Consolidate Chrome test helpers across all plugin tests

- Add setup_test_env, launch_chromium_session, kill_chromium_session
  to chrome_test_helpers.py for extension tests
- Add chromium_session context manager for cleaner test code
- Refactor ublock, istilldontcareaboutcookies, twocaptcha tests to use
  shared helpers (~450 lines removed)
- Refactor screenshot, dom, pdf tests to use shared get_test_env
  and get_lib_dir (~60 lines removed)
- Net reduction: 228 lines of duplicate code

archivebox/plugins/chrome/tests/chrome_test_helpers.py

@@ -6,19 +6,35 @@ duplication across test files. It uses the JavaScript utilities from chrome_util
 where appropriate.
 
 Usage:
+    # For simple tests (screenshot, dom, pdf, etc.):
     from archivebox.plugins.chrome.tests.chrome_test_helpers import (
         get_test_env,
+        get_lib_dir,
+        find_chromium_binary,
+    )
+
+    # For extension tests (ublock, istilldontcareaboutcookies, twocaptcha):
+    from archivebox.plugins.chrome.tests.chrome_test_helpers import (
+        setup_test_env,
+        launch_chromium_session,
+        kill_chromium_session,
+    )
+
+    # For tab-based tests (infiniscroll, modalcloser):
+    from archivebox.plugins.chrome.tests.chrome_test_helpers import (
         setup_chrome_session,
         cleanup_chrome,
-        find_chromium_binary,
-        get_node_modules_dir,
+        chrome_session,
     )
 """
 
+import json
 import os
+import platform
 import signal
 import subprocess
 import time
+from datetime import datetime
 from pathlib import Path
 from typing import Tuple, Optional
 from contextlib import contextmanager
@@ -29,34 +45,48 @@ CHROME_PLUGIN_DIR = Path(__file__).parent.parent
 PLUGINS_ROOT = CHROME_PLUGIN_DIR.parent
 
 # Hook script locations
+CHROME_INSTALL_HOOK = CHROME_PLUGIN_DIR / 'on_Crawl__00_install_puppeteer_chromium.py'
 CHROME_LAUNCH_HOOK = CHROME_PLUGIN_DIR / 'on_Crawl__30_chrome_launch.bg.js'
 CHROME_TAB_HOOK = CHROME_PLUGIN_DIR / 'on_Snapshot__20_chrome_tab.bg.js'
 CHROME_NAVIGATE_HOOK = next(CHROME_PLUGIN_DIR.glob('on_Snapshot__*_chrome_navigate.*'), None)
 CHROME_UTILS = CHROME_PLUGIN_DIR / 'chrome_utils.js'
 
 
+def get_lib_dir() -> Path:
+    """Get LIB_DIR for tests, checking env first then ArchiveBox config.
+
+    Returns the path to the lib directory, checking:
+    1. LIB_DIR environment variable
+    2. ArchiveBox config STORAGE_CONFIG.LIB_DIR
+    """
+    if os.environ.get('LIB_DIR'):
+        return Path(os.environ['LIB_DIR'])
+    from archivebox.config.common import STORAGE_CONFIG
+    return Path(str(STORAGE_CONFIG.LIB_DIR))
+
+
 def get_node_modules_dir() -> Path:
     """Get NODE_MODULES_DIR for tests, checking env first.
 
     Returns the path to the node_modules directory, checking:
     1. NODE_MODULES_DIR environment variable
-    2. Computed from LIB_DIR via ArchiveBox config
+    2. Computed from LIB_DIR
     """
     if os.environ.get('NODE_MODULES_DIR'):
         return Path(os.environ['NODE_MODULES_DIR'])
-    # Otherwise compute from LIB_DIR
-    from archivebox.config.common import STORAGE_CONFIG
-    lib_dir = Path(os.environ.get('LIB_DIR') or str(STORAGE_CONFIG.LIB_DIR))
+    lib_dir = get_lib_dir()
     return lib_dir / 'npm' / 'node_modules'
 
 
 def get_test_env() -> dict:
-    """Get environment dict with NODE_MODULES_DIR set correctly for tests.
+    """Get environment dict with NODE_MODULES_DIR and LIB_DIR set correctly for tests.
 
-    Returns a copy of os.environ with NODE_MODULES_DIR added/updated.
-    Use this for all subprocess calls in plugin tests.
+    Returns a copy of os.environ with NODE_MODULES_DIR and LIB_DIR added/updated.
+    Use this for all subprocess calls in simple plugin tests (screenshot, dom, pdf).
     """
     env = os.environ.copy()
+    lib_dir = get_lib_dir()
+    env['LIB_DIR'] = str(lib_dir)
     env['NODE_MODULES_DIR'] = str(get_node_modules_dir())
     return env
 
@@ -113,6 +143,219 @@ def get_extensions_dir() -> str:
     return str(Path(data_dir) / 'personas' / persona / 'chrome_extensions')
 
