more tests and migrations fixes

archivebox/plugins/forumdl/config.json

@@ -0,0 +1,46 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "SAVE_FORUMDL": {
+      "type": "boolean",
+      "default": true,
+      "description": "Enable forum downloading with forum-dl"
+    },
+    "FORUMDL_BINARY": {
+      "type": "string",
+      "default": "forum-dl",
+      "description": "Path to forum-dl binary"
+    },
+    "FORUMDL_TIMEOUT": {
+      "type": "integer",
+      "default": 3600,
+      "minimum": 30,
+      "x-fallback": "TIMEOUT",
+      "description": "Timeout for forum downloads in seconds"
+    },
+    "FORUMDL_OUTPUT_FORMAT": {
+      "type": "string",
+      "default": "jsonl",
+      "enum": ["jsonl", "warc", "mbox", "maildir", "mh", "mmdf", "babyl"],
+      "description": "Output format for forum downloads"
+    },
+    "FORUMDL_TEXTIFY": {
+      "type": "boolean",
+      "default": false,
+      "description": "Convert HTML content to plaintext (keep false to preserve HTML)"
+    },
+    "FORUMDL_CHECK_SSL_VALIDITY": {
+      "type": "boolean",
+      "default": true,
+      "x-fallback": "CHECK_SSL_VALIDITY",
+      "description": "Whether to verify SSL certificates"
+    },
+    "FORUMDL_EXTRA_ARGS": {
+      "type": "string",
+      "default": "",
+      "description": "Extra arguments for forum-dl (space-separated)"
+    }
+  }
+}

archivebox/plugins/forumdl/on_Crawl__00_validate_forumdl.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+"""
+Validation hook for forum-dl.
+
+Runs at crawl start to verify forum-dl binary is available.
+Outputs JSONL for InstalledBinary and Machine config updates.
+"""
+
+import os
+import sys
+import json
+import shutil
+import hashlib
+import subprocess
+from pathlib import Path
+
+
+def get_binary_version(abspath: str, version_flag: str = '--version') -> str | None:
+    """Get version string from binary."""
+    try:
+        result = subprocess.run(
+            [abspath, version_flag],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+        if result.returncode == 0 and result.stdout:
+            first_line = result.stdout.strip().split('\n')[0]
+            return first_line[:64]
+    except Exception:
+        pass
+    return None
+
+
+def get_binary_hash(abspath: str) -> str | None:
+    """Get SHA256 hash of binary."""
+    try:
+        with open(abspath, 'rb') as f:
+            return hashlib.sha256(f.read()).hexdigest()
+    except Exception:
+        return None
+
+
+def find_forumdl() -> dict | None:
+    """Find forum-dl binary."""
+    try:
+        from abx_pkg import Binary, PipProvider, EnvProvider
+
+        class ForumdlBinary(Binary):
+            name: str = 'forum-dl'
+            binproviders_supported = [PipProvider(), EnvProvider()]
+
+        binary = ForumdlBinary()
+        loaded = binary.load()
+        if loaded and loaded.abspath:
+            return {
+                'name': 'forum-dl',
+                'abspath': str(loaded.abspath),
+                'version': str(loaded.version) if loaded.version else None,
+                'sha256': loaded.sha256 if hasattr(loaded, 'sha256') else None,
+                'binprovider': loaded.binprovider.name if loaded.binprovider else 'env',
+            }
+    except ImportError:
+        pass
+    except Exception:
+        pass
+
+    # Fallback to shutil.which
+    abspath = shutil.which('forum-dl') or os.environ.get('FORUMDL_BINARY', '')
+    if abspath and Path(abspath).is_file():
+        return {
+            'name': 'forum-dl',
+            'abspath': abspath,
+            'version': get_binary_version(abspath),
+            'sha256': get_binary_hash(abspath),
+            'binprovider': 'env',
+        }
+
+    return None
+
+
+def main():
+    # Check for forum-dl (required)
+    forumdl_result = find_forumdl()
+
+    missing_deps = []
+
+    # Emit results for forum-dl
+    if forumdl_result and forumdl_result.get('abspath'):
+        print(json.dumps({
+            'type': 'InstalledBinary',
+            'name': forumdl_result['name'],
+            'abspath': forumdl_result['abspath'],
+            'version': forumdl_result['version'],
+            'sha256': forumdl_result['sha256'],
+            'binprovider': forumdl_result['binprovider'],
+        }))
+
+        print(json.dumps({
+            'type': 'Machine',
+            '_method': 'update',
+            'key': 'config/FORUMDL_BINARY',
+            'value': forumdl_result['abspath'],
+        }))
+
+        if forumdl_result['version']:
+            print(json.dumps({
+                'type': 'Machine',
+                '_method': 'update',
+                'key': 'config/FORUMDL_VERSION',
+                'value': forumdl_result['version'],
+            }))
+    else:
+        print(json.dumps({
+            'type': 'Dependency',
+            'bin_name': 'forum-dl',
+            'bin_providers': 'pip,env',
+        }))
+        missing_deps.append('forum-dl')
+
+    if missing_deps:
+        print(f"Missing dependencies: {', '.join(missing_deps)}", file=sys.stderr)
+        sys.exit(1)
+    else:
+        sys.exit(0)
+
+
+if __name__ == '__main__':
+    main()

