remote-debugging-port=9999", "--remote-debugging-address=0.0.0.0", "--no-sandbox"]
|
||||
config, passthrough = parse_cli_args(args)
|
||||
assert passthrough == ["--no-sandbox"]
|
||||
|
||||
def test_passthrough_args(self):
|
||||
args = ["--no-sandbox", "--disable-gpu", "--fingerprint=999"]
|
||||
_, passthrough = parse_cli_args(args)
|
||||
assert passthrough == args
|
||||
|
||||
def test_port_not_in_passthrough(self):
|
||||
_, passthrough = parse_cli_args(["--port=9222", "--no-sandbox"])
|
||||
assert "--port=9222" not in passthrough
|
||||
assert "--no-sandbox" in passthrough
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# URL rewriting logic (pure string manipulation, extracted from handlers)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestURLRewriting:
|
||||
"""Test the URL rewriting logic used by /json/version and /json/list."""
|
||||
|
||||
def _rewrite_version(self, orig_ws: str, host: str, seed: str | None, scheme: str = "ws") -> str:
|
||||
"""Replicate the URL rewrite logic from handle_json_version."""
|
||||
if seed:
|
||||
ws_path = f"fingerprint/{seed}/devtools/browser"
|
||||
else:
|
||||
ws_path = "devtools/browser"
|
||||
guid = orig_ws.rsplit("/", 1)[-1] if "/devtools/" in orig_ws else ""
|
||||
return f"{scheme}://{host}/{ws_path}/{guid}"
|
||||
|
||||
def _rewrite_list_entry(self, orig_ws: str, host: str, seed: str | None, scheme: str = "ws") -> str:
|
||||
"""Replicate the URL rewrite logic from handle_json_list."""
|
||||
ws_tail = orig_ws.split("/devtools/")[-1]
|
||||
if seed:
|
||||
return f"{scheme}://{host}/fingerprint/{seed}/devtools/{ws_tail}"
|
||||
else:
|
||||
return f"{scheme}://{host}/devtools/{ws_tail}"
|
||||
|
||||
def test_version_rewrite_with_seed(self):
|
||||
orig = "ws://127.0.0.1:5100/devtools/browser/abc-123"
|
||||
result = self._rewrite_version(orig, "container:9222", "12345")
|
||||
assert result == "ws://container:9222/fingerprint/12345/devtools/browser/abc-123"
|
||||
|
||||
def test_version_rewrite_no_seed(self):
|
||||
orig = "ws://127.0.0.1:5100/devtools/browser/abc-123"
|
||||
result = self._rewrite_version(orig, "container:9222", None)
|
||||
assert result == "ws://container:9222/devtools/browser/abc-123"
|
||||
|
||||
def test_list_rewrite_page_with_seed(self):
|
||||
orig = "ws://127.0.0.1:5100/devtools/page/DEF-456"
|
||||
result = self._rewrite_list_entry(orig, "host:9222", "99")
|
||||
assert result == "ws://host:9222/fingerprint/99/devtools/page/DEF-456"
|
||||
|
||||
def test_list_rewrite_page_no_seed(self):
|
||||
orig = "ws://127.0.0.1:5100/devtools/page/DEF-456"
|
||||
result = self._rewrite_list_entry(orig, "host:9222", None)
|
||||
assert result == "ws://host:9222/devtools/page/DEF-456"
|
||||
|
||||
def test_list_rewrite_browser(self):
|
||||
orig = "ws://127.0.0.1:5100/devtools/browser/XYZ"
|
||||
result = self._rewrite_list_entry(orig, "host:9222", "seed1")
|
||||
assert result == "ws://host:9222/fingerprint/seed1/devtools/browser/XYZ"
|
||||
|
||||
def test_wss_scheme_version(self):
|
||||
orig = "ws://127.0.0.1:5100/devtools/browser/abc-123"
|
||||
