mirror of
https://github.com/FlareSolverr/FlareSolverr.git
synced 2025-06-08 20:45:27 +00:00
Update undetected-chromedriver
This commit is contained in:
parent
7d84f1b663
commit
e163019f28
@ -4,6 +4,7 @@
|
|||||||
|
|
||||||
* Kill Chromium processes properly to avoid defunct/zombie processes
|
* Kill Chromium processes properly to avoid defunct/zombie processes
|
||||||
* Include procps (ps), curl and vim packages in the Docker image
|
* Include procps (ps), curl and vim packages in the Docker image
|
||||||
|
* Update undetected-chromedriver
|
||||||
|
|
||||||
## v3.0.0 (2023/01/04)
|
## v3.0.0 (2023/01/04)
|
||||||
|
|
||||||
|
@ -1,9 +1,9 @@
|
|||||||
bottle==0.12.23
|
bottle==0.12.23
|
||||||
waitress==2.1.2
|
waitress==2.1.2
|
||||||
selenium==4.4.3
|
selenium==4.7.2
|
||||||
func-timeout==4.3.5
|
func-timeout==4.3.5
|
||||||
# required by undetected_chromedriver
|
# required by undetected_chromedriver
|
||||||
requests==2.28.1
|
requests==2.28.1
|
||||||
websockets==10.3
|
websockets==10.4
|
||||||
# only required for linux
|
# only required for linux
|
||||||
xvfbwrapper==0.2.9
|
xvfbwrapper==0.2.9
|
||||||
|
@ -1,7 +1,4 @@
|
|||||||
#!/usr/bin/env python3
|
#!/usr/bin/env python3
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import subprocess
|
|
||||||
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
@ -17,33 +14,38 @@ Y88b. 888 888 888 Y88..88P 888 888 888 Y8b. Y88b 888 888 888 Y
|
|||||||
by UltrafunkAmsterdam (https://github.com/ultrafunkamsterdam)
|
by UltrafunkAmsterdam (https://github.com/ultrafunkamsterdam)
|
||||||
|
|
||||||
"""
|
"""
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
|
||||||
__version__ = "3.1.5r4"
|
__version__ = "3.2.1"
|
||||||
|
|
||||||
|
|
||||||
import json
|
import json
|
||||||
import logging
|
import logging
|
||||||
import os
|
import os
|
||||||
import re
|
import re
|
||||||
import shutil
|
import shutil
|
||||||
|
import subprocess
|
||||||
import sys
|
import sys
|
||||||
import tempfile
|
import tempfile
|
||||||
import time
|
import time
|
||||||
import inspect
|
from weakref import finalize
|
||||||
import threading
|
|
||||||
|
|
||||||
import selenium.webdriver.chrome.service
|
import selenium.webdriver.chrome.service
|
||||||
import selenium.webdriver.chrome.webdriver
|
import selenium.webdriver.chrome.webdriver
|
||||||
|
from selenium.webdriver.common.by import By
|
||||||
import selenium.webdriver.common.service
|
import selenium.webdriver.common.service
|
||||||
|
import selenium.webdriver.remote.command
|
||||||
import selenium.webdriver.remote.webdriver
|
import selenium.webdriver.remote.webdriver
|
||||||
|
|
||||||
from .cdp import CDP
|
from .cdp import CDP
|
||||||
|
from .dprocess import start_detached
|
||||||
from .options import ChromeOptions
|
from .options import ChromeOptions
|
||||||
from .patcher import IS_POSIX
|
from .patcher import IS_POSIX
|
||||||
from .patcher import Patcher
|
from .patcher import Patcher
|
||||||
from .reactor import Reactor
|
from .reactor import Reactor
|
||||||
from .dprocess import start_detached
|
from .webelement import UCWebElement
|
||||||
|
from .webelement import WebElement
|
||||||
|
|
||||||
|
|
||||||
__all__ = (
|
__all__ = (
|
||||||
"Chrome",
|
"Chrome",
|
||||||
@ -108,6 +110,7 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
port=0,
|
port=0,
|
||||||
enable_cdp_events=False,
|
enable_cdp_events=False,
|
||||||
service_args=None,
|
service_args=None,
|
||||||
|
service_creationflags=None,
|
||||||
desired_capabilities=None,
|
desired_capabilities=None,
|
||||||
advanced_elements=False,
|
advanced_elements=False,
|
||||||
service_log_path=None,
|
service_log_path=None,
|
||||||
@ -117,10 +120,10 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
version_main=None,
|
version_main=None,
|
||||||
patcher_force_close=False,
|
patcher_force_close=False,
|
||||||
suppress_welcome=True,
|
suppress_welcome=True,
|
||||||
use_subprocess=False,
|
use_subprocess=True,
|
||||||
debug=False,
|
debug=False,
|
||||||
windows_headless=False,
|
no_sandbox=True,
|
||||||
**kw
|
**kw,
|
||||||
):
|
):
|
||||||
"""
|
"""
|
||||||
Creates a new instance of the chrome driver.
|
Creates a new instance of the chrome driver.
|
||||||
@ -147,7 +150,9 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
If not specified, make sure the executable's folder is in $PATH
|
If not specified, make sure the executable's folder is in $PATH
|
||||||
|
|
||||||
port: int, optional, default: 0
|
port: int, optional, default: 0
|
||||||
port you would like the service to run, if left as 0, a free port will be found.