 
+# =============================================================================
+# Extension Test Helpers
+# Used by extension tests (ublock, istilldontcareaboutcookies, twocaptcha)
+# =============================================================================
+
+
+def setup_test_env(tmpdir: Path) -> dict:
+    """Set up isolated data/lib directory structure for extension tests.
+
+    Creates structure matching real ArchiveBox data dir:
+        <tmpdir>/data/
+            lib/
+                arm64-darwin/   (or x86_64-linux, etc.)
+                    npm/
+                        .bin/
+                        node_modules/
+            personas/
+                Default/
+                    chrome_extensions/
+            users/
+                testuser/
+                    crawls/
+                    snapshots/
+
+    Calls chrome install hook which handles puppeteer-core and chromium installation.
+    Returns env dict with DATA_DIR, LIB_DIR, NPM_BIN_DIR, NODE_MODULES_DIR, CHROME_BINARY, etc.
+
+    Args:
+        tmpdir: Base temporary directory for the test
+
+    Returns:
+        Environment dict with all paths set, or pytest.skip() if Chrome install fails
+    """
+    import pytest
+
+    # Determine machine type (matches archivebox.config.paths.get_machine_type())
+    machine = platform.machine().lower()
+    system = platform.system().lower()
+    if machine in ('arm64', 'aarch64'):
+        machine = 'arm64'
+    elif machine in ('x86_64', 'amd64'):
+        machine = 'x86_64'
+    machine_type = f"{machine}-{system}"
+
+    # Create proper directory structure matching real ArchiveBox layout
+    data_dir = tmpdir / 'data'
+    lib_dir = data_dir / 'lib' / machine_type
+    npm_dir = lib_dir / 'npm'
+    npm_bin_dir = npm_dir / '.bin'
+    node_modules_dir = npm_dir / 'node_modules'
+
+    # Extensions go under personas/Default/
+    chrome_extensions_dir = data_dir / 'personas' / 'Default' / 'chrome_extensions'
+
+    # User data goes under users/{username}/
+    date_str = datetime.now().strftime('%Y%m%d')
+    users_dir = data_dir / 'users' / 'testuser'
+    crawls_dir = users_dir / 'crawls' / date_str
+    snapshots_dir = users_dir / 'snapshots' / date_str
+
+    # Create all directories
+    node_modules_dir.mkdir(parents=True, exist_ok=True)
+    npm_bin_dir.mkdir(parents=True, exist_ok=True)
+    chrome_extensions_dir.mkdir(parents=True, exist_ok=True)
+    crawls_dir.mkdir(parents=True, exist_ok=True)
+    snapshots_dir.mkdir(parents=True, exist_ok=True)
+
+    # Build complete env dict
+    env = os.environ.copy()
+    env.update({
+        'DATA_DIR': str(data_dir),
+        'LIB_DIR': str(lib_dir),
+        'MACHINE_TYPE': machine_type,
+        'NPM_BIN_DIR': str(npm_bin_dir),
+        'NODE_MODULES_DIR': str(node_modules_dir),
+        'CHROME_EXTENSIONS_DIR': str(chrome_extensions_dir),
+        'CRAWLS_DIR': str(crawls_dir),
+        'SNAPSHOTS_DIR': str(snapshots_dir),
+    })
+
+    # Only set headless if not already in environment (allow override for debugging)
+    if 'CHROME_HEADLESS' not in os.environ:
+        env['CHROME_HEADLESS'] = 'true'
+
+    # Call chrome install hook (installs puppeteer-core and chromium, outputs JSONL)
+    result = subprocess.run(
+        ['python', str(CHROME_INSTALL_HOOK)],
+        capture_output=True, text=True, timeout=120, env=env
+    )
+    if result.returncode != 0:
+        pytest.skip(f"Chrome install hook failed: {result.stderr}")
+
+    # Parse JSONL output to get CHROME_BINARY
+    chrome_binary = None
+    for line in result.stdout.strip().split('\n'):
+        if not line.strip():
+            continue
+        try:
+            data = json.loads(line)
+            if data.get('type') == 'Binary' and data.get('abspath'):
+                chrome_binary = data['abspath']
+                break
+        except json.JSONDecodeError:
+            continue
+
+    if not chrome_binary or not Path(chrome_binary).exists():
+        pytest.skip(f"Chromium binary not found: {chrome_binary}")
+
+    env['CHROME_BINARY'] = chrome_binary
+    return env
+
+
+def launch_chromium_session(env: dict, chrome_dir: Path, crawl_id: str) -> Tuple[subprocess.Popen, str]:
+    """Launch Chromium and return (process, cdp_url).
+
+    This launches Chrome using the chrome launch hook and waits for the CDP URL
+    to become available. Use this for extension tests that need direct CDP access.
+
+    Args:
+        env: Environment dict (from setup_test_env)
+        chrome_dir: Directory for Chrome to write its files (cdp_url.txt, chrome.pid, etc.)
+        crawl_id: ID for the crawl
+
+    Returns:
+        Tuple of (chrome_launch_process, cdp_url)
+
+    Raises:
+        RuntimeError: If Chrome fails to launch or CDP URL not available after 20s
+    """
+    chrome_dir.mkdir(parents=True, exist_ok=True)
+
+    chrome_launch_process = subprocess.Popen(
+        ['node', str(CHROME_LAUNCH_HOOK), f'--crawl-id={crawl_id}'],
+        cwd=str(chrome_dir),
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+        env=env
+    )
+
+    # Wait for Chromium to launch and CDP URL to be available
+    cdp_url = None
+    for i in range(20):
+        if chrome_launch_process.poll() is not None:
+            stdout, stderr = chrome_launch_process.communicate()
+            raise RuntimeError(f"Chromium launch failed:\nStdout: {stdout}\nStderr: {stderr}")
+        cdp_file = chrome_dir / 'cdp_url.txt'
+        if cdp_file.exists():
+            cdp_url = cdp_file.read_text().strip()
+            break
+        time.sleep(1)
+
+    if not cdp_url:
+        chrome_launch_process.kill()
+        raise RuntimeError("Chromium CDP URL not found after 20s")
+
+    return chrome_launch_process, cdp_url
+
+
+def kill_chromium_session(chrome_launch_process: subprocess.Popen, chrome_dir: Path) -> None:
+    """Clean up Chromium process launched by launch_chromium_session.
+
+    Args:
+        chrome_launch_process: The Popen object from launch_chromium_session
+        chrome_dir: The chrome directory containing chrome.pid
+    """
+    try:
+        chrome_launch_process.send_signal(signal.SIGTERM)
+        chrome_launch_process.wait(timeout=5)
+    except Exception:
+        pass
+    chrome_pid_file = chrome_dir / 'chrome.pid'
+    if chrome_pid_file.exists():
+        try:
+            chrome_pid = int(chrome_pid_file.read_text().strip())
+            os.kill(chrome_pid, signal.SIGKILL)
+        except (OSError, ValueError):
+            pass
+
+
+@contextmanager
+def chromium_session(env: dict, chrome_dir: Path, crawl_id: str):
+    """Context manager for Chromium sessions with automatic cleanup.
+
+    Usage:
+        with chromium_session(env, chrome_dir, 'test-crawl') as (process, cdp_url):
+            # Use cdp_url to connect with puppeteer
+            pass
+        # Chromium automatically cleaned up
+
+    Args:
+        env: Environment dict (from setup_test_env)
+        chrome_dir: Directory for Chrome files
+        crawl_id: ID for the crawl
+
+    Yields:
+        Tuple of (chrome_launch_process, cdp_url)
+    """
+    chrome_launch_process = None
+    try:
+        chrome_launch_process, cdp_url = launch_chromium_session(env, chrome_dir, crawl_id)
+        yield chrome_launch_process, cdp_url
+    finally:
+        if chrome_launch_process:
+            kill_chromium_session(chrome_launch_process, chrome_dir)
+
+
+# =============================================================================
+# Tab-based Test Helpers
+# Used by tab-based tests (infiniscroll, modalcloser)
+# =============================================================================
+
+
 def setup_chrome_session(
     tmpdir: Path,
     crawl_id: str = 'test-crawl',

