Mirrors
/
undetected-chromedriver
mirror of https://github.com/ultrafunkamsterdam/undetected-chromedriver.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

1.5.0

This commit is contained in:
ultrafunkamsterdam 2020-10-13 03:51:35 +02:00
parent 06217efc65
commit 4ce47e7f83
5 changed files with 962 additions and 962 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

258
.gitignore vendored
View File

@ -1,129 +1,129 @@
# Byte-compiled / optimized / DLL files # Byte-compiled / optimized / DLL files
__pycache__/ __pycache__/
*.py[cod] *.py[cod]
*$py.class *$py.class
# C extensions # C extensions
*.so *.so
# Distribution / packaging # Distribution / packaging
.Python .Python
build/ build/
develop-eggs/ develop-eggs/
dist/ dist/
downloads/ downloads/
eggs/ eggs/
.eggs/ .eggs/
lib/ lib/
lib64/ lib64/
parts/ parts/
sdist/ sdist/
var/ var/
wheels/ wheels/
pip-wheel-metadata/ pip-wheel-metadata/
share/python-wheels/ share/python-wheels/
*.egg-info/ *.egg-info/
.installed.cfg .installed.cfg
*.egg *.egg
MANIFEST MANIFEST
# PyInstaller # PyInstaller
# Usually these files are written by a python script from a template # Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it. # before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest *.manifest
*.spec *.spec
# Installer logs # Installer logs
pip-log.txt pip-log.txt
pip-delete-this-directory.txt pip-delete-this-directory.txt
# Unit test / coverage reports # Unit test / coverage reports
htmlcov/ htmlcov/
.tox/ .tox/
.nox/ .nox/
.coverage .coverage
.coverage.* .coverage.*
.cache .cache
nosetests.xml nosetests.xml
coverage.xml coverage.xml
*.cover *.cover
*.py,cover *.py,cover
.hypothesis/ .hypothesis/
.pytest_cache/ .pytest_cache/
# Translations # Translations
*.mo *.mo
*.pot *.pot
# Django stuff: # Django stuff:
*.log *.log
local_settings.py local_settings.py
db.sqlite3 db.sqlite3
db.sqlite3-journal db.sqlite3-journal
# Flask stuff: # Flask stuff:
instance/ instance/
.webassets-cache .webassets-cache
# Scrapy stuff: # Scrapy stuff:
.scrapy .scrapy
# Sphinx documentation # Sphinx documentation
docs/_build/ docs/_build/
# PyBuilder # PyBuilder
target/ target/
# Jupyter Notebook # Jupyter Notebook
.ipynb_checkpoints .ipynb_checkpoints
# IPython # IPython
profile_default/ profile_default/
ipython_config.py ipython_config.py
# pyenv # pyenv
.python-version .python-version
# pipenv # pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies # However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not # having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies. # install all needed dependencies.
#Pipfile.lock #Pipfile.lock
# PEP 582; used by e.g. github.com/David-OConnor/pyflow # PEP 582; used by e.g. github.com/David-OConnor/pyflow
__pypackages__/ __pypackages__/
# Celery stuff # Celery stuff
celerybeat-schedule celerybeat-schedule
celerybeat.pid celerybeat.pid
# SageMath parsed files # SageMath parsed files
*.sage.py *.sage.py
# Environments # Environments
.env .env
.venv .venv
env/ env/
venv/ venv/
ENV/ ENV/
env.bak/ env.bak/
venv.bak/ venv.bak/
# Spyder project settings # Spyder project settings
.spyderproject .spyderproject
.spyproject .spyproject
# Rope project settings # Rope project settings
.ropeproject .ropeproject
# mkdocs documentation # mkdocs documentation
/site /site
# mypy # mypy
.mypy_cache/ .mypy_cache/
.dmypy.json .dmypy.json
dmypy.json dmypy.json
# Pyre type checker # Pyre type checker
.pyre/ .pyre/