archivebox/plugins/forumdl/on_Snapshot__53_forumdl.py

@@ -0,0 +1,237 @@
+#!/usr/bin/env python3
+"""
+Download forum content from a URL using forum-dl.
+
+Usage: on_Snapshot__forumdl.py --url=<url> --snapshot-id=<uuid>
+Output: Downloads forum content to $PWD/
+
+Environment variables:
+    FORUMDL_BINARY: Path to forum-dl binary
+    FORUMDL_TIMEOUT: Timeout in seconds (default: 3600 for large forums)
+    FORUMDL_OUTPUT_FORMAT: Output format (default: jsonl)
+    FORUMDL_TEXTIFY: Convert HTML to plaintext (default: False - keeps HTML)
+    FORUMDL_CHECK_SSL_VALIDITY: Whether to check SSL certificates (default: True)
+    FORUMDL_EXTRA_ARGS: Extra arguments for forum-dl (space-separated)
+
+    # Forum-dl feature toggles
+    SAVE_FORUMDL: Enable forum-dl forum extraction (default: True)
+
+    # Fallback to ARCHIVING_CONFIG values if FORUMDL_* not set:
+    TIMEOUT: Fallback timeout
+    CHECK_SSL_VALIDITY: Fallback SSL check
+"""
+
+import json
+import os
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+import rich_click as click
+
+
+# Extractor metadata
+EXTRACTOR_NAME = 'forumdl'
+BIN_NAME = 'forum-dl'
+BIN_PROVIDERS = 'pip,env'
+OUTPUT_DIR = '.'
+
+
+def get_env(name: str, default: str = '') -> str:
+    return os.environ.get(name, default).strip()
+
+
+def get_env_bool(name: str, default: bool = False) -> bool:
+    val = get_env(name, '').lower()
+    if val in ('true', '1', 'yes', 'on'):
+        return True
+    if val in ('false', '0', 'no', 'off'):
+        return False
+    return default
+
+
+def get_env_int(name: str, default: int = 0) -> int:
+    try:
+        return int(get_env(name, str(default)))
+    except ValueError:
+        return default
+
+
+def find_forumdl() -> str | None:
+    """Find forum-dl binary."""
+    forumdl = get_env('FORUMDL_BINARY')
+    if forumdl and os.path.isfile(forumdl):
+        return forumdl
+
+    binary = shutil.which('forum-dl')
+    if binary:
+        return binary
+
+    return None
+
+
+def get_version(binary: str) -> str:
+    """Get forum-dl version."""
+    try:
+        result = subprocess.run([binary, '--version'], capture_output=True, text=True, timeout=10)
+        return result.stdout.strip()[:64]
+    except Exception:
+        return ''
+
+
+def save_forum(url: str, binary: str) -> tuple[bool, str | None, str]:
+    """
+    Download forum using forum-dl.
+
+    Returns: (success, output_path, error_message)
+    """
+    # Get config from env
+    timeout = get_env_int('FORUMDL_TIMEOUT') or get_env_int('TIMEOUT', 3600)
+    check_ssl = get_env_bool('FORUMDL_CHECK_SSL_VALIDITY', get_env_bool('CHECK_SSL_VALIDITY', True))
+    textify = get_env_bool('FORUMDL_TEXTIFY', False)
+    extra_args = get_env('FORUMDL_EXTRA_ARGS', '')
+    output_format = get_env('FORUMDL_OUTPUT_FORMAT', 'jsonl')
+
+    # Output directory is current directory (hook already runs in output dir)
+    output_dir = Path(OUTPUT_DIR)
+
+    # Build output filename based on format
+    if output_format == 'warc':
+        output_file = output_dir / 'forum.warc.gz'
+    elif output_format == 'jsonl':
+        output_file = output_dir / 'forum.jsonl'
+    elif output_format == 'maildir':
+        output_file = output_dir / 'forum'  # maildir is a directory
+    elif output_format in ('mbox', 'mh', 'mmdf', 'babyl'):
+        output_file = output_dir / f'forum.{output_format}'
+    else:
+        output_file = output_dir / f'forum.{output_format}'
+
+    # Build command
+    cmd = [binary, '-f', output_format, '-o', str(output_file)]
+
+    if textify:
+        cmd.append('--textify')
+
+    if not check_ssl:
+        cmd.append('--no-check-certificate')
+
+    if extra_args:
+        cmd.extend(extra_args.split())
+
+    cmd.append(url)
+
+    try:
+        result = subprocess.run(cmd, capture_output=True, timeout=timeout, text=True)
+