archivebox/plugins/dom/tests/test_dom.py

@@ -20,6 +20,11 @@ from pathlib import Path
 
 import pytest
 
+from archivebox.plugins.chrome.tests.chrome_test_helpers import (
+    get_test_env,
+    get_lib_dir,
+)
+
 
 PLUGIN_DIR = Path(__file__).parent.parent
 PLUGINS_ROOT = PLUGIN_DIR.parent
@@ -27,22 +32,9 @@ DOM_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_dom.*'), None)
 NPM_PROVIDER_HOOK = next((PLUGINS_ROOT / 'npm').glob('on_Binary__install_using_npm_provider.py'), None)
 TEST_URL = 'https://example.com'
 
-# Get LIB_DIR for NODE_MODULES_DIR
-def get_lib_dir():
-    """Get LIB_DIR for tests."""
-    from archivebox.config.common import STORAGE_CONFIG
-    return Path(os.environ.get('LIB_DIR') or str(STORAGE_CONFIG.LIB_DIR))
-
 LIB_DIR = get_lib_dir()
 NODE_MODULES_DIR = LIB_DIR / 'npm' / 'node_modules'
 
-def get_test_env():
-    """Get environment with NODE_MODULES_DIR set correctly."""
-    env = os.environ.copy()
-    env['NODE_MODULES_DIR'] = str(NODE_MODULES_DIR)
-    env['LIB_DIR'] = str(LIB_DIR)
-    return env
-
 
 def test_hook_script_exists():
     """Verify on_Snapshot hook exists."""

archivebox/plugins/istilldontcareaboutcookies/tests/test_istilldontcareaboutcookies.py

