Reduce Chrome-related code duplication across JS and Python

This change consolidates duplicated logic between chrome_utils.js and
extension installer hooks, as well as between Python plugin tests:

JavaScript changes:
- Add getExtensionsDir() to centralize extension directory path calculation
- Add installExtensionWithCache() to handle extension install + cache workflow
- Add CLI commands for new utilities
- Refactor all 3 extension installers (ublock, istilldontcareaboutcookies,
  twocaptcha) to use shared utilities, reducing each from ~115 lines to ~60
- Update chrome_launch hook to use getExtensionsDir()

Python test changes:
- Add chrome_test_helpers.py with shared Chrome session management utilities
- Refactor infiniscroll and modalcloser tests to use shared helpers
- setup_chrome_session(), cleanup_chrome(), get_test_env() now centralized
- Add chrome_session() context manager for automatic cleanup

Net result: ~208 lines of code removed while maintaining same functionality.
This commit is contained in:
Claude
2025-12-31 08:13:00 +00:00
parent 84a4fb0785
commit fd9ba86220
8 changed files with 469 additions and 401 deletions

View File

@@ -14,7 +14,6 @@ Tests verify:
import json
import os
import re
import signal
import subprocess
import time
import tempfile
@@ -22,37 +21,19 @@ from pathlib import Path
import pytest
# Import shared Chrome test helpers
from archivebox.plugins.chrome.tests.chrome_test_helpers import (
get_test_env,
setup_chrome_session,
cleanup_chrome,
)
PLUGIN_DIR = Path(__file__).parent.parent
PLUGINS_ROOT = PLUGIN_DIR.parent
INFINISCROLL_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_infiniscroll.*'), None)
CHROME_LAUNCH_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Crawl__30_chrome_launch.bg.js'
CHROME_TAB_HOOK = PLUGINS_ROOT / 'chrome' / 'on_Snapshot__20_chrome_tab.bg.js'
CHROME_NAVIGATE_HOOK = next((PLUGINS_ROOT / 'chrome').glob('on_Snapshot__*_chrome_navigate.*'), None)
TEST_URL = 'https://www.singsing.movie/'
def get_node_modules_dir():
"""Get NODE_MODULES_DIR for tests, checking env first."""
# Check if NODE_MODULES_DIR is already set in environment
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))
return lib_dir / 'npm' / 'node_modules'
NODE_MODULES_DIR = get_node_modules_dir()
def get_test_env():
"""Get environment with NODE_MODULES_DIR set correctly."""
env = os.environ.copy()
env['NODE_MODULES_DIR'] = str(NODE_MODULES_DIR)
return env
def test_hook_script_exists():
"""Verify on_Snapshot hook exists."""
assert INFINISCROLL_HOOK is not None, "Infiniscroll hook not found"
@@ -117,95 +98,18 @@ def test_fails_gracefully_without_chrome_session():
f"Should mention chrome/CDP/puppeteer in error: {result.stderr}"
def setup_chrome_session(tmpdir):
"""Helper to set up Chrome session with tab and navigation."""
crawl_dir = Path(tmpdir) / 'crawl'
crawl_dir.mkdir()
chrome_dir = crawl_dir / 'chrome'
chrome_dir.mkdir()
env = get_test_env()
env['CHROME_HEADLESS'] = 'true'
# Launch Chrome at crawl level
chrome_launch_process = subprocess.Popen(
['node', str(CHROME_LAUNCH_HOOK), '--crawl-id=test-infiniscroll'],
cwd=str(chrome_dir),
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
env=env
)
# Wait for Chrome to launch
for i in range(15):
if chrome_launch_process.poll() is not None:
stdout, stderr = chrome_launch_process.communicate()
raise RuntimeError(f"Chrome launch failed:\nStdout: {stdout}\nStderr: {stderr}")
if (chrome_dir / 'cdp_url.txt').exists():
break
time.sleep(1)
if not (chrome_dir / 'cdp_url.txt').exists():
raise RuntimeError("Chrome CDP URL not found after 15s")
chrome_pid = int((chrome_dir / 'chrome.pid').read_text().strip())
# Create snapshot directory structure
snapshot_dir = Path(tmpdir) / 'snapshot'
snapshot_dir.mkdir()
snapshot_chrome_dir = snapshot_dir / 'chrome'
snapshot_chrome_dir.mkdir()
# Create tab
tab_env = env.copy()
tab_env['CRAWL_OUTPUT_DIR'] = str(crawl_dir)
result = subprocess.run(
['node', str(CHROME_TAB_HOOK), f'--url={TEST_URL}', '--snapshot-id=snap-infiniscroll', '--crawl-id=test-infiniscroll'],
cwd=str(snapshot_chrome_dir),
capture_output=True,
text=True,
timeout=60,
env=tab_env
)
if result.returncode != 0:
raise RuntimeError(f"Tab creation failed: {result.stderr}")
# Navigate to URL
result = subprocess.run(
['node', str(CHROME_NAVIGATE_HOOK), f'--url={TEST_URL}', '--snapshot-id=snap-infiniscroll'],
cwd=str(snapshot_chrome_dir),
capture_output=True,
text=True,
timeout=120,
env=env
)
if result.returncode != 0:
raise RuntimeError(f"Navigation failed: {result.stderr}")
return chrome_launch_process, chrome_pid, snapshot_chrome_dir
def cleanup_chrome(chrome_launch_process, chrome_pid):
"""Helper to clean up Chrome processes."""
try:
chrome_launch_process.send_signal(signal.SIGTERM)
chrome_launch_process.wait(timeout=5)
except:
pass
try:
os.kill(chrome_pid, signal.SIGKILL)
except OSError:
pass
def test_scrolls_page_and_outputs_stats():
"""Integration test: scroll page and verify JSONL output format."""
with tempfile.TemporaryDirectory() as tmpdir:
chrome_launch_process = None
chrome_pid = None
try:
chrome_launch_process, chrome_pid, snapshot_chrome_dir = setup_chrome_session(tmpdir)
chrome_launch_process, chrome_pid, snapshot_chrome_dir = setup_chrome_session(
Path(tmpdir),
crawl_id='test-infiniscroll',
snapshot_id='snap-infiniscroll',
test_url=TEST_URL,
)
# Create infiniscroll output directory (sibling to chrome)
infiniscroll_dir = snapshot_chrome_dir.parent / 'infiniscroll'
@@ -265,7 +169,12 @@ def test_config_scroll_limit_honored():
chrome_launch_process = None
chrome_pid = None
try:
chrome_launch_process, chrome_pid, snapshot_chrome_dir = setup_chrome_session(tmpdir)
chrome_launch_process, chrome_pid, snapshot_chrome_dir = setup_chrome_session(
Path(tmpdir),
crawl_id='test-scroll-limit',
snapshot_id='snap-limit',
test_url=TEST_URL,
)
infiniscroll_dir = snapshot_chrome_dir.parent / 'infiniscroll'
infiniscroll_dir.mkdir()
@@ -317,7 +226,12 @@ def test_config_timeout_honored():
chrome_launch_process = None
chrome_pid = None
try:
chrome_launch_process, chrome_pid, snapshot_chrome_dir = setup_chrome_session(tmpdir)
chrome_launch_process, chrome_pid, snapshot_chrome_dir = setup_chrome_session(
Path(tmpdir),
crawl_id='test-timeout',
snapshot_id='snap-timeout',
test_url=TEST_URL,
)
infiniscroll_dir = snapshot_chrome_dir.parent / 'infiniscroll'
infiniscroll_dir.mkdir()