summaryrefslogtreecommitdiff
path: root/searx/network
diff options
context:
space:
mode:
authorvojkovic <git@vojk.au>2026-09-03 14:19:54 +0000
committerBrock Vojkovic <brock@vojk.au>2026-09-04 16:16:09 +0800
commitbe836e614a2f2e7512e2e1915a0bc37d51ee865c (patch)
treed08d26492eb1746d2c4b4f03c74dcff4e2a0072e /searx/network
parent15b0c8ef3ab02a86131040e5eabc0d5b82bb9470 (diff)
[mod] network: migrate to curl_cffi
Diffstat (limited to 'searx/network')
-rw-r--r--searx/network/__init__.py27
-rw-r--r--searx/network/client.py281
-rw-r--r--searx/network/network.py143
-rw-r--r--searx/network/raise_for_httperror.py7
4 files changed, 170 insertions, 288 deletions
diff --git a/searx/network/__init__.py b/searx/network/__init__.py
index 3a3b93d08..2257bcd31 100644
--- a/searx/network/__init__.py
+++ b/searx/network/__init__.py
@@ -14,8 +14,7 @@ from timeit import default_timer
from collections.abc import Iterable
from contextlib import contextmanager
-import httpx
-import anyio
+from curl_cffi.requests.exceptions import StreamConsumedError, Timeout
from searx.extended_types import SXNG_Response
from .network import get_network, initialize, check_network_configuration # pylint:disable=cyclic-import
@@ -74,7 +73,6 @@ def _get_timeout(start_time: float, kwargs: t.Any) -> float:
# pylint: disable=too-many-branches
timeout: float | None
- # timeout (httpx)
if 'timeout' in kwargs:
timeout = kwargs['timeout']
else:
@@ -105,10 +103,10 @@ def request(method: str, url: str, **kwargs: t.Any) -> SXNG_Response:
try:
return future.result(timeout)
except concurrent.futures.TimeoutError as e:
- raise httpx.TimeoutException('Timeout', request=None) from e
+ raise Timeout('Timeout') from e
-def multi_requests(request_list: list["Request"]) -> list[httpx.Response | Exception]:
+def multi_requests(request_list: list["Request"]) -> list[SXNG_Response | Exception]:
"""send multiple HTTP requests in parallel. Wait for all requests to finish."""
with _record_http_time() as start_time:
# send the requests
@@ -128,7 +126,7 @@ def multi_requests(request_list: list["Request"]) -> list[httpx.Response | Excep
try:
responses.append(future.result(timeout))
except concurrent.futures.TimeoutError:
- responses.append(httpx.TimeoutException('Timeout', request=None))
+ responses.append(Timeout('Timeout'))
except Exception as e: # pylint: disable=broad-except
responses.append(e)
return responses
@@ -205,14 +203,12 @@ async def stream_chunk_to_queue(network, queue, method: str, url: str, **kwargs:
try:
async with await network.stream(method, url, **kwargs) as response:
queue.put(response)
- # aiter_raw: access the raw bytes on the response without applying any HTTP content decoding
- # https://www.python-httpx.org/quickstart/#streaming-responses
- async for chunk in response.aiter_raw(65536):
+ async for chunk in response.aiter_content():
if len(chunk) > 0:
queue.put(chunk)
- except (httpx.StreamClosed, anyio.ClosedResourceError):
+ except StreamConsumedError:
# the response was queued before the exception.
- # the exception was raised on aiter_raw.
+ # the exception was raised on aiter_content.
# we do nothing here: in the finally block, None will be queued
# so stream(method, url, **kwargs) generator can stop
pass
@@ -246,22 +242,19 @@ def _close_response_method(self):
asyncio.run_coroutine_threadsafe(self.aclose(), get_loop())
# reach the end of _self.generator ( _stream_generator ) to an avoid memory leak.
# it makes sure that :
- # * the httpx response is closed (see the stream_chunk_to_queue function)
+ # * the curl_cffi response is closed (see the stream_chunk_to_queue function)
# * to call future.result() in _stream_generator
for _ in self._generator: # pylint: disable=protected-access
continue
def stream(method: str, url: str, **kwargs: t.Any) -> tuple[SXNG_Response, Iterable[bytes]]:
- """Replace httpx.stream.