@@ -14,6 +14,14 @@ from pathlib import Path
 
 import pytest
 
+from archivebox.plugins.chrome.tests.chrome_test_helpers import (
+    setup_test_env,
+    launch_chromium_session,
+    kill_chromium_session,
+    CHROME_LAUNCH_HOOK,
+    PLUGINS_ROOT,
+)
+
 
 PLUGIN_DIR = Path(__file__).parent.parent
 INSTALL_SCRIPT = next(PLUGIN_DIR.glob('on_Crawl__*_install_istilldontcareaboutcookies_extension.*'), None)
@@ -124,107 +132,6 @@ def test_no_configuration_required():
         assert "API" not in (result.stdout + result.stderr) or result.returncode == 0
 
 
-PLUGINS_ROOT = PLUGIN_DIR.parent
-CHROME_INSTALL_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Crawl__00_install_puppeteer_chromium.py'
-CHROME_LAUNCH_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Crawl__30_chrome_launch.bg.js'
-
-
-def setup_test_env(tmpdir: Path) -> dict:
-    """Set up isolated data/lib directory structure for tests.
-
-    Creates structure matching real ArchiveBox data dir:
-        <tmpdir>/data/
-            lib/
-                arm64-darwin/   (or x86_64-linux, etc.)
-                    npm/
-                        .bin/
-                        node_modules/
-            personas/
-                Default/
-                    chrome_extensions/
-            users/
-                testuser/
-                    crawls/
-                    snapshots/
-
-    Calls chrome install hook which handles puppeteer-core and chromium installation.
-    Returns env dict with DATA_DIR, LIB_DIR, NPM_BIN_DIR, NODE_MODULES_DIR, CHROME_BINARY, etc.
-    """
-    import platform
-    from datetime import datetime
-
-    # Determine machine type (matches archivebox.config.paths.get_machine_type())
-    machine = platform.machine().lower()
-    system = platform.system().lower()
-    if machine in ('arm64', 'aarch64'):
-        machine = 'arm64'
-    elif machine in ('x86_64', 'amd64'):
-        machine = 'x86_64'
-    machine_type = f"{machine}-{system}"
-
-    # Create proper directory structure matching real ArchiveBox layout
-    data_dir = tmpdir / 'data'
-    lib_dir = data_dir / 'lib' / machine_type
-    npm_dir = lib_dir / 'npm'
-    npm_bin_dir = npm_dir / '.bin'
-    node_modules_dir = npm_dir / 'node_modules'
-
-    # Extensions go under personas/Default/
-    chrome_extensions_dir = data_dir / 'personas' / 'Default' / 'chrome_extensions'
-
-    # User data goes under users/{username}/
-    date_str = datetime.now().strftime('%Y%m%d')
-    users_dir = data_dir / 'users' / 'testuser'
-    crawls_dir = users_dir / 'crawls' / date_str
-    snapshots_dir = users_dir / 'snapshots' / date_str
-
-    # Create all directories
-    node_modules_dir.mkdir(parents=True, exist_ok=True)
-    npm_bin_dir.mkdir(parents=True, exist_ok=True)
-    chrome_extensions_dir.mkdir(parents=True, exist_ok=True)
-    crawls_dir.mkdir(parents=True, exist_ok=True)
-    snapshots_dir.mkdir(parents=True, exist_ok=True)
-
-    # Build complete env dict
-    env = os.environ.copy()
-    env.update({
-        'DATA_DIR': str(data_dir),
-        'LIB_DIR': str(lib_dir),
-        'MACHINE_TYPE': machine_type,
-        'NPM_BIN_DIR': str(npm_bin_dir),
-        'NODE_MODULES_DIR': str(node_modules_dir),
-        'CHROME_EXTENSIONS_DIR': str(chrome_extensions_dir),
-        'CRAWLS_DIR': str(crawls_dir),
-        'SNAPSHOTS_DIR': str(snapshots_dir),
-    })
-
-    # Call chrome install hook (installs puppeteer-core and chromium, outputs JSONL)
-    result = subprocess.run(
-        ['python', str(CHROME_INSTALL_HOOK)],
-        capture_output=True, text=True, timeout=120, env=env
-    )
-    if result.returncode != 0:
-        pytest.skip(f"Chrome install hook failed: {result.stderr}")
-
-    # Parse JSONL output to get CHROME_BINARY
-    chrome_binary = None
-    for line in result.stdout.strip().split('\n'):
-        if not line.strip():
-            continue
-        try:
-            data = json.loads(line)
-            if data.get('type') == 'Binary' and data.get('abspath'):
-                chrome_binary = data['abspath']
-                break
-        except json.JSONDecodeError:
-            continue
-
-    if not chrome_binary or not Path(chrome_binary).exists():
-        pytest.skip(f"Chromium binary not found: {chrome_binary}")
-
-    env['CHROME_BINARY'] = chrome_binary
-    return env
-
 TEST_URL = 'https://www.filmin.es/'
 
 
@@ -420,54 +327,6 @@ const puppeteer = require('puppeteer-core');
                     pass
 
