rename media plugin to ytdlp with backwards-compatible aliases

- Rename archivebox/plugins/media/ → archivebox/plugins/ytdlp/
- Rename hook script on_Snapshot__63_media.bg.py → on_Snapshot__63_ytdlp.bg.py
- Update config.json: YTDLP_* as primary keys, MEDIA_* as x-aliases
- Update templates CSS classes: media-* → ytdlp-*
- Fix gallerydl bug: remove incorrect dependency on media plugin output
- Update all codebase references to use YTDLP_* and SAVE_YTDLP
- Add backwards compatibility test for MEDIA_ENABLED alias
This commit is contained in:
Claude
2025-12-29 19:09:05 +00:00
parent 30c60eef76
commit a5654e877f
19 changed files with 110 additions and 102 deletions

View File

@@ -0,0 +1,3 @@
{"type": "Binary", "name": "yt-dlp", "binproviders": "pip,brew,apt,env"}
{"type": "Binary", "name": "node", "binproviders": "apt,brew,env", "overrides": {"apt": {"packages": ["nodejs"]}}}
{"type": "Binary", "name": "ffmpeg", "binproviders": "apt,brew,env"}

View File

@@ -0,0 +1,60 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"additionalProperties": false,
"properties": {
"YTDLP_ENABLED": {
"type": "boolean",
"default": true,
"x-aliases": ["MEDIA_ENABLED", "SAVE_MEDIA", "USE_MEDIA", "USE_YTDLP", "FETCH_MEDIA", "SAVE_YTDLP"],
"description": "Enable video/audio downloading with yt-dlp"
},
"YTDLP_BINARY": {
"type": "string",
"default": "yt-dlp",
"x-aliases": ["MEDIA_BINARY", "YOUTUBEDL_BINARY", "YOUTUBE_DL_BINARY"],
"description": "Path to yt-dlp binary"
},
"YTDLP_TIMEOUT": {
"type": "integer",
"default": 3600,
"minimum": 30,
"x-fallback": "TIMEOUT",
"x-aliases": ["MEDIA_TIMEOUT"],
"description": "Timeout for yt-dlp downloads in seconds"
},
"YTDLP_MAX_SIZE": {
"type": "string",
"default": "750m",
"pattern": "^\\d+[kmgKMG]?$",
"x-aliases": ["MEDIA_MAX_SIZE"],
"description": "Maximum file size for yt-dlp downloads"
},
"YTDLP_CHECK_SSL_VALIDITY": {
"type": "boolean",
"default": true,
"x-fallback": "CHECK_SSL_VALIDITY",
"x-aliases": ["MEDIA_CHECK_SSL_VALIDITY"],
"description": "Whether to verify SSL certificates"
},
"YTDLP_ARGS": {
"type": "array",
"items": {"type": "string"},
"default": [
"--write-info-json",
"--write-thumbnail",
"--write-sub",
"--embed-subs",
"--write-auto-sub"
],
"x-aliases": ["MEDIA_ARGS"],
"description": "Default yt-dlp arguments"
},
"YTDLP_EXTRA_ARGS": {
"type": "string",
"default": "",
"x-aliases": ["MEDIA_EXTRA_ARGS"],
"description": "Extra arguments for yt-dlp (space-separated)"
}
}
}