+ """Stream for the image proxy.
Usage:
- response, stream = poolrequests.stream(...)
+ response, stream = searx.network.stream(...)
for chunk in stream:
...
-
- httpx.Client.stream requires to write the httpx.HTTPTransport version of the
- the httpx.AsyncHTTPTransport declared above.
"""
generator = _stream_generator(method, url, **kwargs)
diff --git a/searx/network/client.py b/searx/network/client.py
index 4019e907c..9e6d213be 100644
--- a/searx/network/client.py
+++ b/searx/network/client.py
@@ -2,207 +2,114 @@
# pylint: disable=missing-module-docstring, global-statement
import typing as t
-from types import TracebackType
import asyncio
import logging
-import random
-from ssl import SSLContext
+import os
import threading
-import httpx
-from httpx_socks import AsyncProxyTransport
-from python_socks import parse_proxy_url, ProxyConnectionError, ProxyTimeoutError, ProxyError
+from curl_cffi import AsyncSession, CurlHttpVersion, CurlOpt
+from curl_cffi.requests.exceptions import InvalidSchema, RequestException
-from searx import logger
+from searx.extended_types import SXNG_Response
-CertTypes = str | tuple[str, str] | tuple[str, str, str]
-SslContextKeyType = tuple[str | None, CertTypes | None, bool, bool]
-
-logger = logger.getChild('searx.network.client')
LOOP: asyncio.AbstractEventLoop = None # pyright: ignore[reportAssignmentType]
-SSLCONTEXTS: dict[SslContextKeyType, SSLContext] = {}
-
-
-def shuffle_ciphers(ssl_context: SSLContext):
- """Shuffle httpx's default ciphers of a SSL context randomly.
-
- From `What Is TLS Fingerprint and How to Bypass It`_
-
- > When implementing TLS fingerprinting, servers can't operate based on a
- > locked-in whitelist database of fingerprints. New fingerprints appear
- > when web clients or TLS libraries release new versions. So, they have to
- > live off a blocklist database instead.
- > ...
- > It's safe to leave the first three as is but shuffle the remaining ciphers
- > and you can bypass the TLS fingerprint check.
-
- .. _What Is TLS Fingerprint and How to Bypass It:
- https://www.zenrows.com/blog/what-is-tls-fingerprint#how-to-bypass-tls-fingerprinting
-
- """
- c_list = [cipher["name"] for cipher in ssl_context.get_ciphers()]
- sc_list, c_list = c_list[:3], c_list[3:]
- random.shuffle(c_list)
- ssl_context.set_ciphers(":".join(sc_list + c_list))
-
+# chrome is used by default
+DEFAULT_IMPERSONATE = "chrome"
+NO_IMPERSONATE = "none"
-def get_sslcontexts(
- proxy_url: str | None = None, cert: CertTypes | None = None, verify: bool = True, trust_env: bool = True
-) -> SSLContext:
- key: SslContextKeyType = (proxy_url, cert, verify, trust_env)
- if key not in SSLCONTEXTS:
- SSLCONTEXTS[key] = httpx.create_ssl_context(verify, cert, trust_env)
- shuffle_ciphers(SSLCONTEXTS[key])
- return SSLCONTEXTS[key]
+class AsyncClient(AsyncSession):
+ """:class:`curl_cffi.AsyncSession` with ``aclose`` / ``is_closed``."""
-class AsyncHTTPTransportNoHttp(httpx.AsyncHTTPTransport):
- """Block HTTP request
+ def __init__(self, enable_http: bool, **kwargs: t.Any):
+ self.enable_http = enable_http
+ self._closed = False
+ super().__init__(**kwargs)
- The constructor is blank because httpx.AsyncHTTPTransport.__init__ creates an SSLContext unconditionally:
- https://github.com/encode/httpx/blob/0f61aa58d66680c239ce43c8cdd453e7dc532bfc/httpx/_transports/default.py#L271
+ @property
+ def is_closed(self) -> bool:
+ return self._closed
- Each SSLContext consumes more than 500kb of memory, since there is about one network per engine.