 
-def launch_chromium_session(env: dict, chrome_dir: Path, crawl_id: str):
-    """Launch Chromium and return (process, cdp_url) or raise on failure."""
-    chrome_dir.mkdir(parents=True, exist_ok=True)
-
-    chrome_launch_process = subprocess.Popen(
-        ['node', str(CHROME_LAUNCH_HOOK), f'--crawl-id={crawl_id}'],
-        cwd=str(chrome_dir),
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
-        text=True,
-        env=env
-    )
-
-    # Wait for Chromium to launch and CDP URL to be available
-    cdp_url = None
-    for i in range(20):
-        if chrome_launch_process.poll() is not None:
-            stdout, stderr = chrome_launch_process.communicate()
-            raise RuntimeError(f"Chromium launch failed:\nStdout: {stdout}\nStderr: {stderr}")
-        cdp_file = chrome_dir / 'cdp_url.txt'
-        if cdp_file.exists():
-            cdp_url = cdp_file.read_text().strip()
-            break
-        time.sleep(1)
-
-    if not cdp_url:
-        chrome_launch_process.kill()
-        raise RuntimeError("Chromium CDP URL not found after 20s")
-
-    return chrome_launch_process, cdp_url
-
-
-def kill_chromium_session(chrome_launch_process, chrome_dir: Path):
-    """Clean up Chromium process."""
-    try:
-        chrome_launch_process.send_signal(signal.SIGTERM)
-        chrome_launch_process.wait(timeout=5)
-    except:
-        pass
-    chrome_pid_file = chrome_dir / 'chrome.pid'
-    if chrome_pid_file.exists():
-        try:
-            chrome_pid = int(chrome_pid_file.read_text().strip())
-            os.kill(chrome_pid, signal.SIGKILL)
-        except (OSError, ValueError):
-            pass
-
-
 def check_cookie_consent_visibility(cdp_url: str, test_url: str, env: dict, script_dir: Path) -> dict:
     """Check if cookie consent elements are visible on a page.
 

archivebox/plugins/pdf/tests/test_pdf.py

@@ -21,6 +21,11 @@ from pathlib import Path
 
 import pytest
 
+from archivebox.plugins.chrome.tests.chrome_test_helpers import (
+    get_test_env,
+    get_lib_dir,
+)
+
 
 PLUGIN_DIR = Path(__file__).parent.parent
 PLUGINS_ROOT = PLUGIN_DIR.parent
@@ -28,22 +33,9 @@ PDF_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_pdf.*'), None)
 NPM_PROVIDER_HOOK = PLUGINS_ROOT / 'npm' / 'on_Binary__install_using_npm_provider.py'
 TEST_URL = 'https://example.com'
 
-# Get LIB_DIR for NODE_MODULES_DIR
-def get_lib_dir():
-    """Get LIB_DIR for tests."""
-    from archivebox.config.common import STORAGE_CONFIG
-    return Path(os.environ.get('LIB_DIR') or str(STORAGE_CONFIG.LIB_DIR))
-
 LIB_DIR = get_lib_dir()
 NODE_MODULES_DIR = LIB_DIR / 'npm' / 'node_modules'
 
-def get_test_env():
-    """Get environment with NODE_MODULES_DIR set correctly."""
-    env = os.environ.copy()
-    env['NODE_MODULES_DIR'] = str(NODE_MODULES_DIR)
-    env['LIB_DIR'] = str(LIB_DIR)
-    return env
-
 
 def test_hook_script_exists():
     """Verify on_Snapshot hook exists."""

archivebox/plugins/screenshot/tests/test_screenshot.py

@@ -20,28 +20,20 @@ from pathlib import Path
 
 import pytest
 
+from archivebox.plugins.chrome.tests.chrome_test_helpers import (
+    get_test_env,
+    get_lib_dir,
+)
+
 
 PLUGIN_DIR = Path(__file__).parent.parent
 PLUGINS_ROOT = PLUGIN_DIR.parent
 SCREENSHOT_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_screenshot.*'), None)
 TEST_URL = 'https://example.com'
 
-# Get LIB_DIR for NODE_MODULES_DIR
-def get_lib_dir():
-    """Get LIB_DIR for tests."""
-    from archivebox.config.common import STORAGE_CONFIG
-    return Path(os.environ.get('LIB_DIR') or str(STORAGE_CONFIG.LIB_DIR))
-
 LIB_DIR = get_lib_dir()
 NODE_MODULES_DIR = LIB_DIR / 'npm' / 'node_modules'
 
-def get_test_env():
-    """Get environment with NODE_MODULES_DIR set correctly."""
-    env = os.environ.copy()
-    env['NODE_MODULES_DIR'] = str(NODE_MODULES_DIR)
-    env['LIB_DIR'] = str(LIB_DIR)
-    return env
-
 
 def test_hook_script_exists():
     """Verify on_Snapshot hook exists."""