|
port to be used by the chromedriver executable, this is NOT the debugger port.
|
||||||
|
leave it at 0 unless you know what you are doing.
|
||||||
|
the default value of 0 automatically picks an available port.
|
||||||
|
|
||||||
enable_cdp_events: bool, default: False
|
enable_cdp_events: bool, default: False
|
||||||
:: currently for chrome only
|
:: currently for chrome only
|
||||||
@ -207,11 +212,12 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
now, in case you are nag-fetishist, or a diagnostics data feeder to google, you can set this to False.
|
now, in case you are nag-fetishist, or a diagnostics data feeder to google, you can set this to False.
|
||||||
Note: if you don't handle the nag screen in time, the browser loses it's connection and throws an Exception.
|
Note: if you don't handle the nag screen in time, the browser loses it's connection and throws an Exception.
|
||||||
|
|
||||||
use_subprocess: bool, optional , default: False,
|
use_subprocess: bool, optional , default: True,
|
||||||
|
|
||||||
False (the default) makes sure Chrome will get it's own process (so no subprocess of chromedriver.exe or python
|
False (the default) makes sure Chrome will get it's own process (so no subprocess of chromedriver.exe or python
|
||||||
This fixes a LOT of issues, like multithreaded run, but mst importantly. shutting corectly after
|
This fixes a LOT of issues, like multithreaded run, but mst importantly. shutting corectly after
|
||||||
program exits or using .quit()
|
program exits or using .quit()
|
||||||
|
you should be knowing what you're doing, and know how python works.
|
||||||
|
|
||||||
unfortunately, there is always an edge case in which one would like to write an single script with the only contents being:
|
unfortunately, there is always an edge case in which one would like to write an single script with the only contents being:
|
||||||
--start script--
|
--start script--
|
||||||
@ -224,7 +230,13 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
in that case you can set this to `True`. The browser will start via subprocess, and will keep running most of times.
|
in that case you can set this to `True`. The browser will start via subprocess, and will keep running most of times.
|
||||||
! setting it to True comes with NO support when being detected. !
|
! setting it to True comes with NO support when being detected. !
|
||||||
|
|
||||||
|
no_sandbox: bool, optional, default=True
|
||||||
|
uses the --no-sandbox option, and additionally does suppress the "unsecure option" status bar
|
||||||
|
this option has a default of True since many people seem to run this as root (....) , and chrome does not start
|
||||||
|
when running as root without using --no-sandbox flag.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
finalize(self, self._ensure_close, self)
|
||||||
self.debug = debug
|
self.debug = debug
|
||||||
patcher = Patcher(
|
patcher = Patcher(
|
||||||
executable_path=driver_executable_path,
|
executable_path=driver_executable_path,
|
||||||
@ -236,7 +248,6 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
if not options:
|
if not options:
|
||||||
options = ChromeOptions()
|
options = ChromeOptions()
|
||||||
|
|
||||||
|
|
||||||
try:
|
try:
|
||||||
if hasattr(options, "_session") and options._session is not None:
|
if hasattr(options, "_session") and options._session is not None:
|
||||||
# prevent reuse of options,
|
# prevent reuse of options,
|
||||||
@ -248,11 +259,17 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
|
|
||||||
options._session = self
|
options._session = self
|
||||||
|
|
||||||
debug_port = selenium.webdriver.common.service.utils.free_port()
|
|
||||||
debug_host = "127.0.0.1"
|
|
||||||
|
|
||||||
if not options.debugger_address:
|
if not options.debugger_address:
|
||||||
|
debug_port = (
|
||||||
|
port
|
||||||
|
if port != 0
|
||||||
|
else selenium.webdriver.common.service.utils.free_port()
|
||||||
|
)
|
||||||
|
debug_host = "127.0.0.1"
|
||||||
options.debugger_address = "%s:%d" % (debug_host, debug_port)
|
options.debugger_address = "%s:%d" % (debug_host, debug_port)
|
||||||
|
else:
|
||||||
|
debug_host, debug_port = options.debugger_address.split(":")
|
||||||
|
debug_port = int(debug_port)
|
||||||
|
|
||||||
if enable_cdp_events:
|
if enable_cdp_events:
|
||||||
options.set_capability(
|
options.set_capability(
|
||||||
@ -263,13 +280,12 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
options.add_argument("--remote-debugging-port=%s" % debug_port)
|
options.add_argument("--remote-debugging-port=%s" % debug_port)
