kamp/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-11-22 12:10:11 +01:00
Code

Merge pull request #94 from return42/pylint-network

Browse Source 
Pylint searx.network
This commit is contained in:
Alexandre Flament 2021-05-26 18:35:29 +02:00 committed by GitHub
commit 7c76cef746
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 163 additions and 100 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
searx/network/__init__.py
View File

@ -1,4 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
# pylint: disable=missing-module-docstring, missing-function-docstring, global-statement
import asyncio
import threading
@ -31,29 +33,33 @@ except ImportError:
self._count.release()
def get(self):
if not self._count.acquire(True):
if not self._count.acquire(True): #pylint: disable=consider-using-with
raise Empty
return self._queue.popleft()
THREADLOCAL = threading.local()
"""Thread-local data is data for thread specific values."""
def reset_time_for_thread():
global THREADLOCAL
THREADLOCAL.total_time = 0
def get_time_for_thread():
"""returns thread's total time or None"""
global THREADLOCAL
return THREADLOCAL.__dict__.get('total_time')
def set_timeout_for_thread(timeout, start_time=None):
global THREADLOCAL
THREADLOCAL.timeout = timeout
THREADLOCAL.start_time = start_time
def set_context_network_name(network_name):
global THREADLOCAL
THREADLOCAL.network = get_network(network_name)
@ -62,11 +68,13 @@ def get_context_network():
If unset, return value from :py:obj:`get_network`.
"""
global THREADLOCAL
return THREADLOCAL.__dict__.get('network') or get_network()
def request(method, url, **kwargs):
"""same as requests/requests/api.py request(...)"""
global THREADLOCAL
time_before_request = default_timer()
# timeout (httpx)
@ -153,18 +161,17 @@ def patch(url, data=None, **kwargs):
def delete(url, **kwargs):
return request('delete', url, **kwargs)
async def stream_chunk_to_queue(network, q, method, url, **kwargs):
async def stream_chunk_to_queue(network, queue, method, url, **kwargs):
try:
async with network.stream(method, url, **kwargs) as response:
q.put(response)
queue.put(response)
async for chunk in response.aiter_bytes(65536):
if len(chunk) > 0:
q.put(chunk)
queue.put(chunk)
except (httpx.HTTPError, OSError, h2.exceptions.ProtocolError) as e:
q.put(e)
queue.put(e)
finally:
q.put(None)
queue.put(None)
def stream(method, url, **kwargs):
@ -179,13 +186,15 @@ def stream(method, url, **kwargs):
httpx.Client.stream requires to write the httpx.HTTPTransport version of the
the httpx.AsyncHTTPTransport declared above.
"""
q = SimpleQueue()
future = asyncio.run_coroutine_threadsafe(stream_chunk_to_queue(get_network(), q, method, url, **kwargs),
get_loop())
chunk_or_exception = q.get()
queue = SimpleQueue()
future = asyncio.run_coroutine_threadsafe(
stream_chunk_to_queue(get_network(), queue, method, url, **kwargs),
get_loop()
)
chunk_or_exception = queue.get()
while chunk_or_exception is not None:
if isinstance(chunk_or_exception, Exception):
raise chunk_or_exception
yield chunk_or_exception
chunk_or_exception = q.get()
chunk_or_exception = queue.get()
return future.result()

