feat : stealth browser with selenium_stealth for captcha

install.sh

@@ -7,12 +7,14 @@ echo "Detecting operating system..."
 
 OS_TYPE=$(uname -s)
 
+
 case "$OS_TYPE" in
     "Linux"*)
         echo "Detected Linux OS"
         if [ -f "$SCRIPTS_DIR/linux_install.sh" ]; then
             echo "Running Linux installation script..."
             bash "$SCRIPTS_DIR/linux_install.sh"
+            bash -c "wget https://github.com/Fosowl/fosowl.github.io/raw/refs/heads/main/usefull/anticaptcha.crx"
             bash -c "cd $LLM_ROUTER_DIR && ./dl_safetensors.sh"
         else
             echo "Error: $SCRIPTS_DIR/linux_install.sh not found!"
@@ -24,6 +26,7 @@ case "$OS_TYPE" in
         if [ -f "$SCRIPTS_DIR/macos_install.sh" ]; then
             echo "Running macOS installation script..."
             bash "$SCRIPTS_DIR/macos_install.sh"
+            bash -c "wget https://github.com/Fosowl/fosowl.github.io/raw/refs/heads/main/usefull/anticaptcha.crx"
             bash -c "cd $LLM_ROUTER_DIR && ./dl_safetensors.sh"
         else
             echo "Error: $SCRIPTS_DIR/macos_install.sh not found!"

requirements.txt

@@ -29,6 +29,9 @@ distro>=1.7.0,<2
 jiter>=0.4.0,<1
 sniffio
 tqdm>4
+fake_useragent>=2.1.0
+selenium_stealth>=1.0.6
+undetected-chromedriver>=3.5.5
 # for api provider
 openai
 # if use chinese

scripts/macos_install.sh

@@ -5,6 +5,9 @@ echo "Starting installation for macOS..."
 # Install Python dependencies from requirements.txt
 pip3 install -r requirements.txt
 
+# make sure wget installed
+brew install wget
+
 # Install chromedriver using Homebrew
 brew install --cask chromedriver
 

setup.py

@@ -41,6 +41,9 @@ setup(
         "anyio>=3.5.0,<5",
         "distro>=1.7.0,<2",
         "jiter>=0.4.0,<1",
+        "fake_useragent>=2.1.0",
+        "selenium_stealth>=1.0.6",
+        "undetected-chromedriver>=3.5.5",
         "sniffio",
         "tqdm>4"
     ],

sources/browser.py

@@ -7,17 +7,21 @@ from selenium.webdriver.support import expected_conditions as EC
 from selenium.common.exceptions import TimeoutException, WebDriverException
 from selenium.webdriver.common.action_chains import ActionChains
 from selenium.webdriver.chrome.options import Options
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
 from typing import List, Tuple
+from fake_useragent import UserAgent
+from selenium_stealth import stealth
+import undetected_chromedriver as uc
 import chromedriver_autoinstaller
 import time
+import random
 import os
 import shutil
-from bs4 import BeautifulSoup
 import markdownify
 import logging
 import sys
 import re
-from urllib.parse import urlparse
 
 from sources.utility import pretty_print, animate_thinking
 
@@ -39,7 +43,8 @@ def get_chrome_path() -> str:
             return path
     return None
 
-def create_driver(headless=False):
+def create_driver(headless=False, stealth_mode=True) -> webdriver.Chrome:
+    """Create a Chrome WebDriver with specified options."""
     chrome_options = Options()
     chrome_path = get_chrome_path()
     
@@ -51,20 +56,19 @@ def create_driver(headless=False):
         chrome_options.add_argument("--headless")
         chrome_options.add_argument("--disable-gpu")
         chrome_options.add_argument("--disable-webgl")
+    #ua = UserAgent()
+    #user_agent = ua.random # NOTE sometime return wrong user agent, investigate
+    #chrome_options.add_argument(f'user-agent={user_agent}')
     chrome_options.add_argument("--no-sandbox")
     chrome_options.add_argument("--disable-dev-shm-usage")
     chrome_options.add_argument("--autoplay-policy=user-gesture-required")
     chrome_options.add_argument("--mute-audio")
     chrome_options.add_argument("--disable-notifications")
     chrome_options.add_argument('--window-size=1080,560')
-    security_prefs = {
-        "profile.default_content_setting_values.media_stream": 2,
-        "profile.default_content_setting_values.geolocation": 2,
-        "safebrowsing.enabled": True,
-    }
-    chrome_options.add_experimental_option("prefs", security_prefs)
-    chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
-    chrome_options.add_experimental_option('useAutomationExtension', False)
+    try:
+        chrome_options.add_extension("./anticaptcha.crx")
+    except Exception as e:
+        print(f"Failed to load AntiCaptcha extension: {str(e)}")
     
     chromedriver_path = shutil.which("chromedriver")
     if not chromedriver_path:
@@ -74,10 +78,29 @@ def create_driver(headless=False):
         raise FileNotFoundError("ChromeDriver not found. Please install it or add it to your PATH.")
     
     service = Service(chromedriver_path)
+    if stealth_mode:
+        driver = uc.Chrome(service=service, options=chrome_options)
+        stealth(driver,
+            languages=["en-US", "en"],
+            vendor="Google Inc.",
+            platform="Win32",
+            webgl_vendor="Intel Inc.",
+            renderer="Intel Iris OpenGL Engine",
+            fix_hairline=True,
+        )
+        return driver
+    security_prefs = {
+        "profile.default_content_setting_values.media_stream": 2,
+        "profile.default_content_setting_values.geolocation": 2,
+        "safebrowsing.enabled": True,
+    }
+    chrome_options.add_experimental_option("prefs", security_prefs)
+    chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    chrome_options.add_experimental_option('useAutomationExtension', False)
     return webdriver.Chrome(service=service, options=chrome_options)
 
 class Browser:
-    def __init__(self, driver, anticaptcha_install=True):
+    def __init__(self, driver, anticaptcha_manual_install=False):
         """Initialize the browser with optional AntiCaptcha installation."""
         self.js_scripts_folder = "./sources/web_scripts/" if not __name__ == "__main__" else "./web_scripts/"
         self.anticaptcha = "https://chrome.google.com/webstore/detail/nopecha-captcha-solver/dknlfmjaanfblgfdfebhijalfmhmjjjo/related"
@@ -88,10 +111,11 @@ class Browser:
             self.logger.info("Browser initialized successfully")
         except Exception as e:
             raise Exception(f"Failed to initialize browser: {str(e)}")
-        if anticaptcha_install:
-            self.load_anticatpcha()
+        self.driver.get("https://www.google.com")
+        if anticaptcha_manual_install:
+            self.load_anticatpcha_manually()
             
-    def load_anticatpcha(self):
+    def load_anticatpcha_manually(self):
         print("You might want to install the AntiCaptcha extension for captchas.")
         self.driver.get(self.anticaptcha)
 
@@ -129,11 +153,11 @@ class Browser:
             for element in soup(['script', 'style']):
                 element.decompose()
             
-            text = soup.get_text()
             
             lines = (line.strip() for line in text.splitlines())
             chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
             text = "\n".join(chunk for chunk in chunks if chunk and self.is_sentence(chunk))
+            text = text[:4096]
             #markdown_text = markdownify.markdownify(text, heading_style="ATX")
             return "[Start of page]\n" + text + "\n[End of page]"
         except Exception as e: