Compare commits

..
Author SHA1 Message Date
Typosaurus 3fed6463be ticket #75 attempt 1 2026-07-19 20:08:35 +00:00
6 changed files with 75 additions and 47 deletions
+18 -1
View File
@@ -4,12 +4,13 @@ import asyncio
import fcntl
import logging
import os
import re
import time
from collections import defaultdict
from contextlib import asynccontextmanager, contextmanager
from pathlib import Path
from fastapi import FastAPI, Request
from fastapi.responses import HTMLResponse, RedirectResponse
from fastapi.responses import HTMLResponse, RedirectResponse, Response
from fastapi.staticfiles import StaticFiles
from fastapi.exceptions import RequestValidationError
from starlette.middleware.gzip import GZipMiddleware
@@ -611,6 +612,22 @@ async def response_timing(request: Request, call_next):
return response
_KNOWN_CRAWLERS = re.compile(
r"(google.*read.*aloud|googlebot|bingbot|slurp|duckduckbot|baiduspider|yandexbot)",
re.IGNORECASE,
)
_AUTH_GATED_PATHS = frozenset({"/messages", "/notifications", "/game", "/admin"})
@app.middleware("http")
async def crawler_detection(request: Request, call_next):
if request.method == "GET" and request.url.path in _AUTH_GATED_PATHS:
ua = request.headers.get("user-agent", "")
if _KNOWN_CRAWLERS.search(ua):
return Response(status_code=204)
return await call_next(request)
app.add_middleware(GZipMiddleware, minimum_size=512, compresslevel=5)
+1
View File
@@ -17,6 +17,7 @@ async def robots_txt(request: Request):
Disallow: /auth/
Disallow: /messages/
Disallow: /notifications/
Disallow: /game/
Disallow: /votes/
Disallow: /avatar/
Disallow: /follow/
+2 -39
View File
@@ -2,10 +2,8 @@
from __future__ import annotations
import socket
import subprocess
import sys
import time
from devplacepy.config import XMLRPC_BIND, XMLRPC_PORT
from devplacepy.services.base import BaseService
@@ -27,48 +25,20 @@ class XmlrpcService(BaseService):
def __init__(self) -> None:
super().__init__("xmlrpc", interval_seconds=XMLRPC_INTERVAL_SECONDS)
self._process: subprocess.Popen | None = None
self._last_stderr: str | None = None
def _alive(self) -> bool:
return self._process is not None and self._process.poll() is None
def _spawn(self) -> None:
self._last_stderr = None
self._process = subprocess.Popen(
[sys.executable, "-m", SERVER_MODULE],
stdout=subprocess.DEVNULL,
stderr=subprocess.PIPE,
stderr=subprocess.DEVNULL,
)
self.log(
f"Forking XML-RPC server spawning (pid {self._process.pid}) on "
f"Forking XML-RPC server started (pid {self._process.pid}) on "
f"{XMLRPC_BIND}:{XMLRPC_PORT}"
)
time.sleep(0.5)
if self._process.poll() is not None:
stderr_data = self._process.communicate()[1]
if stderr_data:
self._last_stderr = stderr_data.decode("utf-8", errors="replace")
self.log(
f"Forking XML-RPC server died after spawn (pid {self._process.pid}, "
f"exit code {self._process.returncode})"
)
if self._last_stderr:
for line in self._last_stderr.strip().split("\n"):
self.log(f" stderr: {line}")
return
try:
sock = socket.create_connection((XMLRPC_BIND, XMLRPC_PORT), timeout=1)
sock.close()
except (OSError, socket.timeout):
self.log(
f"Forking XML-RPC server not yet ready (pid {self._process.pid}) "
f"on {XMLRPC_BIND}:{XMLRPC_PORT}"
)
else:
self.log(
f"Forking XML-RPC server started (pid {self._process.pid}) on "
f"{XMLRPC_BIND}:{XMLRPC_PORT}"
)
def _terminate(self) -> None:
if not self._alive():
@@ -95,13 +65,6 @@ class XmlrpcService(BaseService):
self.log(f"XML-RPC server healthy (pid {self._process.pid})")
return
self.log("XML-RPC server not running, starting it")
if self._process is not None:
self.log(
f"Previous process exited with code {self._process.returncode}"
)
if self._last_stderr:
for line in self._last_stderr.strip().split("\n"):
self.log(f" last stderr: {line}")
self._spawn()
def collect_metrics(self) -> dict:
-4
View File
@@ -3,7 +3,6 @@
from __future__ import annotations
import logging
import sys
from socketserver import ForkingMixIn
from xmlrpc.server import SimpleXMLRPCDispatcher, SimpleXMLRPCRequestHandler, SimpleXMLRPCServer
@@ -117,9 +116,6 @@ def main() -> None:
server.serve_forever()
except KeyboardInterrupt:
logger.info("XML-RPC server interrupted")
except Exception:
logging.exception("XML-RPC server crashed with unhandled exception")
sys.exit(1)
finally:
server.server_close()
+4 -3
View File
@@ -196,7 +196,8 @@ def test_robots_txt_exists(app_server):
assert "Sitemap:" in r.text
def test_robots_disallows_admin_and_uploads(app_server):
def test_robots_disallows_auth_gated_paths(app_server):
r = requests.get(f"{BASE_URL}/robots.txt")
assert "Disallow: /admin/" in r.text
assert "Disallow: /uploads/" in r.text
required = ["/auth/", "/game/", "/messages/", "/notifications/", "/admin/", "/uploads/"]
for path in required:
assert f"Disallow: {path}" in r.text, f"Missing Disallow: {path}"
+50
View File
@@ -0,0 +1,50 @@
# retoor <retoor@molodetz.nl>
import requests
from tests.conftest import BASE_URL
def test_bot_blocked_on_auth_path(app_server):
headers = {"User-Agent": "Google-Read-Aloud"}
r = requests.get(f"{BASE_URL}/messages", headers=headers)
assert r.status_code == 204
assert r.content == b""
def test_bot_blocked_on_game_path(app_server):
headers = {"User-Agent": "Google-Read-Aloud"}
r = requests.get(f"{BASE_URL}/game", headers=headers)
assert r.status_code == 204
assert r.content == b""
def test_bot_blocked_on_admin_path(app_server):
headers = {"User-Agent": "Google-Read-Aloud"}
r = requests.get(f"{BASE_URL}/admin", headers=headers)
assert r.status_code == 204
assert r.content == b""
def test_bot_not_blocked_on_public_path(app_server):
headers = {"User-Agent": "Google-Read-Aloud"}
r = requests.get(f"{BASE_URL}/", headers=headers)
assert r.status_code == 200
def test_normal_user_not_blocked(app_server):
r = requests.get(f"{BASE_URL}/messages", allow_redirects=False)
assert r.status_code == 303
def test_known_crawler_user_agent_variants(app_server):
ua_list = [
"Googlebot",
"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)",
"bingbot/2.0; +http://www.bing.com/bingbot.htm",
"Mozilla/5.0 (compatible; DuckDuckBot-Https/1.1; ...)",
"Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
]
for ua in ua_list:
headers = {"User-Agent": ua}
r = requests.get(f"{BASE_URL}/admin", headers=headers)
assert r.status_code == 204, f"Expected 204 for UA: {ua}"