105
searx/network/client.py
View File

@ -1,14 +1,19 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
# pylint: disable=missing-module-docstring, missing-function-docstring, global-statement
import asyncio
import logging
import threading
import httpcore
import httpx
from httpx_socks import AsyncProxyTransport
from python_socks import parse_proxy_url
import python_socks._errors
from python_socks import (
parse_proxy_url,
ProxyConnectionError,
ProxyTimeoutError,
ProxyError
)
from searx import logger
@ -30,7 +35,11 @@ TRANSPORT_KWARGS = {
}
async def close_connections_for_url(connection_pool: httpcore.AsyncConnectionPool, url: httpcore._utils.URL):
# pylint: disable=protected-access
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)
connections_to_close = connection_pool._connections_for_origin(origin)
@ -40,6 +49,7 @@ async def close_connections_for_url(connection_pool: httpcore.AsyncConnectionPoo
await connection.aclose()
except httpcore.NetworkError as e:
logger.warning('Error closing an existing connection', exc_info=e)
# pylint: enable=protected-access
def get_sslcontexts(proxy_url=None, cert=None, verify=True, trust_env=True, http2=False):
@ -80,9 +90,7 @@ class AsyncProxyTransportFixed(AsyncProxyTransport):
retry -= 1
try:
return await super().arequest(method, url, headers, stream, ext)
except (python_socks._errors.ProxyConnectionError,
python_socks._errors.ProxyTimeoutError,
python_socks._errors.ProxyError) as e:
except (ProxyConnectionError, ProxyTimeoutError, ProxyError) as e:
raise httpcore.ProxyError(e)
except OSError as e:
# socket.gaierror when DNS resolution fails
@ -114,7 +122,7 @@ class AsyncHTTPTransportFixed(httpx.AsyncHTTPTransport):
except httpcore.CloseError as e:
# httpcore.CloseError: [Errno 104] Connection reset by peer
# raised by _keepalive_sweep()
# from https://github.com/encode/httpcore/blob/4b662b5c42378a61e54d673b4c949420102379f5/httpcore/_backends/asyncio.py#L198 # noqa
# from https://github.com/encode/httpcore/blob/4b662b5c42378a61e54d673b4c949420102379f5/httpcore/_backends/asyncio.py#L198 # pylint: disable=line-too-long
await close_connections_for_url(self._pool, url)
logger.warning('httpcore.CloseError: retry', exc_info=e)
# retry
@ -129,6 +137,7 @@ class AsyncHTTPTransportFixed(httpx.AsyncHTTPTransport):
def get_transport_for_socks_proxy(verify, http2, local_address, proxy_url, limit, retries):
global TRANSPORT_KWARGS
# support socks5h (requests compatibility):
# https://requests.readthedocs.io/en/master/user/advanced/#socks
# socks5:// hostname is resolved on client side
@ -141,29 +150,35 @@ def get_transport_for_socks_proxy(verify, http2, local_address, proxy_url, limit
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,
rdns=rdns,
loop=get_loop(),
verify=verify,
http2=http2,
local_address=local_address,
max_connections=limit.max_connections,
max_keepalive_connections=limit.max_keepalive_connections,
keepalive_expiry=limit.keepalive_expiry,
retries=retries,
**TRANSPORT_KWARGS)
return AsyncProxyTransportFixed(
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,
http2=http2,
local_address=local_address,
max_connections=limit.max_connections,
max_keepalive_connections=limit.max_keepalive_connections,
keepalive_expiry=limit.keepalive_expiry,
retries=retries,
**TRANSPORT_KWARGS
)
def get_transport(verify, http2, local_address, proxy_url, limit, retries):
global TRANSPORT_KWARGS
verify = get_sslcontexts(None, None, True, False, http2) if verify is True else verify
return AsyncHTTPTransportFixed(verify=verify,
http2=http2,
local_address=local_address,
proxy=httpx._config.Proxy(proxy_url) if proxy_url else None,
limits=limit,
retries=retries,
**TRANSPORT_KWARGS)
return AsyncHTTPTransportFixed(
# pylint: disable=protected-access
verify=verify,
http2=http2,
local_address=local_address,
proxy=httpx._config.Proxy(proxy_url) if proxy_url else None,
limits=limit,
retries=retries,
**TRANSPORT_KWARGS
)
def iter_proxies(proxies):
@ -175,24 +190,32 @@ def iter_proxies(proxies):
yield pattern, proxy_url
def new_client(enable_http, verify, enable_http2,
max_connections, max_keepalive_connections, keepalive_expiry,
proxies, local_address, retries, max_redirects):
limit = httpx.Limits(max_connections=max_connections,
max_keepalive_connections=max_keepalive_connections,
keepalive_expiry=keepalive_expiry)
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 ):
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 = {}
for pattern, proxy_url in iter_proxies(proxies):
if not enable_http and (pattern == 'http' or 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)
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()
@ -217,12 +240,12 @@ def init():
LOOP = asyncio.new_event_loop()
LOOP.run_forever()
th = threading.Thread(
thread = threading.Thread(
target=loop_thread,
name='asyncio_loop',
daemon=True,
)
th.start()
thread.start()
init()