-
- In consequence, this class overrides all public methods
-
- For reference: https://github.com/encode/httpx/issues/2298
- """
-
- def __init__(self, *args, **kwargs): # type: ignore
- # pylint: disable=super-init-not-called
- # this on purpose if the base class is not called
- pass
-
- async def handle_async_request(self, request: httpx.Request):
- raise httpx.UnsupportedProtocol('HTTP protocol is disabled')
+ def check_url(self, url: str) -> None:
+ if not self.enable_http and str(url).startswith("http://"):
+ raise InvalidSchema("HTTP protocol is disabled")
async def aclose(self) -> None:
- pass
-
- async def __aenter__(self):
- return self
-
- async def __aexit__(
- self,
- exc_type: type[BaseException] | None = None,
- exc_value: BaseException | None = None,
- traceback: TracebackType | None = None,
- ) -> None:
- pass
-
-
-class AsyncProxyTransportFixed(AsyncProxyTransport):
- """Fix httpx_socks.AsyncProxyTransport
+ if self._closed:
+ return
+ self._closed = True
+ try:
+ await self.close()
+ except RequestException:
+ pass
- Map python_socks exceptions to httpx.ProxyError exceptions
- """
- async def handle_async_request(self, request: httpx.Request):
- try:
- return await super().handle_async_request(request)
- except ProxyConnectionError as e:
- raise httpx.ProxyError("ProxyConnectionError: " + str(e.strerror), request=request) from e
- except ProxyTimeoutError as e:
- raise httpx.ProxyError("ProxyTimeoutError: " + str(e.args[0]), request=request) from e
- except ProxyError as e:
- raise httpx.ProxyError("ProxyError: " + str(e.args[0]), request=request) from e
-
-
-def get_transport_for_socks_proxy(
- verify: bool, http2: bool, local_address: str, proxy_url: str, limit: httpx.Limits, retries: int
-):
- # support socks5h (requests compatibility):
- # https://requests.readthedocs.io/en/master/user/advanced/#socks
- # socks5:// hostname is resolved on client side
- # socks5h:// hostname is resolved on proxy side
- rdns = False
- socks5h = 'socks5h://'
- if proxy_url.startswith(socks5h):
- proxy_url = 'socks5://' + proxy_url[len(socks5h) :]
- rdns = True
-
- proxy_type, proxy_host, proxy_port, proxy_username, proxy_password = parse_proxy_url(proxy_url)
- _verify = get_sslcontexts(proxy_url, None, verify, True) if verify is True else verify
- return AsyncProxyTransportFixed(
- proxy_type=proxy_type,
- proxy_host=proxy_host,
- proxy_port=proxy_port,
- username=proxy_username,
- password=proxy_password,
- rdns=rdns,
- verify=_verify, # pyright: ignore[reportArgumentType]
- http2=http2,
- local_address=local_address,
- limits=limit,
- retries=retries,
- )
-
-
-def get_transport(
- verify: bool, http2: bool, local_address: str, proxy_url: str | None, limit: httpx.Limits, retries: int
-):
- _verify = get_sslcontexts(None, None, verify, True) if verify is True else verify
- return httpx.AsyncHTTPTransport(
- # pylint: disable=protected-access
- verify=_verify,
- http2=http2,
- limits=limit,
- proxy=httpx._config.Proxy(proxy_url) if proxy_url else None, # pyright: ignore[reportPrivateUsage]
- local_address=local_address,
- retries=retries,
- )
+def _proxy_kwargs(proxies: dict[str, str], enable_http: bool) -> dict[str, t.Any]:
+ """Map settings.yml proxy keys (``all://``, ``https://``) to curl_cffi."""