archivebox/plugins/twocaptcha/tests/test_twocaptcha.py

@@ -16,184 +16,25 @@ from pathlib import Path
 
 import pytest
 
+from archivebox.plugins.chrome.tests.chrome_test_helpers import (
+    setup_test_env,
+    launch_chromium_session,
+    kill_chromium_session,
+    CHROME_LAUNCH_HOOK,
+    PLUGINS_ROOT,
+)
+
 
 PLUGIN_DIR = Path(__file__).parent.parent
-PLUGINS_ROOT = PLUGIN_DIR.parent
 INSTALL_SCRIPT = PLUGIN_DIR / 'on_Crawl__20_install_twocaptcha_extension.js'
 CONFIG_SCRIPT = PLUGIN_DIR / 'on_Crawl__25_configure_twocaptcha_extension_options.js'
-CHROME_INSTALL_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Crawl__00_install_puppeteer_chromium.py'
-CHROME_LAUNCH_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Crawl__30_chrome_launch.bg.js'
 
 TEST_URL = 'https://2captcha.com/demo/recaptcha-v2'
 
 
-def setup_test_env(tmpdir: Path) -> dict:
-    """Set up isolated data/lib directory structure for tests.
-
-    Creates structure matching real ArchiveBox data dir:
-        <tmpdir>/data/
-            lib/
-                arm64-darwin/   (or x86_64-linux, etc.)
-                    npm/
-                        .bin/
-                        node_modules/
-            personas/
-                default/
-                    chrome_extensions/
-            users/
-                testuser/
-                    crawls/
-                    snapshots/
-
-    Calls chrome install hook which handles puppeteer-core and chromium installation.
-    Returns env dict with DATA_DIR, LIB_DIR, NPM_BIN_DIR, NODE_MODULES_DIR, CHROME_BINARY, etc.
-    """
-    import platform
-    from datetime import datetime
-
-    # Determine machine type (matches archivebox.config.paths.get_machine_type())
-    machine = platform.machine().lower()
-    system = platform.system().lower()
-    if machine in ('arm64', 'aarch64'):
-        machine = 'arm64'
-    elif machine in ('x86_64', 'amd64'):
-        machine = 'x86_64'
-    machine_type = f"{machine}-{system}"
-
-    # Create proper directory structure matching real ArchiveBox layout
-    data_dir = tmpdir / 'data'
-    lib_dir = data_dir / 'lib' / machine_type
-    npm_dir = lib_dir / 'npm'
-    npm_bin_dir = npm_dir / '.bin'
-    node_modules_dir = npm_dir / 'node_modules'
-
-    # Extensions go under personas/Default/
-    chrome_extensions_dir = data_dir / 'personas' / 'Default' / 'chrome_extensions'
-
-    # User data goes under users/{username}/
-    date_str = datetime.now().strftime('%Y%m%d')
-    users_dir = data_dir / 'users' / 'testuser'
-    crawls_dir = users_dir / 'crawls' / date_str
-    snapshots_dir = users_dir / 'snapshots' / date_str
-
-    # Create all directories
-    node_modules_dir.mkdir(parents=True, exist_ok=True)
-    npm_bin_dir.mkdir(parents=True, exist_ok=True)
-    chrome_extensions_dir.mkdir(parents=True, exist_ok=True)
-    crawls_dir.mkdir(parents=True, exist_ok=True)
-    snapshots_dir.mkdir(parents=True, exist_ok=True)
-
-    # Build complete env dict
-    env = os.environ.copy()
-    env.update({
-        'DATA_DIR': str(data_dir),
-        'LIB_DIR': str(lib_dir),
-        'MACHINE_TYPE': machine_type,
-        'NPM_BIN_DIR': str(npm_bin_dir),
-        'NODE_MODULES_DIR': str(node_modules_dir),
-        'CHROME_EXTENSIONS_DIR': str(chrome_extensions_dir),
-        'CRAWLS_DIR': str(crawls_dir),
-        'SNAPSHOTS_DIR': str(snapshots_dir),
-    })
-
-    # Only set headless if not already in environment (allow override for debugging)
-    if 'CHROME_HEADLESS' not in os.environ:
-        env['CHROME_HEADLESS'] = 'true'
-
-    # Call chrome install hook (installs puppeteer-core and chromium, outputs JSONL)
-    result = subprocess.run(
-        ['python', str(CHROME_INSTALL_HOOK)],
-        capture_output=True, text=True, timeout=120, env=env
-    )
-    if result.returncode != 0:
-        pytest.skip(f"Chrome install hook failed: {result.stderr}")
-
-    # Parse JSONL output to get CHROME_BINARY
-    chrome_binary = None
-    for line in result.stdout.strip().split('\n'):
-        if not line.strip():
-            continue
-        try:
-            data = json.loads(line)
-            if data.get('type') == 'Binary' and data.get('abspath'):
-                chrome_binary = data['abspath']
-                break
-        except json.JSONDecodeError:
-            continue
-
-    if not chrome_binary or not Path(chrome_binary).exists():
-        pytest.skip(f"Chromium binary not found: {chrome_binary}")
-
-    env['CHROME_BINARY'] = chrome_binary
-    return env
-
-
-def launch_chrome(env: dict, chrome_dir: Path, crawl_id: str):
-    """Launch Chromium and return (process, cdp_url)."""
-    chrome_dir.mkdir(parents=True, exist_ok=True)
-
-    process = subprocess.Popen(
-        ['node', str(CHROME_LAUNCH_HOOK), f'--crawl-id={crawl_id}'],
-        cwd=str(chrome_dir),
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
-        text=True,
-        env=env
-    )
-
-    cdp_url = None
-    extensions_ready = False
-    for _ in range(30):
-        if process.poll() is not None:
-            stdout, stderr = process.communicate()
-            raise RuntimeError(f"Chromium failed:\n{stdout}\n{stderr}")
-        cdp_file = chrome_dir / 'cdp_url.txt'
-        ext_file = chrome_dir / 'extensions.json'
-        if cdp_file.exists() and not cdp_url:
-            cdp_url = cdp_file.read_text().strip()
-        if ext_file.exists():
-            extensions_ready = True
-        if cdp_url and extensions_ready:
-            break
-        time.sleep(1)
-
-    if not cdp_url:
-        process.kill()
-        stdout, stderr = process.communicate()
-        raise RuntimeError(f"CDP URL not found after 30s.\nstdout: {stdout}\nstderr: {stderr}")
-
-    # Print chrome launch hook output for debugging
-    import select
-    if hasattr(select, 'poll'):
-        # Read any available stderr without blocking
-        import fcntl
-        import os as os_module
-        fd = process.stderr.fileno()
-        fl = fcntl.fcntl(fd, fcntl.F_GETFL)
-        fcntl.fcntl(fd, fcntl.F_SETFL, fl | os_module.O_NONBLOCK)
-        try:
-            stderr_output = process.stderr.read()
-            if stderr_output:
-                print(f"[Chrome Launch Hook Output]\n{stderr_output}")
-        except:
-            pass
-
-    return process, cdp_url
-
-
-def kill_chrome(process, chrome_dir: Path):
-    """Kill Chromium process."""
-    try:
-        process.send_signal(signal.SIGTERM)
-        process.wait(timeout=5)
-    except:
-        pass
-    pid_file = chrome_dir / 'chrome.pid'
-    if pid_file.exists():
-        try:
-            os.kill(int(pid_file.read_text().strip()), signal.SIGKILL)
-        except:
-            pass
+# Alias for backward compatibility with existing test names
+launch_chrome = launch_chromium_session
+kill_chrome = kill_chromium_session
 