result = self._rewrite_version(orig, "host:443", "seed1", scheme="wss")
|
||||
assert result == "wss://host:443/fingerprint/seed1/devtools/browser/abc-123"
|
||||
|
||||
def test_wss_scheme_list(self):
|
||||
orig = "ws://127.0.0.1:5100/devtools/page/DEF-456"
|
||||
result = self._rewrite_list_entry(orig, "host:443", "seed1", scheme="wss")
|
||||
assert result == "wss://host:443/fingerprint/seed1/devtools/page/DEF-456"
|
||||
+8
-8
@@ -4,7 +4,7 @@ from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from cloakbrowser.browser import _maybe_resolve_geoip
|
||||
from cloakbrowser.browser import maybe_resolve_geoip
|
||||
from cloakbrowser.geoip import (
|
||||
COUNTRY_LOCALE_MAP,
|
||||
_is_private_ip,
|
||||
@@ -92,25 +92,25 @@ def test_resolve_geo_returns_none_when_db_missing():
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# _maybe_resolve_geoip (browser.py helper)
|
||||
# maybe_resolve_geoip (browser.py helper)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_maybe_resolve_skips_when_geoip_false():
|
||||
tz, loc = _maybe_resolve_geoip(False, "http://proxy:8080", None, None)
|
||||
tz, loc = maybe_resolve_geoip(False, "http://proxy:8080", None, None)
|
||||
assert tz is None
|
||||
assert loc is None
|
||||
|
||||
|
||||
def test_maybe_resolve_skips_when_no_proxy():
|
||||
tz, loc = _maybe_resolve_geoip(True, None, None, None)
|
||||
tz, loc = maybe_resolve_geoip(True, None, None, None)
|
||||
assert tz is None
|
||||
assert loc is None
|
||||
|
||||
|
||||
def test_maybe_resolve_skips_when_both_explicit():
|
||||
"""Explicit values should not trigger geoip resolution."""
|
||||
tz, loc = _maybe_resolve_geoip(True, "http://proxy:8080", "Europe/Berlin", "de-DE")
|
||||
tz, loc = maybe_resolve_geoip(True, "http://proxy:8080", "Europe/Berlin", "de-DE")
|
||||
assert tz == "Europe/Berlin"
|
||||
assert loc == "de-DE"
|
||||
|
||||
@@ -118,7 +118,7 @@ def test_maybe_resolve_skips_when_both_explicit():
|
||||
def test_maybe_resolve_fills_missing_timezone():
|
||||
"""When only locale is explicit, geoip should fill timezone."""
|
||||
with patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("America/New_York", "en-US")):
|
||||
tz, loc = _maybe_resolve_geoip(True, "http://proxy:8080", None, "fr-FR")
|
||||
tz, loc = maybe_resolve_geoip(True, "http://proxy:8080", None, "fr-FR")
|
||||
assert tz == "America/New_York"
|
||||
assert loc == "fr-FR" # Explicit wins
|
||||
|
||||
@@ -126,7 +126,7 @@ def test_maybe_resolve_fills_missing_timezone():
|
||||
def test_maybe_resolve_fills_missing_locale():
|
||||
"""When only timezone is explicit, geoip should fill locale."""
|
||||
with patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("America/New_York", "en-US")):
|
||||
tz, loc = _maybe_resolve_geoip(True, "http://proxy:8080", "Asia/Tokyo", None)
|
||||
tz, loc = maybe_resolve_geoip(True, "http://proxy:8080", "Asia/Tokyo", None)
|
||||
assert tz == "Asia/Tokyo" # Explicit wins
|
||||
assert loc == "en-US"
|
||||
|
||||
@@ -134,7 +134,7 @@ def test_maybe_resolve_fills_missing_locale():
|
||||
def test_maybe_resolve_fills_both():
|
||||
"""When neither is set, geoip should fill both."""