+ mapped: dict[str, str] = {}
+ all_proxy: str | None = None
+ for pattern, proxy_url in proxies.items():
+ if not enable_http and pattern.startswith("http://"):
+ continue
+ if pattern.startswith("https"):
+ mapped["https"] = proxy_url
+ elif pattern.startswith("http"):
+ mapped["http"] = proxy_url
+ else:
+ all_proxy = proxy_url
+ if all_proxy:
+ return {"proxy": all_proxy}
+ if mapped:
+ return {"proxies": mapped}
+ return {}
def new_client(
# pylint: disable=too-many-arguments
enable_http: bool,
- verify: bool,
+ verify: bool | str,
enable_http2: bool,
+ enable_http3: bool,
max_connections: int,
- max_keepalive_connections: int,
- keepalive_expiry: float,
proxies: dict[str, str],
- local_address: str,
- retries: int,
+ local_address: str | None,
max_redirects: int,
- hook_log_response: t.Callable[..., t.Any] | None,
-) -> httpx.AsyncClient:
- limit = httpx.Limits(
- max_connections=max_connections,
- max_keepalive_connections=max_keepalive_connections,
- keepalive_expiry=keepalive_expiry,
- )
- # See https://www.python-httpx.org/advanced/#routing
- mounts = {}
- mounts: None | (dict[str, t.Any | None]) = {}
- for pattern, proxy_url in proxies.items():
- if not enable_http and pattern.startswith('http://'):
- continue
- if proxy_url.startswith('socks4://') or proxy_url.startswith('socks5://') or proxy_url.startswith('socks5h://'):
- mounts[pattern] = get_transport_for_socks_proxy(
- verify, enable_http2, local_address, proxy_url, limit, retries
- )
- else:
- mounts[pattern] = get_transport(verify, enable_http2, local_address, proxy_url, limit, retries)
-
- if not enable_http:
- mounts['http://'] = AsyncHTTPTransportNoHttp()
-
- transport = get_transport(verify, enable_http2, local_address, None, limit, retries)
-
- event_hooks = None
- if hook_log_response:
- event_hooks = {'response': [hook_log_response]}
-
- return httpx.AsyncClient(
- transport=transport,
- mounts=mounts,
- max_redirects=max_redirects,
- event_hooks=event_hooks,
- )
+ impersonate: str = DEFAULT_IMPERSONATE,
+ curl_options: dict[int, t.Any] | None = None,
+) -> AsyncClient:
+ extra_curl = dict(curl_options or {})
+ cert_file = os.environ.get("SSL_CERT_FILE")
+ if cert_file:
+ extra_curl.setdefault(CurlOpt.CAINFO, cert_file)
+ cert_dir = os.environ.get("SSL_CERT_DIR")
+ if cert_dir:
+ extra_curl.setdefault(CurlOpt.CAPATH, cert_dir)
+ use_impersonate = impersonate not in ("", NO_IMPERSONATE)
+ kwargs: dict[str, t.Any] = {
+ "enable_http": enable_http,
+ "verify": verify,
+ "max_redirects": max_redirects,
+ "max_clients": max_connections or 10,
+ "response_class": SXNG_Response,
+ "discard_cookies": True,
+ **_proxy_kwargs(proxies, enable_http),
+ }
+ if use_impersonate:
+ kwargs["impersonate"] = impersonate
+ kwargs["default_headers"] = True
+ if local_address:
+ kwargs["interface"] = local_address
+ if not enable_http2:
+ kwargs["http_version"] = CurlHttpVersion.V1_1
+ elif enable_http3 and not proxies:
+ kwargs["http_version"] = CurlHttpVersion.V3
+ else:
+ kwargs["http_version"] = CurlHttpVersion.V2_0
+ if extra_curl:
+ kwargs["curl_options"] = extra_curl
+ return AsyncClient(**kwargs)
def get_loop() -> asyncio.AbstractEventLoop:
@@ -210,30 +117,18 @@ def get_loop() -> asyncio.AbstractEventLoop:
def init():
- # log
- for logger_name in (
- 'httpx',
- 'httpcore.proxy',
- 'httpcore.connection',
- 'httpcore.http11',
- 'httpcore.http2',
- 'hpack.hpack',
- 'hpack.table',
- ):
- logging.getLogger(logger_name).setLevel(logging.WARNING)
-
- # loop
+ logging.getLogger("curl_cffi").setLevel(logging.WARNING)
+
+ ready = threading.Event()
+
def loop_thread():
global LOOP
LOOP = asyncio.new_event_loop()
+ ready.set()
LOOP.run_forever()