 
 class TestTwoCaptcha:

archivebox/plugins/ublock/tests/test_ublock.py

@@ -12,6 +12,14 @@ from pathlib import Path
 
 import pytest
 
+from archivebox.plugins.chrome.tests.chrome_test_helpers import (
+    setup_test_env,
+    launch_chromium_session,
+    kill_chromium_session,
+    CHROME_LAUNCH_HOOK,
+    PLUGINS_ROOT,
+)
+
 
 PLUGIN_DIR = Path(__file__).parent.parent
 INSTALL_SCRIPT = next(PLUGIN_DIR.glob('on_Crawl__*_install_ublock_extension.*'), None)
@@ -157,64 +165,6 @@ def test_large_extension_size():
             assert size_bytes > 1_000_000, f"uBlock Origin should be > 1MB, got {size_bytes} bytes"
 
 
-PLUGINS_ROOT = PLUGIN_DIR.parent
-CHROME_INSTALL_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Crawl__00_install_puppeteer_chromium.py'
-CHROME_LAUNCH_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Crawl__30_chrome_launch.bg.js'
-
-
-def launch_chromium_session(env: dict, chrome_dir: Path, crawl_id: str):
-    """Launch Chromium and return (process, cdp_url) or raise on failure."""
-    import signal
-    import time
-
-    chrome_dir.mkdir(parents=True, exist_ok=True)
-
-    chrome_launch_process = subprocess.Popen(
-        ['node', str(CHROME_LAUNCH_HOOK), f'--crawl-id={crawl_id}'],
-        cwd=str(chrome_dir),
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
-        text=True,
-        env=env
-    )
-
-    # Wait for Chromium to launch and CDP URL to be available
-    cdp_url = None
-    for i in range(20):
-        if chrome_launch_process.poll() is not None:
-            stdout, stderr = chrome_launch_process.communicate()
-            raise RuntimeError(f"Chromium launch failed:\nStdout: {stdout}\nStderr: {stderr}")
-        cdp_file = chrome_dir / 'cdp_url.txt'
-        if cdp_file.exists():
-            cdp_url = cdp_file.read_text().strip()
-            break
-        time.sleep(1)
-
-    if not cdp_url:
-        chrome_launch_process.kill()
-        raise RuntimeError("Chromium CDP URL not found after 20s")
-
-    return chrome_launch_process, cdp_url
-
-
-def kill_chromium_session(chrome_launch_process, chrome_dir: Path):
-    """Clean up Chromium process."""
-    import signal
-
-    try:
-        chrome_launch_process.send_signal(signal.SIGTERM)
-        chrome_launch_process.wait(timeout=5)
-    except:
-        pass
-    chrome_pid_file = chrome_dir / 'chrome.pid'
-    if chrome_pid_file.exists():
-        try:
-            chrome_pid = int(chrome_pid_file.read_text().strip())
-            os.kill(chrome_pid, signal.SIGKILL)
-        except (OSError, ValueError):
-            pass
-
-
 def check_ad_blocking(cdp_url: str, test_url: str, env: dict, script_dir: Path) -> dict:
     """Check ad blocking effectiveness by counting ad elements on page.
 