|
||||||
|
|
||||||
if user_data_dir:
|
if user_data_dir:
|
||||||
options.add_argument('--user-data-dir=%s' % user_data_dir)
|
options.add_argument("--user-data-dir=%s" % user_data_dir)
|
||||||
|
|
||||||
language, keep_user_data_dir = None, bool(user_data_dir)
|
language, keep_user_data_dir = None, bool(user_data_dir)
|
||||||
|
|
||||||
# see if a custom user profile is specified in options
|
# see if a custom user profile is specified in options
|
||||||
for arg in options.arguments:
|
for arg in options.arguments:
|
||||||
|
|
||||||
if "lang" in arg:
|
if "lang" in arg:
|
||||||
m = re.search("(?:--)?lang(?:[ =])?(.*)", arg)
|
m = re.search("(?:--)?lang(?:[ =])?(.*)", arg)
|
||||||
try:
|
try:
|
||||||
@ -294,7 +310,6 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
)
|
)
|
||||||
|
|
||||||
if not user_data_dir:
|
if not user_data_dir:
|
||||||
|
|
||||||
# backward compatiblity
|
# backward compatiblity
|
||||||
# check if an old uc.ChromeOptions is used, and extract the user data dir
|
# check if an old uc.ChromeOptions is used, and extract the user data dir
|
||||||
|
|
||||||
@ -347,6 +362,8 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
|
|
||||||
if suppress_welcome:
|
if suppress_welcome:
|
||||||
options.arguments.extend(["--no-default-browser-check", "--no-first-run"])
|
options.arguments.extend(["--no-default-browser-check", "--no-first-run"])
|
||||||
|
if no_sandbox:
|
||||||
|
options.arguments.extend(["--no-sandbox", "--test-type"])
|
||||||
if headless or options.headless:
|
if headless or options.headless:
|
||||||
options.headless = True
|
options.headless = True
|
||||||
options.add_argument("--window-size=1920,1080")
|
options.add_argument("--window-size=1920,1080")
|
||||||
@ -360,7 +377,7 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
or divmod(logging.getLogger().getEffectiveLevel(), 10)[0]
|
or divmod(logging.getLogger().getEffectiveLevel(), 10)[0]
|
||||||
)
|
)
|
||||||
|
|
||||||
if hasattr(options, 'handle_prefs'):
|
if hasattr(options, "handle_prefs"):
|
||||||
options.handle_prefs(user_data_dir)
|
options.handle_prefs(user_data_dir)
|
||||||
|
|
||||||
# fix exit_type flag to prevent tab-restore nag
|
# fix exit_type flag to prevent tab-restore nag
|
||||||
@ -376,6 +393,7 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
config["profile"]["exit_type"] = None
|
config["profile"]["exit_type"] = None
|
||||||
fs.seek(0, 0)
|
fs.seek(0, 0)
|
||||||
json.dump(config, fs)
|
json.dump(config, fs)
|
||||||
|
fs.truncate() # the file might be shorter
|
||||||
logger.debug("fixed exit_type flag")
|
logger.debug("fixed exit_type flag")
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.debug("did not find a bad exit_type flag ")
|
logger.debug("did not find a bad exit_type flag ")
|
||||||
@ -385,24 +403,31 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
if not desired_capabilities:
|
if not desired_capabilities:
|
||||||
desired_capabilities = options.to_capabilities()
|
desired_capabilities = options.to_capabilities()
|
||||||
|
|
||||||
if not use_subprocess and not windows_headless:
|
if not use_subprocess:
|
||||||
self.browser_pid = start_detached(
|
self.browser_pid = start_detached(
|
||||||
options.binary_location, *options.arguments
|
options.binary_location, *options.arguments
|
||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
startupinfo = subprocess.STARTUPINFO()
|
|
||||||
if os.name == 'nt' and windows_headless:
|
|
||||||
startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
|
|
||||||
browser = subprocess.Popen(
|
browser = subprocess.Popen(
|
||||||
[options.binary_location, *options.arguments],
|
[options.binary_location, *options.arguments],
|
||||||
stdin=subprocess.PIPE,
|
stdin=subprocess.PIPE,
|
||||||
stdout=subprocess.PIPE,
|
stdout=subprocess.PIPE,
|
||||||
stderr=subprocess.PIPE,
|
stderr=subprocess.PIPE,
|
||||||
close_fds=IS_POSIX,
|
close_fds=IS_POSIX,
|
||||||
startupinfo=startupinfo
|
|
||||||
)
|
)
|
||||||
self.browser_pid = browser.pid
|
self.browser_pid = browser.pid
|
||||||
|
|
||||||
|
if service_creationflags:
|
||||||
|
service = selenium.webdriver.common.service.Service(
|
||||||
|
patcher.executable_path, port, service_args, service_log_path
|
||||||
|
)
|
||||||
|
for attr_name in ("creationflags", "creation_flags"):
|
||||||
|
if hasattr(service, attr_name):
|
||||||
|
setattr(service, attr_name, service_creationflags)
|
||||||
|
break
|
||||||
|
else:
|
||||||
|
service = None
|
||||||
|
|
||||||
super(Chrome, self).__init__(
|
super(Chrome, self).__init__(
|
||||||