1348
LICENSE
View File

File diff suppressed because it is too large Load Diff

252
README.md
View File

@ -1,126 +1,126 @@
# undetected_chromedriver # undetected_chromedriver
https://github.com/ultrafunkamsterdam/undetected-chromedriver https://github.com/ultrafunkamsterdam/undetected-chromedriver
Optimized Selenium Chromedriver patch which does not trigger anti-bot services like Distill Network / Imperva / DataDome / Botprotect.io Optimized Selenium Chromedriver patch which does not trigger anti-bot services like Distill Network / Imperva / DataDome / Botprotect.io
Automatically downloads the driver binary and patches it. Automatically downloads the driver binary and patches it.
* **Tested on version 75,76,77,78,79,80,81,83,84,85,86** * **Tested on version 75,76,77,78,79,80,81,83,84,85,86**
* **patching also works on MS Edge (chromium-based) webdriver binary** * **patching also works on MS Edge (chromium-based) webdriver binary**
## New ## ## New ##
By default, the console log function is disabled to prevent certain detections. By default, the console log function is disabled to prevent certain detections.
Until a cleaner solution is found, use the following to manually enable it Until a cleaner solution is found, use the following to manually enable it
```python ```python
import undetected_chromedriver as uc import undetected_chromedriver as uc
driver = uc.Chrome(enable_console_log=True) driver = uc.Chrome(enable_console_log=True)
``` ```
## Installation ## ## Installation ##
``` ```
pip install undetected-chromedriver pip install undetected-chromedriver
``` ```
## Usage ## ## Usage ##
To prevent unnecessary hair-pulling and issue-rasing, please mind the **[important note at the end of this document](#important-note) .** To prevent unnecessary hair-pulling and issue-rasing, please mind the **[important note at the end of this document](#important-note) .**
<br> <br>
#### the easy way (recommended) #### #### the easy way (recommended) ####
```python ```python
import undetected_chromedriver as uc import undetected_chromedriver as uc
driver = uc.Chrome() driver = uc.Chrome()
driver.get('https://distilnetworks.com') driver.get('https://distilnetworks.com')
# To target specific version # To target specific version
import undetected_chromedriver as uc import undetected_chromedriver as uc
uc.TARGET_VERSION = 85 uc.TARGET_VERSION = 85
driver = uc.Chrome() driver = uc.Chrome()
``` ```
#### patches selenium module #### #### patches selenium module ####
Needs to be done before importing from selenium package Needs to be done before importing from selenium package
```python ```python
import undetected_chromedriver as uc import undetected_chromedriver as uc
uc.install() uc.install()
from selenium.webdriver import Chrome from selenium.webdriver import Chrome
driver = Chrome() driver = Chrome()
driver.get('https://distilnetworks.com') driver.get('https://distilnetworks.com')
```` ````
#### the customized way #### #### the customized way ####
```python ```python
import undetected_chromedriver as uc import undetected_chromedriver as uc
#specify chromedriver version to download and patch #specify chromedriver version to download and patch
#this did not work correctly until 1.2.1 #this did not work correctly until 1.2.1
uc.TARGET_VERSION = 78 uc.TARGET_VERSION = 78
# or specify your own chromedriver binary to patch # or specify your own chromedriver binary to patch
undetected_chromedriver.install( undetected_chromedriver.install(
executable_path='c:/users/user1/chromedriver.exe', executable_path='c:/users/user1/chromedriver.exe',
) )
from selenium.webdriver import Chrome, ChromeOptions from selenium.webdriver import Chrome, ChromeOptions
opts = ChromeOptions() opts = ChromeOptions()
opts.add_argument(f'--proxy-server=socks5://127.0.0.1:9050') opts.add_argument(f'--proxy-server=socks5://127.0.0.1:9050')
driver = Chrome(options=opts) driver = Chrome(options=opts)
driver.get('https://distilnetworks.com') driver.get('https://distilnetworks.com')
``` ```
### datadome.co #### ### datadome.co ####
These guys have actually a powerful product, and a link to this repo, which makes me wanna test their product. These guys have actually a powerful product, and a link to this repo, which makes me wanna test their product.