View File

@@ -0,0 +1,222 @@
#!/usr/bin/env python3
"""
Download video/audio from a URL using yt-dlp.
Usage: on_Snapshot__ytdlp.py --url=<url> --snapshot-id=<uuid>
Output: Downloads video/audio files to $PWD/ytdlp/
Environment variables:
YTDLP_BINARY: Path to yt-dlp binary
YTDLP_TIMEOUT: Timeout in seconds (default: 3600 for large downloads)
YTDLP_CHECK_SSL_VALIDITY: Whether to check SSL certificates (default: True)
YTDLP_EXTRA_ARGS: Extra arguments for yt-dlp (space-separated)
YTDLP_MAX_SIZE: Maximum file size (default: 750m)
# Feature toggles (with backwards-compatible aliases)
YTDLP_ENABLED: Enable yt-dlp extraction (default: True)
SAVE_YTDLP: Alias for YTDLP_ENABLED
MEDIA_ENABLED: Backwards-compatible alias for YTDLP_ENABLED
# Fallback to ARCHIVING_CONFIG values if YTDLP_* not set:
TIMEOUT: Fallback timeout
CHECK_SSL_VALIDITY: Fallback SSL check
"""
import json
import os
import subprocess
import sys
from pathlib import Path
import rich_click as click
# Extractor metadata
PLUGIN_NAME = 'ytdlp'
BIN_NAME = 'yt-dlp'
BIN_PROVIDERS = 'pip,apt,brew,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
STATICFILE_DIR = '../staticfile'
def has_staticfile_output() -> bool:
"""Check if staticfile extractor already downloaded this URL."""
staticfile_dir = Path(STATICFILE_DIR)
return staticfile_dir.exists() and any(staticfile_dir.iterdir())
# Default yt-dlp args (from old YTDLP_CONFIG)
def get_ytdlp_default_args(max_size: str = '750m') -> list[str]:
"""Build default yt-dlp arguments."""
return [
'--restrict-filenames',
'--trim-filenames', '128',
'--write-description',
'--write-info-json',
'--write-thumbnail',
'--write-sub',
'--write-auto-subs',
'--convert-subs=srt',
'--yes-playlist',
'--continue',
'--no-abort-on-error',
'--ignore-errors',
'--geo-bypass',
'--add-metadata',
f'--format=(bv*+ba/b)[filesize<={max_size}][filesize_approx<=?{max_size}]/(bv*+ba/b)',
]
def save_ytdlp(url: str, binary: str) -> tuple[bool, str | None, str]:
"""
Download video/audio using yt-dlp.
Returns: (success, output_path, error_message)
"""
# Get config from env (YTDLP_* primary, MEDIA_* as fallback via aliases)
timeout = get_env_int('TIMEOUT', 3600)
check_ssl = get_env_bool('CHECK_SSL_VALIDITY', True)
extra_args = get_env('YTDLP_EXTRA_ARGS', '')
max_size = get_env('YTDLP_MAX_SIZE', '') or get_env('MEDIA_MAX_SIZE', '750m')
# Output directory is current directory (hook already runs in output dir)
output_dir = Path(OUTPUT_DIR)
# Build command (later options take precedence)
cmd = [
binary,
*get_ytdlp_default_args(max_size),
'--no-progress',
'-o', '%(title)s.%(ext)s',
]
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 any media files were downloaded
media_extensions = (
'.mp4', '.webm', '.mkv', '.avi', '.mov', '.flv', '.wmv', '.m4v',
'.mp3', '.m4a', '.ogg', '.wav', '.flac', '.aac', '.opus',
'.json', '.jpg', '.png', '.webp', '.jpeg',
'.vtt', '.srt', '.ass', '.lrc',
'.description',
)
downloaded_files = [
f for f in output_dir.glob('*')
if f.is_file() and f.suffix.lower() in media_extensions
]
if downloaded_files:
# Return first video/audio file, or first file if no media
video_audio = [
f for f in downloaded_files
if f.suffix.lower() in ('.mp4', '.webm', '.mkv', '.avi', '.mov', '.mp3', '.m4a', '.ogg', '.wav', '.flac')
]
output = str(video_audio[0]) if video_audio else str(downloaded_files[0])
return True, output, ''
else:
stderr = result.stderr
# These are NOT errors - page simply has no downloadable media
# Return success with no output (legitimate "nothing to download")
if 'ERROR: Unsupported URL' in stderr:
return True, None, '' # Not a media site - success, no output
if 'URL could be a direct video link' in stderr:
return True, None, '' # Not a supported media URL - success, no output
if result.returncode == 0:
return True, None, '' # yt-dlp exited cleanly, just no media - success
# These ARE errors - something went wrong
if 'HTTP Error 404' in stderr:
return False, None, '404 Not Found'
if 'HTTP Error 403' in stderr:
return False, None, '403 Forbidden'
if 'Unable to extract' in stderr:
return False, None, 'Unable to extract media info'
return False, None, f'yt-dlp 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 video/audio from')
@click.option('--snapshot-id', required=True, help='Snapshot UUID')
def main(url: str, snapshot_id: str):
"""Download video/audio from a URL using yt-dlp."""
try:
# Check if yt-dlp downloading is enabled (YTDLP_ENABLED primary, MEDIA_ENABLED fallback)
ytdlp_enabled = get_env_bool('YTDLP_ENABLED', True) and get_env_bool('MEDIA_ENABLED', True)
if not ytdlp_enabled:
print('Skipping ytdlp (YTDLP_ENABLED=False)', file=sys.stderr)
# Temporary failure (config disabled) - NO JSONL emission
sys.exit(0)
# Check if staticfile extractor already handled this (permanent skip)
if has_staticfile_output():
print('Skipping ytdlp - staticfile extractor already downloaded this', file=sys.stderr)
print(json.dumps({'type': 'ArchiveResult', 'status': 'skipped', 'output_str': 'staticfile already exists'}))
sys.exit(0)
# Get binary from environment
binary = get_env('YTDLP_BINARY', 'yt-dlp')
# Run extraction
success, output, error = save_ytdlp(url, binary)
if success:
# Success - emit ArchiveResult
result = {
'type': 'ArchiveResult',
'status': 'succeeded',
'output_str': output or ''
}
print(json.dumps(result))
sys.exit(0)
else:
# Transient error - emit NO JSONL
print(f'ERROR: {error}', file=sys.stderr)
sys.exit(1)
except Exception as e:
# Transient error - emit NO JSONL
print(f'ERROR: {type(e).__name__}: {e}', file=sys.stderr)
sys.exit(1)
if __name__ == '__main__':
main()

