diff options
author | Markus Heiser <markus.heiser@darmarit.de> | 2021-12-27 09:26:22 +0100 |
---|---|---|
committer | Markus Heiser <markus.heiser@darmarit.de> | 2021-12-27 09:26:22 +0100 |
commit | 3d96a9839a12649874b6d4cf9466bd3616b0a03c (patch) | |
tree | e7d54d1e345b1e792d538ddc250f4827bb2fd9b9 /searx/network | |
parent | fcdc2c2cd26e24c2aa3f064d93cee3e29dc2a30c (diff) | |
download | searxng-3d96a9839a12649874b6d4cf9466bd3616b0a03c.tar.gz searxng-3d96a9839a12649874b6d4cf9466bd3616b0a03c.zip |
[format.python] initial formatting of the python code
This patch was generated by black [1]::
make format.python
[1] https://github.com/psf/black
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
Diffstat (limited to 'searx/network')
-rw-r--r-- | searx/network/__init__.py | 13 | ||||
-rw-r--r-- | searx/network/client.py | 68 | ||||
-rw-r--r-- | searx/network/network.py | 68 | ||||
-rw-r--r-- | searx/network/raise_for_httperror.py | 27 |
4 files changed, 86 insertions, 90 deletions
diff --git a/searx/network/__init__.py b/searx/network/__init__.py index 82959e355..7d02a0014 100644 --- a/searx/network/__init__.py +++ b/searx/network/__init__.py @@ -35,7 +35,7 @@ except ImportError: self._count.release() def get(self): - if not self._count.acquire(True): #pylint: disable=consider-using-with + if not self._count.acquire(True): # pylint: disable=consider-using-with raise Empty return self._queue.popleft() @@ -43,6 +43,7 @@ except ImportError: THREADLOCAL = threading.local() """Thread-local data is data for thread specific values.""" + def reset_time_for_thread(): THREADLOCAL.total_time = 0 @@ -187,10 +188,7 @@ async def stream_chunk_to_queue(network, queue, method, url, **kwargs): def _stream_generator(method, url, **kwargs): queue = SimpleQueue() network = get_context_network() - future = asyncio.run_coroutine_threadsafe( - stream_chunk_to_queue(network, queue, method, url, **kwargs), - get_loop() - ) + future = asyncio.run_coroutine_threadsafe(stream_chunk_to_queue(network, queue, method, url, **kwargs), get_loop()) # yield chunks obj_or_exception = queue.get() @@ -203,10 +201,7 @@ def _stream_generator(method, url, **kwargs): def _close_response_method(self): - asyncio.run_coroutine_threadsafe( - self.aclose(), - get_loop() - ) + 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) diff --git a/searx/network/client.py b/searx/network/client.py index a6cec352d..cd1e41460 100644 --- a/searx/network/client.py +++ b/searx/network/client.py @@ -10,12 +10,7 @@ import anyio import httpcore import httpx from httpx_socks import AsyncProxyTransport -from python_socks import ( - parse_proxy_url, - ProxyConnectionError, - ProxyTimeoutError, - ProxyError -) +from python_socks import parse_proxy_url, ProxyConnectionError, ProxyTimeoutError, ProxyError from searx import logger @@ -41,9 +36,7 @@ TRANSPORT_KWARGS = { # pylint: disable=protected-access -async def close_connections_for_url( - connection_pool: httpcore.AsyncConnectionPool, url: httpcore._utils.URL -): +async def close_connections_for_url(connection_pool: httpcore.AsyncConnectionPool, url: httpcore._utils.URL): origin = httpcore._utils.url_to_origin(url) logger.debug('Drop connections for %r', origin) @@ -54,6 +47,8 @@ async def close_connections_for_url( await connection.aclose() except httpx.NetworkError as e: logger.warning('Error closing an existing connection', exc_info=e) + + # pylint: enable=protected-access @@ -67,9 +62,7 @@ def get_sslcontexts(proxy_url=None, cert=None, verify=True, trust_env=True, http class AsyncHTTPTransportNoHttp(httpx.AsyncHTTPTransport): """Block HTTP request""" - async def handle_async_request( - self, method, url, headers=None, stream=None, extensions=None - ): + async def handle_async_request(self, method, url, headers=None, stream=None, extensions=None): raise httpx.UnsupportedProtocol('HTTP protocol is disabled') @@ -83,9 +76,7 @@ class AsyncProxyTransportFixed(AsyncProxyTransport): Note: AsyncProxyTransport inherit from AsyncConnectionPool """ - async def handle_async_request( - self, method, url, headers=None, stream=None, extensions=None - ): + async def handle_async_request(self, method, url, headers=None, stream=None, extensions=None): retry = 2 while retry > 0: retry -= 1 @@ -116,9 +107,7 @@ class AsyncProxyTransportFixed(AsyncProxyTransport): class AsyncHTTPTransportFixed(httpx.AsyncHTTPTransport): """Fix httpx.AsyncHTTPTransport""" - async def handle_async_request( - self, method, url, headers=None, stream=None, extensions=None - ): + async def handle_async_request(self, method, url, headers=None, stream=None, extensions=None): retry = 2 while retry > 0: retry -= 1 @@ -152,14 +141,17 @@ def get_transport_for_socks_proxy(verify, http2, local_address, proxy_url, limit rdns = False socks5h = 'socks5h://' if proxy_url.startswith(socks5h): - proxy_url = 'socks5://' + proxy_url[len(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, True, False, http2) 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, + proxy_type=proxy_type, + proxy_host=proxy_host, + proxy_port=proxy_port, + username=proxy_username, + password=proxy_password, rdns=rdns, loop=get_loop(), verify=verify, @@ -169,7 +161,7 @@ def get_transport_for_socks_proxy(verify, http2, local_address, proxy_url, limit max_keepalive_connections=limit.max_keepalive_connections, keepalive_expiry=limit.keepalive_expiry, retries=retries, - **TRANSPORT_KWARGS + **TRANSPORT_KWARGS, ) @@ -183,36 +175,40 @@ def get_transport(verify, http2, local_address, proxy_url, limit, retries): proxy=httpx._config.Proxy(proxy_url) if proxy_url else None, limits=limit, retries=retries, - **TRANSPORT_KWARGS + **TRANSPORT_KWARGS, ) def new_client( - # pylint: disable=too-many-arguments - enable_http, verify, enable_http2, - max_connections, max_keepalive_connections, keepalive_expiry, - proxies, local_address, retries, max_redirects, hook_log_response ): + # pylint: disable=too-many-arguments + enable_http, + verify, + enable_http2, + max_connections, + max_keepalive_connections, + keepalive_expiry, + proxies, + local_address, + retries, + max_redirects, + hook_log_response, +): limit = httpx.Limits( max_connections=max_connections, max_keepalive_connections=max_keepalive_connections, - keepalive_expiry=keepalive_expiry + keepalive_expiry=keepalive_expiry, ) # See https://www.python-httpx.org/advanced/#routing mounts = {} 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://') - ): + 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 - ) + mounts[pattern] = get_transport(verify, enable_http2, local_address, proxy_url, limit, retries) if not enable_http: mounts['http://'] = AsyncHTTPTransportNoHttp() @@ -221,7 +217,7 @@ def new_client( event_hooks = None if hook_log_response: - event_hooks = {'response': [ hook_log_response ]} + event_hooks = {'response': [hook_log_response]} return httpx.AsyncClient( transport=transport, diff --git a/searx/network/network.py b/searx/network/network.py index 613b9ff27..9e14e14bd 100644 --- a/searx/network/network.py +++ b/searx/network/network.py @@ -31,39 +31,49 @@ PROXY_PATTERN_MAPPING = { 'socks5h:': 'socks5h://', } -ADDRESS_MAPPING = { - 'ipv4': '0.0.0.0', - 'ipv6': '::' -} +ADDRESS_MAPPING = {'ipv4': '0.0.0.0', 'ipv6': '::'} class Network: __slots__ = ( - 'enable_http', 'verify', 'enable_http2', - 'max_connections', 'max_keepalive_connections', 'keepalive_expiry', - 'local_addresses', 'proxies', 'using_tor_proxy', 'max_redirects', 'retries', 'retry_on_http_error', - '_local_addresses_cycle', '_proxies_cycle', '_clients', '_logger' + 'enable_http', + 'verify', + 'enable_http2', + 'max_connections', + 'max_keepalive_connections', + 'keepalive_expiry', + 'local_addresses', + 'proxies', + 'using_tor_proxy', + 'max_redirects', + 'retries', + 'retry_on_http_error', + '_local_addresses_cycle', + '_proxies_cycle', + '_clients', + '_logger', ) _TOR_CHECK_RESULT = {} def __init__( - # pylint: disable=too-many-arguments - self, - enable_http=True, - verify=True, - enable_http2=False, - max_connections=None, - max_keepalive_connections=None, - keepalive_expiry=None, - proxies=None, - using_tor_proxy=False, - local_addresses=None, - retries=0, - retry_on_http_error=None, - max_redirects=30, - logger_name=None): + # pylint: disable=too-many-arguments + self, + enable_http=True, + verify=True, + enable_http2=False, + max_connections=None, + max_keepalive_connections=None, + keepalive_expiry=None, + proxies=None, + using_tor_proxy=False, + local_addresses=None, + retries=0, + retry_on_http_error=None, + max_redirects=30, + logger_name=None, + ): self.enable_http = enable_http self.verify = verify @@ -144,9 +154,7 @@ class Network: response_line = f"{response.