Make sure you use a "clean" ip for this one. Make sure you use a "clean" ip for this one.
``` ```
# STANDARD chromedriver # STANDARD chromedriver
from selenium import webdriver from selenium import webdriver
chrome = webdriver.Chrome() chrome = webdriver.Chrome()
chrome.get('https://datadome.co/customers-stories/toppreise-ends-web-scraping-and-content-theft-with-datadome/') chrome.get('https://datadome.co/customers-stories/toppreise-ends-web-scraping-and-content-theft-with-datadome/')
chrome.save_screenshot('datadome_regular_webdriver.png') chrome.save_screenshot('datadome_regular_webdriver.png')
True True
# after this detectioon, you'll keep being nagged with puzzles, even if you use another machine from the same same network (they use a very tight but effective regime, possibly combination of fingerprinting and ip-flagging). # after this detectioon, you'll keep being nagged with puzzles, even if you use another machine from the same same network (they use a very tight but effective regime, possibly combination of fingerprinting and ip-flagging).
# UNDETECTED chromedriver (headless,even) # UNDETECTED chromedriver (headless,even)
import undetected_chromedriver as uc import undetected_chromedriver as uc
options = uc.ChromeOptions() options = uc.ChromeOptions()
options.headless=True options.headless=True
options.add_argument('--headless') options.add_argument('--headless')
chrome = uc.Chrome(options=options) chrome = uc.Chrome(options=options)
chrome.get('https://datadome.co/customers-stories/toppreise-ends-web-scraping-and-content-theft-with-datadome/') chrome.get('https://datadome.co/customers-stories/toppreise-ends-web-scraping-and-content-theft-with-datadome/')
chrome.save_screenshot('datadome_undetected_webddriver.png') chrome.save_screenshot('datadome_undetected_webddriver.png')
``` ```
**Check both saved screenhots [here](https://imgur.com/a/fEmqadP)** **Check both saved screenhots [here](https://imgur.com/a/fEmqadP)**
## important note ## ## important note ##
the default blank page on start plays a BIG role in the anti-detection workings of the module. You will only become undetectable from the moment you use driver.get(url) to navigate to some url (and next and next and next). This automatically means that if you enter a url in the browser screen by hand right after launch, you are NOT protected! New Tabs: same story. If you really need multi-tabs, then open the tab with the blank page (hint: url is `data:,` including comma, and yes, driver accepts it) and do your thing as usual. If you follow these "rules" (actually its default behaviour), then you will have a great time for now. the default blank page on start plays a BIG role in the anti-detection workings of the module. You will only become undetectable from the moment you use driver.get(url) to navigate to some url (and next and next and next). This automatically means that if you enter a url in the browser screen by hand right after launch, you are NOT protected! New Tabs: same story. If you really need multi-tabs, then open the tab with the blank page (hint: url is `data:,` including comma, and yes, driver accepts it) and do your thing as usual. If you follow these "rules" (actually its default behaviour), then you will have a great time for now.
TL;DR and for the visual-minded: TL;DR and for the visual-minded:
```python ```python
In [1]: import undetected_chromedriver as uc In [1]: import undetected_chromedriver as uc
In [2]: driver = uc.Chrome() In [2]: driver = uc.Chrome()
In [3]: driver.execute_script('return navigator.webdriver') In [3]: driver.execute_script('return navigator.webdriver')
Out[3]: True # Detectable Out[3]: True # Detectable
In [4]: driver.get('https://distilnetworks.com') # starts magic In [4]: driver.get('https://distilnetworks.com') # starts magic
In [4]: driver.execute_script('return navigator.webdriver') In [4]: driver.execute_script('return navigator.webdriver')
In [5]: None # Undetectable! In [5]: None # Undetectable!
``` ```
## end important note ## ## end important note ##