@@ -350,103 +300,6 @@ const puppeteer = require('puppeteer-core');
     return json.loads(output_lines[-1])
 
 
-def setup_test_env(tmpdir: Path) -> dict:
-    """Set up isolated data/lib directory structure for tests.
-
-    Creates structure matching real ArchiveBox data dir:
-        <tmpdir>/data/
-            lib/
-                arm64-darwin/   (or x86_64-linux, etc.)
-                    npm/
-                        .bin/
-                        node_modules/
-            personas/
-                default/
-                    chrome_extensions/
-            users/
-                testuser/
-                    crawls/
-                    snapshots/
-
-    Calls chrome install hook which handles puppeteer-core and chromium installation.
-    Returns env dict with DATA_DIR, LIB_DIR, NPM_BIN_DIR, NODE_MODULES_DIR, CHROME_BINARY, etc.
-    """
-    import platform
-    from datetime import datetime
-
-    # Determine machine type (matches archivebox.config.paths.get_machine_type())
-    machine = platform.machine().lower()
-    system = platform.system().lower()
-    if machine in ('arm64', 'aarch64'):
-        machine = 'arm64'
-    elif machine in ('x86_64', 'amd64'):
-        machine = 'x86_64'
-    machine_type = f"{machine}-{system}"
-
-    # Create proper directory structure matching real ArchiveBox layout
-    data_dir = tmpdir / 'data'
-    lib_dir = data_dir / 'lib' / machine_type
-    npm_dir = lib_dir / 'npm'
-    npm_bin_dir = npm_dir / '.bin'
-    node_modules_dir = npm_dir / 'node_modules'
-
-    # Extensions go under personas/Default/
-    chrome_extensions_dir = data_dir / 'personas' / 'Default' / 'chrome_extensions'
-
-    # User data goes under users/{username}/
-    date_str = datetime.now().strftime('%Y%m%d')
-    users_dir = data_dir / 'users' / 'testuser'
-    crawls_dir = users_dir / 'crawls' / date_str
-    snapshots_dir = users_dir / 'snapshots' / date_str
-
-    # Create all directories
-    node_modules_dir.mkdir(parents=True, exist_ok=True)
-    npm_bin_dir.mkdir(parents=True, exist_ok=True)
-    chrome_extensions_dir.mkdir(parents=True, exist_ok=True)
-    crawls_dir.mkdir(parents=True, exist_ok=True)
-    snapshots_dir.mkdir(parents=True, exist_ok=True)
-
-    # Build complete env dict
-    env = os.environ.copy()
-    env.update({
-        'DATA_DIR': str(data_dir),
-        'LIB_DIR': str(lib_dir),
-        'MACHINE_TYPE': machine_type,
-        'NPM_BIN_DIR': str(npm_bin_dir),
-        'NODE_MODULES_DIR': str(node_modules_dir),
-        'CHROME_EXTENSIONS_DIR': str(chrome_extensions_dir),
-        'CRAWLS_DIR': str(crawls_dir),
-        'SNAPSHOTS_DIR': str(snapshots_dir),
-    })
-
-    # Call chrome install hook (installs puppeteer-core and chromium, outputs JSONL)
-    result = subprocess.run(
-        ['python', str(CHROME_INSTALL_HOOK)],
-        capture_output=True, text=True, timeout=120, env=env
-    )
-    if result.returncode != 0:
-        pytest.skip(f"Chrome install hook failed: {result.stderr}")
-
-    # Parse JSONL output to get CHROME_BINARY
-    chrome_binary = None
-    for line in result.stdout.strip().split('\n'):
-        if not line.strip():
-            continue
-        try:
-            data = json.loads(line)
-            if data.get('type') == 'Binary' and data.get('abspath'):
-                chrome_binary = data['abspath']
-                break
-        except json.JSONDecodeError:
-            continue
-
-    if not chrome_binary or not Path(chrome_binary).exists():
-        pytest.skip(f"Chromium binary not found: {chrome_binary}")
-
-    env['CHROME_BINARY'] = chrome_binary
-    return env
-
-
 # Test URL: Yahoo has many ads that uBlock should block
 TEST_URL = 'https://www.yahoo.com/'