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}' - ) + self._logger.debug(f'HTTP Request: {request.method} {request.url} "{response_line}"{content_type}') @staticmethod async def check_tor_proxy(client: httpx.AsyncClient, proxies) -> bool: @@ -187,7 +195,7 @@ class Network: local_address, 0, max_redirects, - hook_log_response + hook_log_response, ) if self.using_tor_proxy and not await self.check_tor_proxy(client, proxies): await client.aclose() @@ -201,6 +209,7 @@ class Network: await client.aclose() except httpx.HTTPError: pass + await asyncio.gather(*[close_client(client) for client in self._clients.values()], return_exceptions=False) @staticmethod @@ -214,7 +223,8 @@ class Network: def is_valid_respones(self, response): # pylint: disable=too-many-boolean-expressions - if ((self.retry_on_http_error is True and 400 <= response.status_code <= 599) + if ( + (self.retry_on_http_error is True and 400 <= response.status_code <= 599) or (isinstance(self.retry_on_http_error, list) and response.status_code in self.retry_on_http_error) or (isinstance(self.retry_on_http_error, int) and response.status_code == self.retry_on_http_error) ): @@ -269,6 +279,7 @@ def check_network_configuration(): network._logger.exception('Error') # pylint: disable=protected-access exception_count += 1 return exception_count + future = asyncio.run_coroutine_threadsafe(check(), get_loop()) exception_count = future.result() if exception_count > 0: @@ -279,6 +290,7 @@ def initialize(settings_engines=None, settings_outgoing=None): # pylint: disable=import-outside-toplevel) from searx.engines import engines from searx import settings + # pylint: enable=import-outside-toplevel) settings_engines = settings_engines or settings['engines'] diff --git a/searx/network/raise_for_httperror.py b/searx/network/raise_for_httperror.py index a2f554614..414074977 100644 --- a/searx/network/raise_for_httperror.py +++ b/searx/network/raise_for_httperror.py @@ -10,13 +10,14 @@ from searx.exceptions import ( SearxEngineAccessDeniedException, ) + def is_cloudflare_challenge(resp): if resp.status_code in [429, 503]: - if (('__cf_chl_jschl_tk__=' in resp.text) - or ('/cdn-cgi/challenge-platform/' in resp.text - and 'orchestrate/jsch/v1' in resp.text - and 'window._cf_chl_enter(' in resp.text - )): + if ('__cf_chl_jschl_tk__=' in resp.text) or ( + '/cdn-cgi/challenge-platform/' in resp.text + and 'orchestrate/jsch/v1' in resp.text + and 'window._cf_chl_enter(' in resp.text + ): return True if resp.status_code == 403 and '__cf_chl_captcha_tk__=' in resp.text: return True @@ -32,21 +33,14 @@ def raise_for_cloudflare_captcha(resp): if is_cloudflare_challenge(resp): # https://support.cloudflare.com/hc/en-us/articles/200170136-Understanding-Cloudflare-Challenge-Passage-Captcha- # suspend for 2 weeks - raise SearxEngineCaptchaException( - message='Cloudflare CAPTCHA', - suspended_time=3600 * 24 * 15 - ) + raise SearxEngineCaptchaException(message='Cloudflare CAPTCHA', suspended_time=3600 * 24 * 15) if is_cloudflare_firewall(resp): - raise SearxEngineAccessDeniedException( - message='Cloudflare Firewall', suspended_time=3600 * 24 - ) + raise SearxEngineAccessDeniedException(message='Cloudflare Firewall', suspended_time=3600 * 24) def raise_for_recaptcha(resp): - if (resp.status_code == 503 - and '"https://www.google.com/recaptcha/' in resp.text - ): + if resp.status_code == 503 and '"https://www.google.com/recaptcha/' in resp.text: raise SearxEngineCaptchaException(message='ReCAPTCHA', suspended_time=3600 * 24 * 7) @@ -71,8 +65,7 @@ def raise_for_httperror(resp): raise_for_captcha(resp) if resp.status_code in (402, 403): raise SearxEngineAccessDeniedException( - message='HTTP error ' + str(resp.status_code), - suspended_time=3600 * 24 + message='HTTP error ' + str(resp.status_code), suspended_time=3600 * 24 ) if resp.status_code == 429: raise SearxEngineTooManyRequestsException() |