- thread = threading.Thread(
- target=loop_thread,
- name='asyncio_loop',
- daemon=True,
- )
- thread.start()
+ threading.Thread(target=loop_thread, name="asyncio_loop", daemon=True).start()
+ ready.wait()
init()
diff --git a/searx/network/network.py b/searx/network/network.py
index eb53afb7f..42828ce41 100644
--- a/searx/network/network.py
+++ b/searx/network/network.py
@@ -13,11 +13,16 @@ import asyncio
import ipaddress
from itertools import cycle
-import httpx
+from curl_cffi import CurlHttpVersion
+from curl_cffi.requests.exceptions import (
+ ConnectionError as CurlConnectionError,
+ ProxyError,
+ RequestException,
+)
from searx import logger, sxng_debug
from searx.extended_types import SXNG_Response
-from .client import new_client, get_loop, AsyncHTTPTransportNoHttp
+from .client import DEFAULT_IMPERSONATE, AsyncClient, new_client, get_loop
from .raise_for_httperror import raise_for_httperror
@@ -48,9 +53,8 @@ class Network:
'enable_http',
'verify',
'enable_http2',
+ 'enable_http3',
'max_connections',
- 'max_keepalive_connections',
- 'keepalive_expiry',
'local_addresses',
'proxies',
'using_tor_proxy',
@@ -64,6 +68,7 @@ class Network:
)
_TOR_CHECK_RESULT = {}
+ _CLIENT_KWARGS = ('verify', 'max_redirects', 'impersonate', 'curl_options', 'enable_http3')
def __init__(
# pylint: disable=too-many-arguments
@@ -71,9 +76,8 @@ class Network:
enable_http: bool = True,
verify: bool = True,
enable_http2: bool = False,
+ enable_http3: bool = False,
max_connections: int = None, # pyright: ignore[reportArgumentType]
- max_keepalive_connections: int = None, # pyright: ignore[reportArgumentType]
- keepalive_expiry: float = None, # pyright: ignore[reportArgumentType]
proxies: str | dict[str, str] | None = None,
using_tor_proxy: bool = False,
local_addresses: str | list[str] | None = None,
@@ -86,9 +90,8 @@ class Network:
self.enable_http = enable_http
self.verify = verify
self.enable_http2 = enable_http2
+ self.enable_http3 = enable_http3
self.max_connections = max_connections
- self.max_keepalive_connections = max_keepalive_connections
- self.keepalive_expiry = keepalive_expiry
self.proxies = proxies
self.using_tor_proxy = using_tor_proxy
self.local_addresses = local_addresses
@@ -137,7 +140,6 @@ class Network:
def iter_proxies(self) -> Generator[tuple[str, list[str]]]:
if not self.proxies:
return
- # https://www.python-httpx.org/compatibility/#proxy-keys
if isinstance(self.proxies, str):
yield 'all://', [self.proxies]
else:
@@ -155,62 +157,73 @@ class Network:
# pylint: disable=stop-iteration-return
yield tuple((pattern, next(proxy_url_cycle)) for pattern, proxy_url_cycle in proxy_settings.items())
- async def log_response(self, response: httpx.Response):
+ _HTTP_VERSION = {
+ int(CurlHttpVersion.V1_0): "HTTP/1.0",
+ int(CurlHttpVersion.V1_1): "HTTP/1.1",
+ int(CurlHttpVersion.V2_0): "HTTP/2",
+ int(CurlHttpVersion.V2TLS): "HTTP/2",
+ int(CurlHttpVersion.V2_PRIOR_KNOWLEDGE): "HTTP/2",
+ int(CurlHttpVersion.V3): "HTTP/3",
+ int(CurlHttpVersion.V3ONLY): "HTTP/3",
+ }
+
+ async def log_response(self, response: SXNG_Response):
request = response.request
- status = f"{response.status_code} {response.reason_phrase}"
- response_line = f"{response.http_version} {status}"
+ http_version = self._HTTP_VERSION.get(response.http_version, str(response.http_version))
+ status = f"{response.status_code} {response.reason}"
+ response_line = f"{http_version} {status}"
content_type = response.headers.get("Content-Type")
content_type = f' ({content_type})' if content_type else ''
- self._logger.debug(f'HTTP Request: {request.method} {request.url} "{response_line}"{content_type}')
+ method = request.method if request else "?"