+        # Check if output file was created
+        if output_file.exists() and output_file.stat().st_size > 0:
+            return True, str(output_file), ''
+        else:
+            stderr = result.stderr
+
+            # These are NOT errors - page simply has no downloadable forum content
+            stderr_lower = stderr.lower()
+            if 'unsupported url' in stderr_lower:
+                return True, None, ''  # Not a forum site - success, no output
+            if 'no content' in stderr_lower:
+                return True, None, ''  # No forum found - success, no output
+            if result.returncode == 0:
+                return True, None, ''  # forum-dl exited cleanly, just no forum - success
+
+            # These ARE errors - something went wrong
+            if '404' in stderr:
+                return False, None, '404 Not Found'
+            if '403' in stderr:
+                return False, None, '403 Forbidden'
+            if 'unable to extract' in stderr_lower:
+                return False, None, 'Unable to extract forum info'
+
+            return False, None, f'forum-dl error: {stderr[:200]}'
+
+    except subprocess.TimeoutExpired:
+        return False, None, f'Timed out after {timeout} seconds'
+    except Exception as e:
+        return False, None, f'{type(e).__name__}: {e}'
+
+
+@click.command()
+@click.option('--url', required=True, help='URL to download forum from')
+@click.option('--snapshot-id', required=True, help='Snapshot UUID')
+def main(url: str, snapshot_id: str):
+    """Download forum content from a URL using forum-dl."""
+
+    version = ''
+    output = None
+    status = 'failed'
+    error = ''
+    binary = None
+    cmd_str = ''
+
+    try:
+        # Check if forum-dl is enabled
+        if not get_env_bool('SAVE_FORUMDL', True):
+            print('Skipping forum-dl (SAVE_FORUMDL=False)')
+            status = 'skipped'
+            print(f'STATUS={status}')
+            print(f'RESULT_JSON={json.dumps({"extractor": EXTRACTOR_NAME, "status": status, "url": url, "snapshot_id": snapshot_id})}')
+            sys.exit(0)
+
+        # Find binary
+        binary = find_forumdl()
+        if not binary:
+            print(f'ERROR: {BIN_NAME} binary not found', file=sys.stderr)
+            print(f'DEPENDENCY_NEEDED={BIN_NAME}', file=sys.stderr)
+            print(f'BIN_PROVIDERS={BIN_PROVIDERS}', file=sys.stderr)
+            print(f'INSTALL_HINT=pip install forum-dl', file=sys.stderr)
+            sys.exit(1)
+
+        version = get_version(binary)
+        cmd_str = f'{binary} {url}'
+
+        # Run extraction
+        success, output, error = save_forum(url, binary)
+        status = 'succeeded' if success else 'failed'
+
+        if success:
+            if output:
+                output_path = Path(output)
+                file_size = output_path.stat().st_size
+                print(f'forum-dl completed: {output_path.name} ({file_size} bytes)')
+            else:
+                print(f'forum-dl completed: no forum content found on page (this is normal)')
+
+    except Exception as e:
+        error = f'{type(e).__name__}: {e}'
+        status = 'failed'
+
+    # Print results
+    if cmd_str:
+        print(f'CMD={cmd_str}')
+    if version:
+        print(f'VERSION={version}')
+    if output:
+        print(f'OUTPUT={output}')
+    print(f'STATUS={status}')
+
+    if error:
+        print(f'ERROR={error}', file=sys.stderr)
+
+    # Print JSON result
+    result_json = {
+        'extractor': EXTRACTOR_NAME,
+        'url': url,
+        'snapshot_id': snapshot_id,
+        'status': status,
+        'cmd_version': version,
+        'output': output,
+        'error': error or None,
+    }
+    print(f'RESULT_JSON={json.dumps(result_json)}')
+
+    sys.exit(0 if status == 'succeeded' else 1)
+
+
+if __name__ == '__main__':
+    main()

archivebox/plugins/forumdl/templates/embed.html

@@ -0,0 +1,40 @@
+<!-- Embedded forum view - renders JSONL forum posts -->
+<div class="extractor-embed forumdl-embed" style="width: 100%; max-width: 900px; margin: 0 auto; background: #1a1a1a; padding: 20px; border-radius: 8px;">
+    <div style="text-align: center; padding: 15px 0; border-bottom: 1px solid #333; margin-bottom: 20px;">
+        <span style="font-size: 32px;">💬</span>
+        <h3 style="margin: 10px 0; color: #fff; font-size: 18px;">Forum Thread</h3>
+    </div>
+    <div id="forum-posts" style="max-height: 500px; overflow-y: auto; color: #ddd;"></div>
+    <script>
+        (async function() {
+            try {
+                const response = await fetch('{{ output_path }}');
+                const text = await response.text();
+                const posts = text.trim().split('\n').map(line => JSON.parse(line));
+                const container = document.getElementById('forum-posts');
+
+                posts.forEach(post => {
+                    const postDiv = document.createElement('div');
+                    postDiv.style.cssText = 'background: #2a2a2a; padding: 15px; margin-bottom: 15px; border-radius: 5px; border-left: 3px solid #4a9eff;';
+
+                    const author = post.author || 'Anonymous';
+                    const date = post.date ? new Date(post.date).toLocaleString() : '';
+                    const title = post.title || '';
+                    const content = post.content || post.body || '';
+
+                    postDiv.innerHTML = `
+                        <div style="display: flex; justify-content: space-between; margin-bottom: 10px; padding-bottom: 8px; border-bottom: 1px solid #444;">
+                            <strong style="color: #4a9eff;">${author}</strong>
+                            <span style="color: #888; font-size: 12px;">${date}</span>
+                        </div>
+                        ${title ? `<h4 style="margin: 0 0 10px 0; color: #fff;">${title}</h4>` : ''}
+                        <div style="color: #ccc; line-height: 1.5;">${content}</div>
+                    `;
+                    container.appendChild(postDiv);
+                });
+            } catch(e) {
+                document.getElementById('forum-posts').innerHTML = '<p style="color: #888;">Error loading forum posts</p>';
+            }
+        })();
+    </script>
+</div>