79
searx/network/network.py
View File

@ -1,4 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
# pylint: disable=global-statement
# pylint: disable=missing-module-docstring, missing-class-docstring, missing-function-docstring
import atexit
import asyncio
@ -34,23 +37,28 @@ ADDRESS_MAPPING = {
class Network:
__slots__ = ('enable_http', 'verify', 'enable_http2',
'max_connections', 'max_keepalive_connections', 'keepalive_expiry',
'local_addresses', 'proxies', 'max_redirects', 'retries', 'retry_on_http_error',
'_local_addresses_cycle', '_proxies_cycle', '_clients')
__slots__ = (
'enable_http', 'verify', 'enable_http2',
'max_connections', 'max_keepalive_connections', 'keepalive_expiry',
'local_addresses', 'proxies', 'max_redirects', 'retries', 'retry_on_http_error',
'_local_addresses_cycle', '_proxies_cycle', '_clients'
)
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,
local_addresses=None,
retries=0,
retry_on_http_error=None,
max_redirects=30 ):
def __init__(self,
enable_http=True,
verify=True,
enable_http2=False,
max_connections=None,
max_keepalive_connections=None,
keepalive_expiry=None,
proxies=None,
local_addresses=None,
retries=0,
retry_on_http_error=None,
max_redirects=30):
self.enable_http = enable_http
self.verify = verify
self.enable_http2 = enable_http2
@ -81,7 +89,7 @@ class Network:
local_addresses = self.local_addresses
if not local_addresses:
return
elif isinstance(local_addresses, str):
if isinstance(local_addresses, str):
local_addresses = [local_addresses]
for address in local_addresses:
yield address
@ -119,6 +127,7 @@ class Network:
for pattern, proxy_urls in self.iter_proxies():
proxy_settings[pattern] = cycle(proxy_urls)
while True:
# pylint: disable=stop-iteration-return
yield tuple((pattern, next(proxy_url_cycle)) for pattern, proxy_url_cycle in proxy_settings.items())
def get_client(self, verify=None, max_redirects=None):
@ -128,16 +137,18 @@ class Network:
proxies = next(self._proxies_cycle) # is a tuple so it can be part of the key
key = (verify, max_redirects, local_address, proxies)
if key not in self._clients or self._clients[key].is_closed:
self._clients[key] = new_client(self.enable_http,
verify,
self.enable_http2,
self.max_connections,
self.max_keepalive_connections,
self.keepalive_expiry,
dict(proxies),
local_address,
0,
max_redirects)
self._clients[key] = new_client(
self.enable_http,
verify,
self.enable_http2,
self.max_connections,
self.max_keepalive_connections,
self.keepalive_expiry,
dict(proxies),
local_address,
0,
max_redirects
)
return self._clients[key]
async def aclose(self):
@ -158,9 +169,11 @@ class Network:
return kwargs_clients
def is_valid_respones(self, response):
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):
# pylint: disable=too-many-boolean-expressions
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)
):
return False
return True
@ -194,6 +207,7 @@ class Network:
@classmethod
async def aclose_all(cls):
global NETWORKS
await asyncio.gather(*[network.aclose() for network in NETWORKS.values()], return_exceptions=False)
@ -203,8 +217,10 @@ def get_network(name=None):
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)
global NETWORKS
@ -212,7 +228,7 @@ def initialize(settings_engines=None, settings_outgoing=None):
settings_outgoing = settings_outgoing or settings.get('outgoing')
# default parameters for AsyncHTTPTransport
# see https://github.com/encode/httpx/blob/e05a5372eb6172287458b37447c30f650047e1b8/httpx/_transports/default.py#L108-L121 # noqa
# see https://github.com/encode/httpx/blob/e05a5372eb6172287458b37447c30f650047e1b8/httpx/_transports/default.py#L108-L121 # pylint: disable=line-too-long
default_params = {
'enable_http': False,
'verify': True,
@ -290,6 +306,7 @@ def done():
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
"""
global NETWORKS
try:
loop = get_loop()
if loop:

44
searx/network/raise_for_httperror.py
View File

@ -1,17 +1,23 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Raise exception for an HTTP response is an error.
"""
from searx.exceptions import (SearxEngineCaptchaException, SearxEngineTooManyRequestsException,
SearxEngineAccessDeniedException)
# lint: pylint
# pylint: disable=missing-function-docstring
"""Raise exception for an HTTP response is an error.
"""
from searx.exceptions import (
SearxEngineCaptchaException,
SearxEngineTooManyRequestsException,
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
@ -27,15 +33,21 @@ 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)
@ -59,8 +71,10 @@ def raise_for_httperror(resp):
if resp.status_code and resp.status_code >= 400:
raise_for_captcha(resp)
if resp.status_code in (402, 403):
raise SearxEngineAccessDeniedException(message='HTTP error ' + str(resp.status_code),
suspended_time=3600 * 24)
raise SearxEngineAccessDeniedException(
message='HTTP error ' + str(resp.status_code),
suspended_time=3600 * 24
)
if resp.status_code == 429:
raise SearxEngineTooManyRequestsException()
resp.raise_for_status()