+ url = request.url if request else response.url
+ self._logger.debug(f'HTTP Request: {method} {url} "{response_line}"{content_type}')
@staticmethod
- async def check_tor_proxy(client: httpx.AsyncClient, proxies) -> bool:
+ async def check_tor_proxy(client: AsyncClient, proxies) -> bool:
if proxies in Network._TOR_CHECK_RESULT:
return Network._TOR_CHECK_RESULT[proxies]
- result = True
- # ignore client._transport because it is not used with all://
- for transport in client._mounts.values(): # pylint: disable=protected-access
- if isinstance(transport, AsyncHTTPTransportNoHttp):
- continue
- if getattr(transport, "_pool") and getattr(
- # pylint: disable=protected-access
- transport._pool, # type: ignore
- "_rdns",
- False,
- ):
- continue
+ if not proxies or not all(url.startswith('socks5h://') for _, url in proxies):
+ Network._TOR_CHECK_RESULT[proxies] = False
return False
+
response = await client.get("https://check.torproject.org/api/ip", timeout=60)
- if not response.json()["IsTor"]:
- result = False
+ result = bool(response.json()["IsTor"])
Network._TOR_CHECK_RESULT[proxies] = result
return result
- async def get_client(self, verify: bool | None = None, max_redirects: int | None = None) -> httpx.AsyncClient:
+ async def get_client(
+ self,
+ verify: bool | None = None,
+ max_redirects: int | None = None,
+ impersonate: str | None = None,
+ curl_options: dict[int, t.Any] | None = None,
+ enable_http3: bool | None = None,
+ ) -> AsyncClient:
verify = self.verify if verify is None else verify
max_redirects = self.max_redirects if max_redirects is None else max_redirects
+ impersonate = impersonate or DEFAULT_IMPERSONATE
+ enable_http3 = self.enable_http3 if enable_http3 is None else enable_http3
local_address = next(self._local_addresses_cycle)
proxies = next(self._proxies_cycle) # is a tuple so it can be part of the key
- key = (verify, max_redirects, local_address, proxies)
- hook_log_response = self.log_response if sxng_debug else None
+ curl_key = tuple(sorted((int(k), v) for k, v in (curl_options or {}).items()))
+ key = (verify, max_redirects, local_address, proxies, impersonate, curl_key, enable_http3)
if key not in self._clients or self._clients[key].is_closed:
client = new_client(
self.enable_http,
verify,
self.enable_http2,
+ enable_http3,
self.max_connections,
- self.max_keepalive_connections,
- self.keepalive_expiry,
dict(proxies),
local_address,
- 0,
max_redirects,
- hook_log_response,
+ impersonate=impersonate,
+ curl_options=curl_options,
)
if self.using_tor_proxy and not await self.check_tor_proxy(client, proxies):
await client.aclose()
- raise httpx.ProxyError('Network configuration problem: not using Tor')
+ raise ProxyError('Network configuration problem: not using Tor')
self._clients[key] = client
return self._clients[key]
@@ -218,22 +231,14 @@ class Network:
async def close_client(client):
try:
await client.aclose()
- except httpx.HTTPError:
+ except RequestException:
pass
await asyncio.gather(*[close_client(client) for client in self._clients.values()], return_exceptions=False)
@staticmethod
def extract_kwargs_clients(kwargs: dict[str, t.Any]) -> dict[str, t.Any]:
- kwargs_clients: dict[str, t.Any] = {}
- if 'verify' in kwargs:
- kwargs_clients['verify'] = kwargs.pop('verify')
- if 'max_redirects' in kwargs:
- kwargs_clients['max_redirects'] = kwargs.pop('max_redirects')
- if 'allow_redirects' in kwargs:
- # see https://github.com/encode/httpx/pull/1808
- kwargs['follow_redirects'] = kwargs.pop('allow_redirects')
- return kwargs_clients
+ return {key: kwargs.pop(key) for key in Network._CLIENT_KWARGS if key in kwargs}
@staticmethod
def extract_do_raise_for_httperror(kwargs: dict[str, t.Any]):
@@ -243,23 +248,18 @@ class Network:
del kwargs['raise_for_httperror']
return do_raise_for_httperror
- def patch_response(self, response: httpx.Response, do_raise_for_httperror: bool) -> SXNG_Response:
- if isinstance(response, httpx.Response):
- response = t.cast(SXNG_Response, response)
- # requests compatibility (response is not streamed)
- # see also https://www.python-httpx.org/compatibility/#checking-for-4xx5xx-responses
- response.ok = not response.is_error
-
- # raise an exception
- if do_raise_for_httperror:
- try:
- raise_for_httperror(response)
- except:
- self._logger.warning(f"HTTP Request failed: {response.request.method} {response.request.url}")
- raise
+ def patch_response(self, response: SXNG_Response, do_raise_for_httperror: bool) -> SXNG_Response:
+ if do_raise_for_httperror:
+ try:
+ raise_for_httperror(response)
+ except:
+ method = response.request.method if response.request else "?"