View File

@@ -0,0 +1,9 @@
<!-- YT-DLP embed - video/audio player -->
<div class="extractor-embed ytdlp-embed" style="width: 100%; height: 100%; min-height: 400px; background: #1a1a1a; display: flex; align-items: center; justify-content: center;">
<video src="{{ output_path }}"
style="max-width: 100%; max-height: 100%;"
controls
preload="metadata">
Your browser does not support the video tag.
</video>
</div>

View File

@@ -0,0 +1,10 @@
<!-- YT-DLP fullscreen - full video/audio player -->
<div class="extractor-fullscreen ytdlp-fullscreen" style="width: 100%; height: 100vh; background: #000; display: flex; align-items: center; justify-content: center;">
<video src="{{ output_path }}"
style="max-width: 100%; max-height: 100%;"
controls
autoplay
preload="auto">
Your browser does not support the video tag.
</video>
</div>

View File

@@ -0,0 +1 @@
🎬

View File

@@ -0,0 +1,14 @@
<!-- YT-DLP thumbnail - shows video/audio player or placeholder -->
<div class="extractor-thumbnail ytdlp-thumbnail" style="width: 100%; height: 100px; overflow: hidden; background: #1a1a1a; display: flex; align-items: center; justify-content: center;">
<video src="{{ output_path }}"
style="width: 100%; height: 100px; object-fit: contain;"
poster=""
preload="metadata"
muted
onerror="this.style.display='none'; this.nextElementSibling.style.display='flex';">
</video>
<div style="display: none; flex-direction: column; align-items: center; color: #888; font-size: 12px;">
<span style="font-size: 32px;">🎬</span>
<span>YT-DLP</span>
</div>
</div>