2
setup.py
View File

@ -16,7 +16,7 @@ from setuptools import setup
setup( setup(
name="undetected-chromedriver", name="undetected-chromedriver",
version="1.4.2", version="1.5.0",
packages=["undetected_chromedriver"], packages=["undetected_chromedriver"],
install_requires=["selenium",], install_requires=["selenium",],
url="https://github.com/ultrafunkamsterdam/undetected_chromedriver", url="https://github.com/ultrafunkamsterdam/undetected_chromedriver",

64
undetected_chromedriver/__init__.py
View File

@ -19,6 +19,7 @@ by UltrafunkAmsterdam (https://github.com/ultrafunkamsterdam)
import io import io
import logging import logging
import os import os
import re
import sys import sys
import zipfile import zipfile
from distutils.version import LooseVersion from distutils.version import LooseVersion
@ -30,7 +31,6 @@ from selenium.webdriver import ChromeOptions as _ChromeOptions
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
__IS_PATCHED__ = 0
TARGET_VERSION = 0 TARGET_VERSION = 0
@ -49,15 +49,15 @@ class Chrome:
kwargs["options"] = ChromeOptions() kwargs["options"] = ChromeOptions()
instance = object.__new__(_Chrome) instance = object.__new__(_Chrome)
instance.__init__(*args, **kwargs) instance.__init__(*args, **kwargs)
instance._orig_get = instance.get instance._orig_get = instance.get
def _get_wrapped(*args, **kwargs): def _get_wrapped(*args, **kwargs):
if instance.execute_script("return navigator.webdriver"): if instance.execute_script("return navigator.webdriver"):
instance.execute_cdp_cmd( instance.execute_cdp_cmd(
"Page.addScriptToEvaluateOnNewDocument", "Page.addScriptToEvaluateOnNewDocument",
{"source": """ {
"source": """
Object.defineProperty(window, 'navigator', { Object.defineProperty(window, 'navigator', {
value: new Proxy(navigator, { value: new Proxy(navigator, {
@ -70,16 +70,18 @@ class Chrome:
: target[key] : target[key]
}) })
}); });
"""
(function () { + (
}) (); "console.log = console.dir = console.error = function(){};"
if not enable_console_log
""" + ("console.log = console.dir = console.error = function(){};" if not enable_console_log else '' ) } else ""
)
},
) )
return instance._orig_get(*args, **kwargs) return instance._orig_get(*args, **kwargs)
instance.get = _get_wrapped instance.get = _get_wrapped
original_user_agent_string = instance.execute_script( original_user_agent_string = instance.execute_script(
"return navigator.userAgent" "return navigator.userAgent"
) )
@ -102,9 +104,7 @@ class ChromeOptions:
instance.__init__() instance.__init__()
instance.add_argument("start-maximized") instance.add_argument("start-maximized")
instance.add_experimental_option("excludeSwitches", ["enable-automation"]) instance.add_experimental_option("excludeSwitches", ["enable-automation"])
instance.add_experimental_option("useAutomationExtension", False) instance.add_argument("--disable-blink-features=AutomationControlled")
instance.add_argument("--disable-blink-features=AutomationControlled");
logger.info(f"starting undetected_chromedriver.ChromeOptions({args}, {kwargs})")
return instance return instance
@ -120,12 +120,16 @@ class ChromeDriverManager(object):
_platform = sys.platform _platform = sys.platform
if TARGET_VERSION: # user override using global if TARGET_VERSION:
# use global if set
self.target_version = TARGET_VERSION self.target_version = TARGET_VERSION
if target_version: if target_version:
# use explicitly passed target
self.target_version = target_version # user override self.target_version = target_version # user override
if not self.target_version: if not self.target_version:
# if target_version still not set, fetch the current major release version # none of the above (default) and just get current version
self.target_version = self.get_release_version_number().version[ self.target_version = self.get_release_version_number().version[
0 0
] # only major version int ] # only major version int
@ -173,8 +177,9 @@ class ChromeDriverManager(object):
""" """
if not os.path.exists(self.executable_path): if not os.path.exists(self.executable_path):
self.fetch_chromedriver() self.fetch_chromedriver()
self.patch_binary() if not self.__class__.installed:
self.__class__.installed = True if self.patch_binary():
self.__class__.installed = True
if patch_selenium: if patch_selenium:
self.patch_selenium_webdriver() self.patch_selenium_webdriver()
@ -220,20 +225,15 @@ class ChromeDriverManager(object):
:return: False on failure, binary name on success :return: False on failure, binary name on success
""" """
if self.__class__.installed: linect = 0
return with io.open(self.executable_path, "r+b") as fh:
for line in iter(lambda: fh.readline(), b""):
with io.open(self.executable_path, "r+b") as binary:
for line in iter(lambda: binary.readline(), b""):
if b"cdc_" in line: if b"cdc_" in line:
binary.seek(-len(line), 1) fh.seek(-len(line), 1)
line = b" var key = '$azc_abcdefghijklmnopQRstuv_';\n" newline = re.sub(b"cdc_.{22}", b"xxx_undetectedchromeDRiver", line)
binary.write(line) fh.write(newline)
__IS_PATCHED__ = 1 linect += 1
break return linect
else:
return False
return True
def install(executable_path=None, target_version=None, *args, **kwargs): def install(executable_path=None, target_version=None, *args, **kwargs):