executable_path=patcher.executable_path,
|
executable_path=patcher.executable_path,
|
||||||
port=port,
|
port=port,
|
||||||
@ -411,6 +436,7 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
desired_capabilities=desired_capabilities,
|
desired_capabilities=desired_capabilities,
|
||||||
service_log_path=service_log_path,
|
service_log_path=service_log_path,
|
||||||
keep_alive=keep_alive,
|
keep_alive=keep_alive,
|
||||||
|
service=service, # needed or the service will be re-created
|
||||||
)
|
)
|
||||||
|
|
||||||
self.reactor = None
|
self.reactor = None
|
||||||
@ -425,35 +451,14 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
self.reactor = reactor
|
self.reactor = reactor
|
||||||
|
|
||||||
if advanced_elements:
|
if advanced_elements:
|
||||||
from .webelement import WebElement
|
self._web_element_cls = UCWebElement
|
||||||
|
else:
|
||||||
self._web_element_cls = WebElement
|
self._web_element_cls = WebElement
|
||||||
|
|
||||||
if options.headless:
|
if options.headless:
|
||||||
self._configure_headless()
|
self._configure_headless()
|
||||||
|
|
||||||
def __getattribute__(self, item):
|
|
||||||
|
|
||||||
if not super().__getattribute__("debug"):
|
|
||||||
return super().__getattribute__(item)
|
|
||||||
else:
|
|
||||||
import inspect
|
|
||||||
|
|
||||||
original = super().__getattribute__(item)
|
|
||||||
if inspect.ismethod(original) and not inspect.isclass(original):
|
|
||||||
|
|
||||||
def newfunc(*args, **kwargs):
|
|
||||||
logger.debug(
|
|
||||||
"calling %s with args %s and kwargs %s\n"
|
|
||||||
% (original.__qualname__, args, kwargs)
|
|
||||||
)
|
|
||||||
return original(*args, **kwargs)
|
|
||||||
|
|
||||||
return newfunc
|
|
||||||
return original
|
|
||||||
|
|
||||||
def _configure_headless(self):
|
def _configure_headless(self):
|
||||||
|
|
||||||
orig_get = self.get
|
orig_get = self.get
|
||||||
logger.info("setting properties for headless")
|
logger.info("setting properties for headless")
|
||||||
|
|
||||||
@ -494,18 +499,107 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
"Page.addScriptToEvaluateOnNewDocument",
|
"Page.addScriptToEvaluateOnNewDocument",
|
||||||
{
|
{
|
||||||
"source": """
|
"source": """
|
||||||
Object.defineProperty(navigator, 'maxTouchPoints', {
|
Object.defineProperty(navigator, 'maxTouchPoints', {get: () => 1});
|
||||||
get: () => 1
|
Object.defineProperty(navigator.connection, 'rtt', {get: () => 100});
|
||||||
})"""
|
|
||||||
|
// https://github.com/microlinkhq/browserless/blob/master/packages/goto/src/evasions/chrome-runtime.js
|
||||||
|
window.chrome = {
|
||||||
|
app: {
|
||||||
|
isInstalled: false,
|
||||||
|
InstallState: {
|
||||||
|
DISABLED: 'disabled',
|
||||||
|
INSTALLED: 'installed',
|
||||||
|
NOT_INSTALLED: 'not_installed'
|
||||||
|
},
|
||||||
|
RunningState: {
|
||||||
|
CANNOT_RUN: 'cannot_run',
|
||||||
|
READY_TO_RUN: 'ready_to_run',
|
||||||
|
RUNNING: 'running'
|
||||||
|
}
|
||||||
|
},
|
||||||
|
runtime: {
|
||||||
|
OnInstalledReason: {
|
||||||
|
CHROME_UPDATE: 'chrome_update',
|
||||||
|
INSTALL: 'install',
|
||||||
|
SHARED_MODULE_UPDATE: 'shared_module_update',
|
||||||
|
UPDATE: 'update'
|
||||||
|
},
|
||||||
|
OnRestartRequiredReason: {
|
||||||
|
APP_UPDATE: 'app_update',
|
||||||
|
OS_UPDATE: 'os_update',
|
||||||
|
PERIODIC: 'periodic'
|
||||||
|
},
|
||||||
|
PlatformArch: {
|
||||||
|
ARM: 'arm',
|
||||||
|
ARM64: 'arm64',
|
||||||
|
MIPS: 'mips',
|
||||||
|
MIPS64: 'mips64',
|
||||||
|
X86_32: 'x86-32',
|
||||||
|
X86_64: 'x86-64'
|
||||||
|
},
|
||||||
|
PlatformNaclArch: {
|
||||||
|
ARM: 'arm',
|
||||||
|
MIPS: 'mips',
|
||||||
|
MIPS64: 'mips64',
|
||||||
|
X86_32: 'x86-32',
|
||||||
|
X86_64: 'x86-64'
|
||||||
|
},
|
||||||
|
PlatformOs: {
|
||||||
|
ANDROID: 'android',
|
||||||
|
CROS: 'cros',
|
||||||
|
LINUX: 'linux',
|
||||||
|
MAC: 'mac',
|
||||||
|
OPENBSD: 'openbsd',
|
||||||
|
WIN: 'win'
|
||||||
|
},
|
||||||
|
RequestUpdateCheckStatus: {
|
||||||
|
NO_UPDATE: 'no_update',
|
||||||
|
THROTTLED: 'throttled',
|
||||||
|
UPDATE_AVAILABLE: 'update_available'
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// https://github.com/microlinkhq/browserless/blob/master/packages/goto/src/evasions/navigator-permissions.js
|
||||||
|
if (!window.Notification) {
|
||||||
|
window.Notification = {
|
||||||
|
permission: 'denied'
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
const originalQuery = window.navigator.permissions.query
|
||||||
|
window.navigator.permissions.__proto__.query = parameters =>
|
||||||
|
parameters.name === 'notifications'
|