+ url = response.request.url if response.request else response.url
+ self._logger.warning(f"HTTP Request failed: {method} {url}")
+ raise
return response
- def is_valid_response(self, response: httpx.Response):
+ def is_valid_response(self, response: SXNG_Response):
# pylint: disable=too-many-boolean-expressions
if (
(self.retry_on_http_error is True and 400 <= response.status_code <= 599)
@@ -276,26 +276,29 @@ class Network:
kwargs_clients = Network.extract_kwargs_clients(kwargs)
while retries >= 0: # pragma: no cover
client = await self.get_client(**kwargs_clients)
- cookies = kwargs.pop("cookies", None)
- client.cookies = httpx.Cookies(cookies)
try:
+ method = method.upper()
+ client.check_url(url)
if stream:
return client.stream(method, url, **kwargs)
response = await client.request(method, url, **kwargs)
+ if sxng_debug:
+ await self.log_response(response)
if self.is_valid_response(response) or retries <= 0:
return self.patch_response(response, do_raise_for_httperror)
- except httpx.RemoteProtocolError as e:
+ await client.aclose()
+ except CurlConnectionError as e:
if not was_disconnected:
# the server has closed the connection:
# try again without decreasing the retries variable & with a new HTTP client
was_disconnected = True
await client.aclose()
- self._logger.warning('httpx.RemoteProtocolError: the server has disconnected, retrying')
+ self._logger.warning('ConnectionError: the server has disconnected, retrying')
continue
if retries <= 0:
raise e
- except (httpx.RequestError, httpx.HTTPStatusError) as e:
+ except RequestException as e:
if retries <= 0:
raise e
retries -= 1
@@ -346,15 +349,12 @@ def initialize(
settings_engines = settings_engines or settings['engines']
settings_outgoing = settings_outgoing or settings['outgoing']
- # default parameters for AsyncHTTPTransport
- # see https://github.com/encode/httpx/blob/e05a5372eb6172287458b37447c30f650047e1b8/httpx/_transports/default.py#L108-L121 # pylint: disable=line-too-long
default_params: dict[str, t.Any] = {
'enable_http': False,
'verify': settings_outgoing['verify'],
'enable_http2': settings_outgoing['enable_http2'],
+ 'enable_http3': False,
'max_connections': settings_outgoing['pool_connections'],
- 'max_keepalive_connections': settings_outgoing['pool_maxsize'],
- 'keepalive_expiry': settings_outgoing['keepalive_expiry'],
'local_addresses': settings_outgoing['source_ips'],
'using_tor_proxy': settings_outgoing['using_tor_proxy'],
'proxies': settings_outgoing['proxies'],
@@ -424,9 +424,6 @@ def initialize(
def done():
"""Close all HTTP client
- Avoid a warning at exit
- See https://github.com/encode/httpx/pull/2026
-
Note: since Network.aclose has to be async, it is not possible to call this method on Network.__del__
So Network.aclose is called here using atexit.register
"""
diff --git a/searx/network/raise_for_httperror.py b/searx/network/raise_for_httperror.py
index d50e650e2..f4f409c99 100644
--- a/searx/network/raise_for_httperror.py
+++ b/searx/network/raise_for_httperror.py
@@ -59,13 +59,10 @@ def raise_for_captcha(resp: "SXNG_Response"):
def raise_for_httperror(resp: "SXNG_Response") -> None:
- """Raise exception for an HTTP response is an error.
-
- Args:
- resp (requests.Response): Response to check
+ """Raise an exception if the HTTP response is an error.
Raises:
- requests.HTTPError: raise by resp.raise_for_status()
+ curl_cffi.requests.exceptions.HTTPError: raised by resp.raise_for_status()
searx.exceptions.SearxEngineAccessDeniedException: raise when the HTTP status code is 402 or 403.
searx.exceptions.SearxEngineTooManyRequestsException: raise when the HTTP status code is 429.
searx.exceptions.SearxEngineCaptchaException: raise when if CATPCHA challenge is detected.