|
||||
with patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("Europe/Berlin", "de-DE")):
|
||||
tz, loc = _maybe_resolve_geoip(True, "http://proxy:8080", None, None)
|
||||
tz, loc = maybe_resolve_geoip(True, "http://proxy:8080", None, None)
|
||||
assert tz == "Europe/Berlin"
|
||||
assert loc == "de-DE"
|
||||
|
||||
|
||||
@@ -114,7 +114,7 @@ def test_color_scheme(mock_launch, _mock_bin):
|
||||
assert ctx_kwargs[1]["color_scheme"] == "dark"
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=("Europe/Berlin", "de-DE"))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=("Europe/Berlin", "de-DE"))
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser.launch")
|
||||
def test_geoip_resolution(mock_launch, _mock_bin, _mock_geoip):
|
||||
|
||||
@@ -26,7 +26,7 @@ def _make_mock_pw_and_context():
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_args_built(_mock_geoip, _mock_bin):
|
||||
"""Stealth args + extra args combined correctly."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -42,7 +42,7 @@ def test_persistent_context_args_built(_mock_geoip, _mock_bin):
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_default_viewport(_mock_geoip, _mock_bin):
|
||||
"""DEFAULT_VIEWPORT applied when no viewport given."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -56,7 +56,7 @@ def test_persistent_context_default_viewport(_mock_geoip, _mock_bin):
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_custom_viewport(_mock_geoip, _mock_bin):
|
||||
"""Custom viewport overrides DEFAULT_VIEWPORT."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -71,7 +71,7 @@ def test_persistent_context_custom_viewport(_mock_geoip, _mock_bin):
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_user_agent(_mock_geoip, _mock_bin):
|
||||
"""user_agent forwarded to launch_persistent_context()."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -103,7 +103,7 @@ def test_persistent_context_locale_and_timezone(_mock_bin):
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_color_scheme(_mock_geoip, _mock_bin):
|
||||
"""color_scheme forwarded correctly."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -116,7 +116,7 @@ def test_persistent_context_color_scheme(_mock_geoip, _mock_bin):
|
||||
assert call_kwargs["color_scheme"] == "dark"
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=("Europe/Berlin", "de-DE"))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=("Europe/Berlin", "de-DE"))
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
def test_persistent_context_geoip(_mock_bin, _mock_geoip):
|
||||
"""geoip fills missing tz/locale — flows to binary args, not CDP context."""
|
||||
@@ -150,7 +150,7 @@ def test_persistent_context_timezone_id_alias(_mock_bin):
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_close_stops_pw(_mock_geoip, _mock_bin):
|
||||
"""context.close() also calls pw.stop()."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -166,7 +166,7 @@ def test_persistent_context_close_stops_pw(_mock_geoip, _mock_bin):
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_proxy_string(_mock_geoip, _mock_bin):
|
||||
"""Proxy string parsed and passed."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -182,7 +182,7 @@ def test_persistent_context_proxy_string(_mock_geoip, _mock_bin):
|
||||
|
||||
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
def test_persistent_context_proxy_dict(_mock_geoip, _mock_bin):
|
||||
"""Proxy dict passed through."""
|
||||
pw_cm, pw, context = _make_mock_pw_and_context()
|
||||
@@ -213,7 +213,7 @@ def _make_mock_async_pw_and_context():
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
async def test_persistent_context_async_args_built(_mock_geoip, _mock_bin):
|
||||
"""Async launch builds args correctly."""
|
||||
pw_cm, pw, context = _make_mock_async_pw_and_context()
|
||||
@@ -229,7 +229,7 @@ async def test_persistent_context_async_args_built(_mock_geoip, _mock_bin):
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("cloakbrowser.browser.ensure_binary", return_value="/fake/chrome")
|
||||
@patch("cloakbrowser.browser._maybe_resolve_geoip", return_value=(None, None))
|
||||
@patch("cloakbrowser.browser.maybe_resolve_geoip", return_value=(None, None))
|
||||
async def test_persistent_context_async_close_stops_pw(_mock_geoip, _mock_bin):
|
||||
"""await context.close() calls await pw.stop()."""