||||||
|
? Promise.resolve({ state: window.Notification.permission })
|
||||||
|
: originalQuery(parameters)
|
||||||
|
|
||||||
|
const oldCall = Function.prototype.call
|
||||||
|
function call() {
|
||||||
|
return oldCall.apply(this, arguments)
|
||||||
|
}
|
||||||
|
Function.prototype.call = call
|
||||||
|
|
||||||
|
const nativeToStringFunctionString = Error.toString().replace(/Error/g, 'toString')
|
||||||
|
const oldToString = Function.prototype.toString
|
||||||
|
|
||||||
|
function functionToString() {
|
||||||
|
if (this === window.navigator.permissions.query) {
|
||||||
|
return 'function query() { [native code] }'
|
||||||
|
}
|
||||||
|
if (this === functionToString) {
|
||||||
|
return nativeToStringFunctionString
|
||||||
|
}
|
||||||
|
return oldCall.call(oldToString, this)
|
||||||
|
}
|
||||||
|
// eslint-disable-next-line
|
||||||
|
Function.prototype.toString = functionToString
|
||||||
|
"""
|
||||||
},
|
},
|
||||||
)
|
)
|
||||||
return orig_get(*args, **kwargs)
|
return orig_get(*args, **kwargs)
|
||||||
|
|
||||||
self.get = get_wrapped
|
self.get = get_wrapped
|
||||||
|
|
||||||
def __dir__(self):
|
|
||||||
return object.__dir__(self)
|
|
||||||
|
|
||||||
def _get_cdc_props(self):
|
def _get_cdc_props(self):
|
||||||
return self.execute_script(
|
return self.execute_script(
|
||||||
"""
|
"""
|
||||||
@ -553,6 +647,11 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
if self.reactor and isinstance(self.reactor, Reactor):
|
if self.reactor and isinstance(self.reactor, Reactor):
|
||||||
self.reactor.handlers.clear()
|
self.reactor.handlers.clear()
|
||||||
|
|
||||||
|
def window_new(self):
|
||||||
|
self.execute(
|
||||||
|
selenium.webdriver.remote.command.Command.NEW_WINDOW, {"type": "window"}
|
||||||
|
)
|
||||||
|
|
||||||
def tab_new(self, url: str):
|
def tab_new(self, url: str):
|
||||||
"""
|
"""
|
||||||
this opens a url in a new tab.
|
this opens a url in a new tab.
|
||||||
@ -597,25 +696,21 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
# super(Chrome, self).start_session(capabilities, browser_profile)
|
# super(Chrome, self).start_session(capabilities, browser_profile)
|
||||||
|
|
||||||
def quit(self):
|
def quit(self):
|
||||||
logger.debug("closing webdriver")
|
|
||||||
if hasattr(self, "service") and getattr(self.service, "process", None):
|
|
||||||
self.service.process.terminate()
|
|
||||||
self.service.process.wait(5)
|
|
||||||
try:
|
try:
|
||||||
if self.reactor and isinstance(self.reactor, Reactor):
|
self.service.process.kill()
|
||||||
logger.debug("shutting down reactor")
|
logger.debug("webdriver process ended")
|
||||||
self.reactor.event.set()
|
except (AttributeError, RuntimeError, OSError):
|
||||||
except Exception: # noqa
|
pass
|
||||||
|
try:
|
||||||
|
self.reactor.event.set()
|
||||||
|
logger.debug("shutting down reactor")
|
||||||
|
except AttributeError:
|
||||||
pass
|
pass
|
||||||
try:
|
try:
|
||||||
logger.debug("killing browser")
|
|
||||||
os.kill(self.browser_pid, 15)
|
os.kill(self.browser_pid, 15)
|
||||||
|
logger.debug("gracefully closed browser")
|
||||||
except TimeoutError as e:
|
except Exception as e: # noqa
|
||||||
logger.debug(e, exc_info=True)
|
logger.debug(e, exc_info=True)
|
||||||
except Exception: # noqa
|
|
||||||
pass
|
|
||||||
|
|
||||||
if (
|
if (
|
||||||
hasattr(self, "keep_user_data_dir")
|
hasattr(self, "keep_user_data_dir")
|
||||||
and hasattr(self, "user_data_dir")
|
and hasattr(self, "user_data_dir")
|
||||||
@ -623,7 +718,6 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
):
|
):
|
||||||
for _ in range(5):
|
for _ in range(5):
|
||||||
try:
|
try:
|
||||||
|
|
||||||
shutil.rmtree(self.user_data_dir, ignore_errors=False)
|
shutil.rmtree(self.user_data_dir, ignore_errors=False)
|
||||||
except FileNotFoundError:
|
except FileNotFoundError:
|
||||||
pass
|
pass
|
||||||
@ -641,13 +735,24 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
# this must come last, otherwise it will throw 'in use' errors
|
# this must come last, otherwise it will throw 'in use' errors
|
||||||
self.patcher = None
|
self.patcher = None
|
||||||
|
|
||||||
def __del__(self):
|
def __getattribute__(self, item):
|
||||||
try:
|
if not super().__getattribute__("debug"):
|
||||||
super().quit()
|
return super().__getattribute__(item)
|
||||||
# self.service.process.kill()
|
else:
|
||||||
except: # noqa
|
import inspect
|
||||||
pass
|
|
||||||
self.quit()
|
original = super().__getattribute__(item)
|
||||||
|
if inspect.ismethod(original) and not inspect.isclass(original):
|
||||||
|
|
||||||
