Refactor Dockerfile and update screenshot capture: streamline Chrome and ChromeDriver installation, enhance memory settings, and improve cleanup process in the capture function.

Author: npv2k1

Dockerfile

@@ -1,19 +1,49 @@
 # Use a Python image with uv pre-installed
 FROM ghcr.io/astral-sh/uv:python3.11-bookworm
 
-# Install Chrome and dependencies
+# Install Chrome and its dependencies
+RUN apt-get -y update && apt-get install -y wget gnupg2
 RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add -
 RUN sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google-chrome.list'
-RUN apt-get -y update
-RUN apt-get install -y google-chrome-stable
-
-# install chromedriver
+RUN apt-get -y update && apt-get install -y \
+    google-chrome-stable \
+    fonts-ipafont-gothic \
+    fonts-wqy-zenhei \
+    fonts-thai-tlwg \
+    fonts-kacst \
+    fonts-symbola \
+    fonts-noto \
+    fonts-freefont-ttf \
+    libxss1 \
+    libx11-xcb1 \
+    libxcomposite1 \
+    libxcursor1 \
+    libxdamage1 \
+    libxi6 \
+    libxtst6 \
+    libnss3 \
+    libcups2 \
+    libxrandr2 \
+    libasound2 \
+    libatk1.0-0 \
+    libatk-bridge2.0-0 \
+    libgtk-3-0 \
+    libgbm1
+
+# Install chromedriver
 RUN apt-get install -yqq unzip
-RUN wget -O /tmp/chromedriver.zip http://chromedriver.storage.googleapis.com/`curl -sS chromedriver.storage.googleapis.com/LATEST_RELEASE`/chromedriver_linux64.zip
-RUN unzip /tmp/chromedriver.zip chromedriver -d /usr/local/bin/
+RUN CHROMEDRIVER_VERSION=$(curl -sS chromedriver.storage.googleapis.com/LATEST_RELEASE) && \
+    wget -O /tmp/chromedriver.zip http://chromedriver.storage.googleapis.com/$CHROMEDRIVER_VERSION/chromedriver_linux64.zip && \
+    unzip /tmp/chromedriver.zip chromedriver -d /usr/local/bin/ && \
+    chmod +x /usr/local/bin/chromedriver && \
+    rm /tmp/chromedriver.zip
 
-# set display port to avoid crash
+# Set display port and shared memory settings
 ENV DISPLAY=:99
+ENV DBUS_SESSION_BUS_ADDRESS=/dev/null
+
+# Create a shared memory volume
+VOLUME /dev/shm
 
 # Create a non-root user
 RUN useradd -m -u 1000 appuser

pyproject.toml

@@ -11,6 +11,7 @@ dependencies = [
     "numpy>=2.2.3",
     "pytest>=8.3.4",
     "selenium>=4.29.0",
+    "psutil>=5.9.0",
 ]
 
 [tool.black]

src/modules/apps/__init__.py

@@ -19,8 +19,9 @@ def capture_page(url: str, output_file: str = "screenshot.png"):
     :param output_file: The filename to save the screenshot.
     """
     options = Options()
+    
     # Basic options
-    options.add_argument('--headless')
+    options.add_argument('--headless=new')  # New headless mode
     options.add_argument('--no-sandbox')  # Required in Docker
     options.add_argument('--disable-dev-shm-usage')  # Required in Docker
 
@@ -32,16 +33,24 @@ def capture_page(url: str, output_file: str = "screenshot.png"):
 
     # Resource configuration
     options.add_argument('--window-size=1920,1080')
-    options.add_argument('--remote-debugging-port=9222')  # Fix DevTools port issue
-    options.add_argument('--disable-features=site-per-process')  # Reduce memory usage
-    options.add_argument('--memory-pressure-off')  # Prevent memory-related crashes
+    options.add_argument('--disable-features=NetworkService,NetworkServiceInProcess')
+    options.add_argument('--disable-features=site-per-process')
+    
+    # Memory and process settings
+    options.add_argument('--single-process')  # Run in single process mode
+    options.add_argument('--memory-pressure-off')
+    options.add_argument('--disable-crash-reporter')
+    options.add_argument('--disable-breakpad')  # Disable crash reporting
 
     # Additional stability options
     options.add_argument('--ignore-certificate-errors')
-    options.add_argument('--allow-insecure-localhost')
     options.add_argument('--disable-setuid-sandbox')
     options.add_argument('--disable-web-security')
 
+    # Set specific shared memory /dev/shm size (if needed)
+    options.add_argument('--disable-dev-shm-usage')
+    options.add_argument('--shm-size=2g')
+    
     # Set up Chrome service with explicit path to chromedriver and logging
     service = Service(
         executable_path='/usr/local/bin/chromedriver',
@@ -83,7 +92,18 @@ def capture_page(url: str, output_file: str = "screenshot.png"):
             raise
         finally:
             print("Closing Chrome...")
-            driver.quit()
+            try:
+                driver.close()  # Close current window
+                driver.quit()   # Quit browser completely
+                import psutil   # For process cleanup
+                current_pid = os.getpid()
+                current_process = psutil.Process(current_pid)
+                children = current_process.children(recursive=True)
+                for child in children:
+                    if 'chrome' in child.name().lower():
+                        child.terminate()
+            except Exception as cleanup_error:
+                print(f"Error during cleanup: {cleanup_error}")
 
     except Exception as e:
         print(f"Error initializing Chrome: {str(e)}")