|
||||
pw_cm, pw, context = _make_mock_async_pw_and_context()
|
||||
|
||||
+8
-8
@@ -2,7 +2,7 @@
|
||||
|
||||
from unittest.mock import patch
|
||||
|
||||
from cloakbrowser.browser import _build_proxy_kwargs, _maybe_resolve_geoip, _parse_proxy_url
|
||||
from cloakbrowser.browser import _build_proxy_kwargs, maybe_resolve_geoip, _parse_proxy_url
|
||||
|
||||
|
||||
class TestParseProxyUrl:
|
||||
@@ -70,7 +70,7 @@ class TestBuildProxyKwargs:
|
||||
class TestMaybeResolveGeoip:
|
||||
@patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("America/New_York", "en-US"))
|
||||
def test_geoip_with_string_proxy(self, mock_geo):
|
||||
tz, locale = _maybe_resolve_geoip(True, "http://proxy:8080", None, None)
|
||||
tz, locale = maybe_resolve_geoip(True, "http://proxy:8080", None, None)
|
||||
mock_geo.assert_called_once_with("http://proxy:8080")
|
||||
assert tz == "America/New_York"
|
||||
assert locale == "en-US"
|
||||
@@ -78,31 +78,31 @@ class TestMaybeResolveGeoip:
|
||||
@patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("Europe/London", "en-GB"))
|
||||
def test_geoip_with_dict_proxy_extracts_server(self, mock_geo):
|
||||
proxy_dict = {"server": "http://proxy:8080", "bypass": ".google.com"}
|
||||
tz, locale = _maybe_resolve_geoip(True, proxy_dict, None, None)
|
||||
tz, locale = maybe_resolve_geoip(True, proxy_dict, None, None)
|
||||
mock_geo.assert_called_once_with("http://proxy:8080")
|
||||
assert tz == "Europe/London"
|
||||
assert locale == "en-GB"
|
||||
|
||||
def test_geoip_disabled_skips_resolution(self):
|
||||
tz, locale = _maybe_resolve_geoip(False, "http://proxy:8080", None, None)
|
||||
tz, locale = maybe_resolve_geoip(False, "http://proxy:8080", None, None)
|
||||
assert tz is None
|
||||
assert locale is None
|
||||
|
||||
def test_geoip_no_proxy_skips_resolution(self):
|
||||
tz, locale = _maybe_resolve_geoip(True, None, None, None)
|
||||
tz, locale = maybe_resolve_geoip(True, None, None, None)
|
||||
assert tz is None
|
||||
assert locale is None
|
||||
|
||||
@patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("Asia/Tokyo", "ja-JP"))
|
||||
def test_geoip_preserves_explicit_timezone(self, mock_geo):
|
||||
tz, locale = _maybe_resolve_geoip(True, "http://proxy:8080", "Europe/Berlin", None)
|
||||
tz, locale = maybe_resolve_geoip(True, "http://proxy:8080", "Europe/Berlin", None)
|
||||
assert tz == "Europe/Berlin"
|
||||
assert locale == "ja-JP"
|
||||
|
||||
@patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("America/New_York", "en-US"))
|
||||
def test_geoip_normalizes_bare_proxy_with_creds(self, mock_geo):
|
||||
# "user:pass@host:port" must be normalized to http:// before geoip lookup.
|
||||
tz, locale = _maybe_resolve_geoip(True, "user:pass@proxy:8080", None, None)
|
||||
tz, locale = maybe_resolve_geoip(True, "user:pass@proxy:8080", None, None)
|
||||
mock_geo.assert_called_once_with("http://user:pass@proxy:8080")
|
||||
assert tz == "America/New_York"
|
||||
assert locale == "en-US"
|
||||
@@ -110,7 +110,7 @@ class TestMaybeResolveGeoip:
|
||||
@patch("cloakbrowser.geoip.resolve_proxy_geo", return_value=("America/New_York", "en-US"))
|
||||
def test_geoip_normalizes_schemeless_proxy_no_creds(self, mock_geo):
|
||||
# "host:port" (no @ and no scheme) must also be normalized.
|
||||
tz, locale = _maybe_resolve_geoip(True, "proxy:8080", None, None)
|
||||
tz, locale = maybe_resolve_geoip(True, "proxy:8080", None, None)
|
||||
mock_geo.assert_called_once_with("http://proxy:8080")
|
||||
assert tz == "America/New_York"
|
||||
|
||||
|
||||
Reference in New Issue
Block a user