|
def newfunc(*args, **kwargs):
|
||||||
|
logger.debug(
|
||||||
|
"calling %s with args %s and kwargs %s\n"
|
||||||
|
% (original.__qualname__, args, kwargs)
|
||||||
|
)
|
||||||
|
return original(*args, **kwargs)
|
||||||
|
|
||||||
|
return newfunc
|
||||||
|
return original
|
||||||
|
|
||||||
def __enter__(self):
|
def __enter__(self):
|
||||||
return self
|
return self
|
||||||
@ -661,6 +766,27 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
|||||||
def __hash__(self):
|
def __hash__(self):
|
||||||
return hash(self.options.debugger_address)
|
return hash(self.options.debugger_address)
|
||||||
|
|
||||||
|
def __dir__(self):
|
||||||
|
return object.__dir__(self)
|
||||||
|
|
||||||
|
def __del__(self):
|
||||||
|
try:
|
||||||
|
self.service.process.kill()
|
||||||
|
except: # noqa
|
||||||
|
pass
|
||||||
|
self.quit()
|
||||||
|
|
||||||
|
@classmethod
|
||||||
|
def _ensure_close(cls, self):
|
||||||
|
# needs to be a classmethod so finalize can find the reference
|
||||||
|
logger.info("ensuring close")
|
||||||
|
if (
|
||||||
|
hasattr(self, "service")
|
||||||
|
and hasattr(self.service, "process")
|
||||||
|
and hasattr(self.service.process, "kill")
|
||||||
|
):
|
||||||
|
self.service.process.kill()
|
||||||
|
|
||||||
|
|
||||||
def find_chrome_executable():
|
def find_chrome_executable():
|
||||||
"""
|
"""
|
||||||
@ -692,14 +818,16 @@ def find_chrome_executable():
|
|||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
for item in map(
|
for item in map(
|
||||||
os.environ.get, ("PROGRAMFILES", "PROGRAMFILES(X86)", "LOCALAPPDATA")
|
os.environ.get,
|
||||||
|
("PROGRAMFILES", "PROGRAMFILES(X86)", "LOCALAPPDATA", "PROGRAMW6432"),
|
||||||
):
|
):
|
||||||
for subitem in (
|
if item is not None:
|
||||||
"Google/Chrome/Application",
|
for subitem in (
|
||||||
"Google/Chrome Beta/Application",
|
"Google/Chrome/Application",
|
||||||
"Google/Chrome Canary/Application",
|
"Google/Chrome Beta/Application",
|
||||||
):
|
"Google/Chrome Canary/Application",
|
||||||
candidates.add(os.sep.join((item, subitem, "chrome.exe")))
|
):
|
||||||
|
candidates.add(os.sep.join((item, subitem, "chrome.exe")))
|
||||||
for candidate in candidates:
|
for candidate in candidates:
|
||||||
if os.path.exists(candidate) and os.access(candidate, os.X_OK):
|
if os.path.exists(candidate) and os.access(candidate, os.X_OK):
|
||||||
return os.path.normpath(candidate)
|
return os.path.normpath(candidate)
|
||||||
|
@ -17,6 +17,7 @@ by UltrafunkAmsterdam (https://github.com/ultrafunkamsterdam)
|
|||||||
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
from distutils.version import LooseVersion
|
||||||
import io
|
import io
|
||||||
import logging
|
import logging
|
||||||
import os
|
import os
|
||||||
@ -24,11 +25,13 @@ import random
|
|||||||
import re
|
import re
|
||||||
import string
|
import string
|
||||||
import sys
|
import sys
|
||||||
|
from urllib.request import urlopen
|
||||||
|
from urllib.request import urlretrieve
|
||||||
import zipfile
|
import zipfile
|
||||||
from distutils.version import LooseVersion
|
|
||||||
from urllib.request import urlopen, urlretrieve
|
|
||||||
|
|
||||||
from selenium.webdriver import Chrome as _Chrome, ChromeOptions as _ChromeOptions
|
from selenium.webdriver import Chrome as _Chrome
|
||||||
|
from selenium.webdriver import ChromeOptions as _ChromeOptions
|
||||||
|
|
||||||
|
|
||||||
TARGET_VERSION = 0
|
TARGET_VERSION = 0
|
||||||
logger = logging.getLogger("uc")
|
logger = logging.getLogger("uc")
|
||||||
|
@ -3,11 +3,11 @@
|
|||||||
|
|
||||||
import json
|
import json
|
||||||
import logging
|
import logging
|
||||||
from collections.abc import Mapping, Sequence
|
|
||||||
|
|
||||||
import requests
|
import requests
|
||||||
import websockets
|
import websockets
|
||||||
|
|
||||||
|
|
||||||
log = logging.getLogger(__name__)
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
|
@ -1,17 +1,16 @@
|
|||||||
import asyncio
|
import asyncio
|
||||||
import logging
|
|
||||||
import time
|
|
||||||
import traceback
|
|
||||||
from collections.abc import Mapping
|
from collections.abc import Mapping
|
||||||
from collections.abc import Sequence
|
from collections.abc import Sequence
|
||||||
|
from functools import wraps
|
||||||
|
import logging
|
||||||
|
import threading
|
||||||
|
import time
|
||||||
|
import traceback
|
||||||
from typing import Any
|
from typing import Any
|
||||||
from typing import Awaitable
|
from typing import Awaitable
|
||||||
from typing import Callable
|
from typing import Callable
|
||||||
from typing import List