archivebox/plugins/forumdl/templates/fullscreen.html

@@ -0,0 +1,147 @@
+<!-- Fullscreen forum view - renders JSONL forum posts -->
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Forum Thread</title>
+    <style>
+        body {
+            margin: 0;
+            padding: 20px;
+            background: #0d1117;
+            color: #c9d1d9;
+            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif;
+            line-height: 1.6;
+        }
+        .header {
+            max-width: 1000px;
+            margin: 0 auto 30px;
+            text-align: center;
+            padding: 20px;
+            border-bottom: 1px solid #30363d;
+        }
+        .icon {
+            font-size: 48px;
+            margin-bottom: 10px;
+        }
+        h1 {
+            margin: 0;
+            font-size: 28px;
+            color: #f0f6fc;
+        }
+        .container {
+            max-width: 1000px;
+            margin: 0 auto;
+        }
+        .post {
+            background: #161b22;
+            border: 1px solid #30363d;
+            border-radius: 6px;
+            margin-bottom: 16px;
+            padding: 16px;
+            transition: border-color 0.2s;
+        }
+        .post:hover {
+            border-color: #58a6ff;
+        }
+        .post-header {
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            margin-bottom: 12px;
+            padding-bottom: 12px;
+            border-bottom: 1px solid #21262d;
+        }
+        .post-author {
+            font-weight: 600;
+            color: #58a6ff;
+            font-size: 14px;
+        }
+        .post-date {
+            color: #8b949e;
+            font-size: 12px;
+        }
+        .post-title {
+            margin: 0 0 12px 0;
+            font-size: 18px;
+            font-weight: 600;
+            color: #f0f6fc;
+        }
+        .post-content {
+            color: #c9d1d9;
+            word-wrap: break-word;
+        }
+        .post-content img {
+            max-width: 100%;
+            height: auto;
+            border-radius: 4px;
+        }
+        .post-content a {
+            color: #58a6ff;
+            text-decoration: none;
+        }
+        .post-content a:hover {
+            text-decoration: underline;
+        }
+        .loading {
+            text-align: center;
+            padding: 40px;
+            color: #8b949e;
+        }
+    </style>
+</head>
+<body>
+    <div class="header">
+        <div class="icon">💬</div>
+        <h1>Forum Thread</h1>
+    </div>
+    <div class="container">
+        <div id="forum-posts" class="loading">Loading posts...</div>
+    </div>
+    <script>
+        (async function() {
+            try {
+                const response = await fetch('{{ output_path }}');
+                const text = await response.text();
+                const posts = text.trim().split('\n').filter(line => line).map(line => JSON.parse(line));
+                const container = document.getElementById('forum-posts');
+                container.innerHTML = '';
+                container.className = '';
+
+                posts.forEach(post => {
+                    const postDiv = document.createElement('div');
+                    postDiv.className = 'post';
+
+                    const author = post.author || 'Anonymous';
+                    const date = post.date ? new Date(post.date).toLocaleString() : '';
+                    const title = post.title || '';
+                    const content = post.content || post.body || '';
+
+                    postDiv.innerHTML = `
+                        <div class="post-header">
+                            <span class="post-author">${escapeHtml(author)}</span>
+                            <span class="post-date">${escapeHtml(date)}</span>
+                        </div>
+                        ${title ? `<h2 class="post-title">${escapeHtml(title)}</h2>` : ''}
+                        <div class="post-content">${content}</div>
+                    `;
+                    container.appendChild(postDiv);
+                });
+
+                if (posts.length === 0) {
+                    container.innerHTML = '<div class="loading">No posts found</div>';
+                }
+            } catch(e) {
+                document.getElementById('forum-posts').innerHTML = '<div class="loading">Error loading posts: ' + e.message + '</div>';
+            }
+        })();
+
+        function escapeHtml(text) {
+            const div = document.createElement('div');
+            div.textContent = text;
+            return div.innerHTML;
+        }
+    </script>
+</body>
+</html>

archivebox/plugins/forumdl/templates/icon.html

@@ -0,0 +1 @@
+💬

archivebox/plugins/forumdl/templates/thumbnail.html

@@ -0,0 +1,7 @@
+<!-- Forum thumbnail - shows icon placeholder -->
+<div class="extractor-thumbnail forumdl-thumbnail" style="width: 100%; height: 100px; overflow: hidden; background: #1a1a1a; display: flex; align-items: center; justify-content: center;">
+    <div style="display: flex; flex-direction: column; align-items: center; color: #888; font-size: 12px;">
+        <span style="font-size: 32px;">💬</span>
+        <span>Forum</span>
+    </div>
+</div>