|
from typing import List
|
||||||
from typing import Optional
|
from typing import Optional
|
||||||
from contextlib import ExitStack
|
|
||||||
import threading
|
|
||||||
from functools import wraps, partial
|
|
||||||
|
|
||||||
|
|
||||||
class Structure(dict):
|
class Structure(dict):
|
||||||
|
@ -1,13 +1,13 @@
|
|||||||
|
import atexit
|
||||||
|
import logging
|
||||||
import multiprocessing
|
import multiprocessing
|
||||||
import os
|
import os
|
||||||
import platform
|
import platform
|
||||||
import sys
|
import signal
|
||||||
from subprocess import PIPE
|
from subprocess import PIPE
|
||||||
from subprocess import Popen
|
from subprocess import Popen
|
||||||
import atexit
|
import sys
|
||||||
import traceback
|
|
||||||
import logging
|
|
||||||
import signal
|
|
||||||
|
|
||||||
CREATE_NEW_PROCESS_GROUP = 0x00000200
|
CREATE_NEW_PROCESS_GROUP = 0x00000200
|
||||||
DETACHED_PROCESS = 0x00000008
|
DETACHED_PROCESS = 0x00000008
|
||||||
@ -27,14 +27,12 @@ def start_detached(executable, *args):
|
|||||||
reader, writer = multiprocessing.Pipe(False)
|
reader, writer = multiprocessing.Pipe(False)
|
||||||
|
|
||||||
# do not keep reference
|
# do not keep reference
|
||||||
process = multiprocessing.Process(
|
multiprocessing.Process(
|
||||||
target=_start_detached,
|
target=_start_detached,
|
||||||
args=(executable, *args),
|
args=(executable, *args),
|
||||||
kwargs={"writer": writer},
|
kwargs={"writer": writer},
|
||||||
daemon=True,
|
daemon=True,
|
||||||
)
|
).start()
|
||||||
process.start()
|
|
||||||
process.join()
|
|
||||||
# receive pid from pipe
|
# receive pid from pipe
|
||||||
pid = reader.recv()
|
pid = reader.recv()
|
||||||
REGISTERED.append(pid)
|
REGISTERED.append(pid)
|
||||||
|
@ -39,6 +39,20 @@ class ChromeOptions(_ChromiumOptions):
|
|||||||
value = ChromeOptions._undot_key(rest, value)
|
value = ChromeOptions._undot_key(rest, value)
|
||||||
return {key: value}
|
return {key: value}
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def _merge_nested(a, b):
|
||||||
|
"""
|
||||||
|
merges b into a
|
||||||
|
leaf values in a are overwritten with values from b
|
||||||
|
"""
|
||||||
|
for key in b:
|
||||||
|
if key in a:
|
||||||
|
if isinstance(a[key], dict) and isinstance(b[key], dict):
|
||||||
|
ChromeOptions._merge_nested(a[key], b[key])
|
||||||
|
continue
|
||||||
|
a[key] = b[key]
|
||||||
|
return a
|
||||||
|
|
||||||
def handle_prefs(self, user_data_dir):
|
def handle_prefs(self, user_data_dir):
|
||||||
prefs = self.experimental_options.get("prefs")
|
prefs = self.experimental_options.get("prefs")
|
||||||
if prefs:
|
if prefs:
|
||||||
@ -50,12 +64,14 @@ class ChromeOptions(_ChromiumOptions):
|
|||||||
# undot prefs dict keys
|
# undot prefs dict keys
|
||||||
undot_prefs = {}
|
undot_prefs = {}
|
||||||
for key, value in prefs.items():
|
for key, value in prefs.items():
|
||||||
undot_prefs.update(self._undot_key(key, value))
|
undot_prefs = self._merge_nested(
|
||||||
|
undot_prefs, self._undot_key(key, value)
|
||||||
|
)
|
||||||
|
|
||||||
prefs_file = os.path.join(default_path, "Preferences")
|
prefs_file = os.path.join(default_path, "Preferences")
|
||||||
if os.path.exists(prefs_file):
|
if os.path.exists(prefs_file):
|
||||||
with open(prefs_file, encoding="latin1", mode="r") as f:
|
with open(prefs_file, encoding="latin1", mode="r") as f:
|
||||||
undot_prefs.update(json.load(f))
|
undot_prefs = self._merge_nested(json.load(f), undot_prefs)
|
||||||
|
|
||||||
with open(prefs_file, encoding="latin1", mode="w") as f:
|
with open(prefs_file, encoding="latin1", mode="w") as f:
|
||||||
json.dump(undot_prefs, f)
|
json.dump(undot_prefs, f)
|
||||||
|
@ -1,23 +1,24 @@
|
|||||||
#!/usr/bin/env python3
|
#!/usr/bin/env python3
|
||||||
# this module is part of undetected_chromedriver
|
# this module is part of undetected_chromedriver
|
||||||
|
|
||||||
|
from distutils.version import LooseVersion
|
||||||
import io
|
import io
|
||||||
import logging
|
import logging
|
||||||
import os
|
import os
|
||||||
import random
|
import random
|
||||||
import re
|
import re
|
||||||
|
import secrets
|
||||||
import string
|
import string
|
||||||
import sys
|
import sys
|
||||||
import time
|
import time
|
||||||
|
from urllib.request import urlopen
|
||||||
|
from urllib.request import urlretrieve
|
||||||
import zipfile
|
import zipfile
|
||||||
from distutils.version import LooseVersion
|
|
||||||
from urllib.request import urlopen, urlretrieve
|
|
||||||
import secrets
|
|
||||||
|
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
IS_POSIX = sys.platform.startswith(("darwin", "cygwin", "linux"))
|
IS_POSIX = sys.platform.startswith(("darwin", "cygwin", "linux", "linux2"))
|
||||||
|
|
||||||
|
|
||||||
class Patcher(object):
|
class Patcher(object):
|
||||||
@ -29,7 +30,7 @@ class Patcher(object):
|
|||||||
if platform.endswith("win32"):
|
if platform.endswith("win32"):
|
||||||
zip_name %= "win32"
|
zip_name %= "win32"
|
||||||
exe_name %= ".exe"
|
exe_name %= ".exe"
|
||||||
if platform.endswith("linux"):
|
if platform.endswith(("linux", "linux2")):
|
||||||
zip_name %= "linux64"
|
zip_name %= "linux64"
|
||||||
exe_name %= ""
|
exe_name %= ""
|
||||||
if platform.endswith("darwin"):
|
if platform.endswith("darwin"):
|
||||||
@ -38,7 +39,9 @@ class Patcher(object):
|
|||||||
|
|
||||||
if platform.endswith("win32"):
|
if platform.endswith("win32"):
|
||||||
d = "~/appdata/roaming/undetected_chromedriver"
|
d = "~/appdata/roaming/undetected_chromedriver"
|
||||||
elif platform.startswith("linux"):
|
elif "LAMBDA_TASK_ROOT" in os.environ:
|
||||||
|
d = "/tmp/undetected_chromedriver"
|
||||||
|
elif platform.startswith(("linux","linux2")):
|
||||||
d = "~/.local/share/undetected_chromedriver"
|
d = "~/.local/share/undetected_chromedriver"
|
||||||
elif platform.endswith("darwin"):
|
elif platform.endswith("darwin"):
|
||||||
d = "~/Library/Application Support/undetected_chromedriver"
|
d = "~/Library/Application Support/undetected_chromedriver"
|
||||||
|
@ -1,7 +1,29 @@
|
|||||||
|
from selenium.webdriver.common.by import By
|
||||||
import selenium.webdriver.remote.webelement
|
import selenium.webdriver.remote.webelement
|
||||||
|
from typing import List
|
||||||
|
|
||||||
|
|
||||||
class WebElement(selenium.webdriver.remote.webelement.WebElement):
|
class WebElement(selenium.webdriver.remote.webelement.WebElement):
|
||||||
|
def click_safe(self):
|
||||||
|
super().click()
|
||||||
|
self._parent.reconnect(0.1)
|
||||||
|
|
||||||
|
def children(
|
||||||
|
self, tag=None, recursive=False
|
||||||
|
) -> List[selenium.webdriver.remote.webelement.WebElement]:
|
||||||
|
"""
|
||||||
|
returns direct child elements of current element
|
||||||
|
:param tag: str, if supplied, returns <tag> nodes only
|
||||||
|
"""
|
||||||
|
script = "return [... arguments[0].children]"
|
||||||
|
if tag:
|
||||||
|
script += ".filter( node => node.tagName === '%s')" % tag.upper()
|
||||||
|
if recursive:
|
||||||
|
return list(_recursive_children(self, tag))
|
||||||
|
return list(self._parent.execute_script(script, self))
|
||||||
|
|
||||||
|
|
||||||
|
class UCWebElement(WebElement):
|
||||||
"""
|
"""
|
||||||
Custom WebElement class which makes it easier to view elements when
|
Custom WebElement class which makes it easier to view elements when
|
||||||
working in an interactive environment.
|
working in an interactive environment.
|
||||||
@ -14,9 +36,13 @@ class WebElement(selenium.webdriver.remote.webelement.WebElement):
|
|||||||
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
def __init__(self, parent, id_):
|
||||||
|
super().__init__(parent, id_)
|
||||||
|
self._attrs = None
|
||||||
|
|
||||||
@property
|
@property
|
||||||
def attrs(self):
|
def attrs(self):
|
||||||
if not hasattr(self, "_attrs"):
|
if not self._attrs:
|
||||||
self._attrs = self._parent.execute_script(
|
self._attrs = self._parent.execute_script(
|
||||||
"""
|
"""
|
||||||
var items = {};
|
var items = {};
|
||||||
@ -35,3 +61,25 @@ class WebElement(selenium.webdriver.remote.webelement.WebElement):
|
|||||||
if strattrs:
|
if strattrs:
|
||||||
strattrs = " " + strattrs
|
strattrs = " " + strattrs
|
||||||
return f"{self.__class__.__name__} <{self.tag_name}{strattrs}>"
|
return f"{self.__class__.__name__} <{self.tag_name}{strattrs}>"
|
||||||
|
|
||||||
|
|
||||||
|
def _recursive_children(element, tag: str = None, _results=None):
|
||||||
|
"""
|
||||||
|
returns all children of <element> recursively
|
||||||
|
|
||||||
|
:param element: `WebElement` object.
|
||||||
|
find children below this <element>
|
||||||
|
|
||||||
|
:param tag: str = None.
|
||||||
|
if provided, return only <tag> elements. example: 'a', or 'img'
|
||||||
|
:param _results: do not use!
|
||||||
|
"""
|
||||||
|
results = _results or set()
|
||||||
|
for element in element.children():
|
||||||
|
if tag:
|
||||||
|
if element.tag_name == tag:
|
||||||
|
results.add(element)
|
||||||
|
else:
|
||||||
|
results.add(element)
|
||||||
|
results |= _recursive_children(element, tag, results)
|
||||||
|
return results
|
||||||
|
Loading…
x
Reference in New Issue
Block a user