archivebox/plugins/forumdl/tests/test_forumdl.py

@@ -0,0 +1,157 @@
+"""
+Integration tests for forumdl plugin
+
+Tests verify:
+1. Hook script exists
+2. Dependencies installed via validation hooks
+3. Verify deps with abx-pkg
+4. Forum extraction works on forum URLs
+5. JSONL output is correct
+6. Config options work
+7. Handles non-forum URLs gracefully
+"""
+
+import json
+import subprocess
+import sys
+import tempfile
+from pathlib import Path
+import pytest
+
+PLUGIN_DIR = Path(__file__).parent.parent
+PLUGINS_ROOT = PLUGIN_DIR.parent
+FORUMDL_HOOK = PLUGIN_DIR / 'on_Snapshot__53_forumdl.py'
+FORUMDL_VALIDATE_HOOK = PLUGIN_DIR / 'on_Crawl__00_validate_forumdl.py'
+TEST_URL = 'https://example.com'
+
+def test_hook_script_exists():
+    """Verify on_Snapshot hook exists."""
+    assert FORUMDL_HOOK.exists(), f"Hook not found: {FORUMDL_HOOK}"
+
+
+def test_forumdl_validate_hook():
+    """Test forum-dl validate hook checks for forum-dl."""
+    # Run forum-dl validate hook
+    result = subprocess.run(
+        [sys.executable, str(FORUMDL_VALIDATE_HOOK)],
+        capture_output=True,
+        text=True,
+        timeout=30
+    )
+
+    # Hook exits 0 if all binaries found, 1 if any not found
+    # Parse output for InstalledBinary and Dependency records
+    found_binary = False
+    found_dependency = False
+
+    for line in result.stdout.strip().split('\n'):
+        if line.strip():
+            try:
+                record = json.loads(line)
+                if record.get('type') == 'InstalledBinary':
+                    if record['name'] == 'forum-dl':
+                        assert record['abspath'], "forum-dl should have abspath"
+                        found_binary = True
+                elif record.get('type') == 'Dependency':
+                    if record['bin_name'] == 'forum-dl':
+                        found_dependency = True
+            except json.JSONDecodeError:
+                pass
+
+    # forum-dl should either be found (InstalledBinary) or missing (Dependency)
+    assert found_binary or found_dependency, \
+        "forum-dl should have either InstalledBinary or Dependency record"
+
+
+def test_verify_deps_with_abx_pkg():
+    """Verify forum-dl is available via abx-pkg."""
+    from abx_pkg import Binary, PipProvider, EnvProvider, BinProviderOverrides
+
+    missing_binaries = []
+
+    # Verify forum-dl is available
+    forumdl_binary = Binary(name='forum-dl', binproviders=[PipProvider(), EnvProvider()])
+    forumdl_loaded = forumdl_binary.load()
+    if not (forumdl_loaded and forumdl_loaded.abspath):
+        missing_binaries.append('forum-dl')
+
+    if missing_binaries:
+        pytest.skip(f"Binaries not available: {', '.join(missing_binaries)} - Dependency records should have been emitted")
+
+
+def test_handles_non_forum_url():
+    """Test that forum-dl extractor handles non-forum URLs gracefully via hook."""
+    # Prerequisites checked by earlier test
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        tmpdir = Path(tmpdir)
+
+        # Run forum-dl extraction hook on non-forum URL
+        result = subprocess.run(
+            [sys.executable, str(FORUMDL_HOOK), '--url', 'https://example.com', '--snapshot-id', 'test789'],
+            cwd=tmpdir,
+            capture_output=True,
+            text=True,
+            timeout=60
+        )
+
+        # Should exit 0 even for non-forum URL
+        assert result.returncode == 0, f"Should handle non-forum URL gracefully: {result.stderr}"
+
+        # Verify JSONL output
+        assert 'STATUS=' in result.stdout, "Should report status"
+        assert 'RESULT_JSON=' in result.stdout, "Should output RESULT_JSON"
+
+        # Parse JSONL result
+        result_json = None
+        for line in result.stdout.split('\n'):
+            if line.startswith('RESULT_JSON='):
+                result_json = json.loads(line.split('=', 1)[1])
+                break
+
+        assert result_json, "Should have RESULT_JSON"
+        assert result_json['extractor'] == 'forumdl'
+
+
+def test_config_save_forumdl_false_skips():
+    """Test that SAVE_FORUMDL=False causes skip."""
+    import os
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        env = os.environ.copy()
+        env['SAVE_FORUMDL'] = 'False'
+
+        result = subprocess.run(
+            [sys.executable, str(FORUMDL_HOOK), '--url', TEST_URL, '--snapshot-id', 'test999'],
+            cwd=tmpdir,
+            capture_output=True,
+            text=True,
+            env=env,
+            timeout=30
+        )
+
+        assert result.returncode == 0, f"Should exit 0 when skipping: {result.stderr}"
+        assert 'STATUS=' in result.stdout
+
+
+def test_config_timeout():
+    """Test that FORUMDL_TIMEOUT config is respected."""
+    import os
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        env = os.environ.copy()
+        env['FORUMDL_TIMEOUT'] = '5'
+
+        result = subprocess.run(
+            [sys.executable, str(FORUMDL_HOOK), '--url', 'https://example.com', '--snapshot-id', 'testtimeout'],
+            cwd=tmpdir,
+            capture_output=True,
+            text=True,
+            env=env,
+            timeout=30
+        )
+
+        assert result.returncode == 0, "Should complete without hanging"
+
+if __name__ == '__main__':
+    pytest.main([__file__, '-v'])