View File

@@ -0,0 +1,227 @@
"""
Integration tests for ytdlp plugin
Tests verify:
1. Hook script exists
2. Dependencies installed via validation hooks
3. Verify deps with abx-pkg
4. YT-DLP extraction works on video URLs
5. JSONL output is correct
6. Config options work (YTDLP_* and backwards-compatible MEDIA_* aliases)
7. Handles non-video URLs gracefully
"""
import json
import subprocess
import sys
import tempfile
import time
from pathlib import Path
import pytest
PLUGIN_DIR = Path(__file__).parent.parent
PLUGINS_ROOT = PLUGIN_DIR.parent
YTDLP_HOOK = next(PLUGIN_DIR.glob('on_Snapshot__*_ytdlp.*'), None)
TEST_URL = 'https://example.com/video.mp4'
def test_hook_script_exists():
"""Verify on_Snapshot hook exists."""
assert YTDLP_HOOK.exists(), f"Hook not found: {YTDLP_HOOK}"
def test_verify_deps_with_abx_pkg():
"""Verify yt-dlp, node, and ffmpeg are available via abx-pkg."""
from abx_pkg import Binary, PipProvider, AptProvider, BrewProvider, EnvProvider, BinProviderOverrides
missing_binaries = []
# Verify yt-dlp is available
ytdlp_binary = Binary(name='yt-dlp', binproviders=[PipProvider(), EnvProvider()])
ytdlp_loaded = ytdlp_binary.load()
if not (ytdlp_loaded and ytdlp_loaded.abspath):
missing_binaries.append('yt-dlp')
# Verify node is available (yt-dlp needs it for JS extraction)
node_binary = Binary(
name='node',
binproviders=[AptProvider(), BrewProvider(), EnvProvider()]
)
node_loaded = node_binary.load()
if not (node_loaded and node_loaded.abspath):
missing_binaries.append('node')
# Verify ffmpeg is available (yt-dlp needs it for video conversion)
ffmpeg_binary = Binary(name='ffmpeg', binproviders=[AptProvider(), BrewProvider(), EnvProvider()])
ffmpeg_loaded = ffmpeg_binary.load()
if not (ffmpeg_loaded and ffmpeg_loaded.abspath):
missing_binaries.append('ffmpeg')
if missing_binaries:
pass
def test_handles_non_video_url():
"""Test that ytdlp extractor handles non-video URLs gracefully via hook."""
# Prerequisites checked by earlier test
with tempfile.TemporaryDirectory() as tmpdir:
tmpdir = Path(tmpdir)
# Run ytdlp extraction hook on non-video URL
result = subprocess.run(
[sys.executable, str(YTDLP_HOOK), '--url', 'https://example.com', '--snapshot-id', 'test789'],
cwd=tmpdir,
capture_output=True,
text=True,
timeout=60
)
# Should exit 0 even for non-media URL
assert result.returncode == 0, f"Should handle non-media URL gracefully: {result.stderr}"
# Parse clean JSONL output
result_json = None
for line in result.stdout.strip().split('\n'):
line = line.strip()
if line.startswith('{'):
pass
try:
record = json.loads(line)
if record.get('type') == 'ArchiveResult':
result_json = record
break
except json.JSONDecodeError:
pass
assert result_json, "Should have ArchiveResult JSONL output"
assert result_json['status'] == 'succeeded', f"Should succeed: {result_json}"
def test_config_ytdlp_enabled_false_skips():
"""Test that YTDLP_ENABLED=False exits without emitting JSONL."""
import os
with tempfile.TemporaryDirectory() as tmpdir:
env = os.environ.copy()
env['YTDLP_ENABLED'] = 'False'
result = subprocess.run(
[sys.executable, str(YTDLP_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 feature disabled: {result.stderr}"
# Feature disabled - temporary failure, should NOT emit JSONL
assert 'Skipping' in result.stderr or 'False' in result.stderr, "Should log skip reason to stderr"
# Should NOT emit any JSONL
jsonl_lines = [line for line in result.stdout.strip().split('\n') if line.strip().startswith('{')]
assert len(jsonl_lines) == 0, f"Should not emit JSONL when feature disabled, but got: {jsonl_lines}"
def test_config_media_enabled_backwards_compat():
"""Test that MEDIA_ENABLED=False (backwards-compatible alias) also works."""
import os
with tempfile.TemporaryDirectory() as tmpdir:
env = os.environ.copy()
env['MEDIA_ENABLED'] = 'False'
result = subprocess.run(
[sys.executable, str(YTDLP_HOOK), '--url', TEST_URL, '--snapshot-id', 'test_compat'],
cwd=tmpdir,
capture_output=True,
text=True,
env=env,
timeout=30
)
assert result.returncode == 0, f"Should exit 0 when feature disabled via MEDIA_ENABLED: {result.stderr}"
# Should NOT emit any JSONL when disabled via backwards-compatible alias
jsonl_lines = [line for line in result.stdout.strip().split('\n') if line.strip().startswith('{')]
assert len(jsonl_lines) == 0, f"Should not emit JSONL when feature disabled via MEDIA_ENABLED, but got: {jsonl_lines}"
def test_config_timeout():
"""Test that YTDLP_TIMEOUT config is respected (also via MEDIA_TIMEOUT alias)."""
import os
with tempfile.TemporaryDirectory() as tmpdir:
env = os.environ.copy()
env['YTDLP_TIMEOUT'] = '5'
start_time = time.time()
result = subprocess.run(
[sys.executable, str(YTDLP_HOOK), '--url', 'https://example.com', '--snapshot-id', 'testtimeout'],
cwd=tmpdir,
capture_output=True,
text=True,
env=env,
timeout=10 # Should complete in 5s, use 10s as safety margin
)
elapsed_time = time.time() - start_time
assert result.returncode == 0, f"Should complete without hanging: {result.stderr}"
# Allow 1 second overhead for subprocess startup and Python interpreter
assert elapsed_time <= 6.0, f"Should complete within 6 seconds (5s timeout + 1s overhead), took {elapsed_time:.2f}s"
def test_real_youtube_url():
"""Test that yt-dlp can extract video/audio from a real YouTube URL."""
import os
with tempfile.TemporaryDirectory() as tmpdir:
tmpdir = Path(tmpdir)
# Use a short, stable YouTube video (YouTube's own about video)
youtube_url = 'https://www.youtube.com/watch?v=jNQXAC9IVRw' # "Me at the zoo" - first YouTube video
env = os.environ.copy()
env['YTDLP_TIMEOUT'] = '120' # Give it time to download
start_time = time.time()
result = subprocess.run(
[sys.executable, str(YTDLP_HOOK), '--url', youtube_url, '--snapshot-id', 'testyoutube'],
cwd=tmpdir,
capture_output=True,
text=True,
env=env,
timeout=180
)
elapsed_time = time.time() - start_time
# Should succeed
assert result.returncode == 0, f"Should extract video/audio successfully: {result.stderr}"
# Parse JSONL output
result_json = None
for line in result.stdout.strip().split('\n'):
line = line.strip()
if line.startswith('{'):
try:
record = json.loads(line)
if record.get('type') == 'ArchiveResult':
result_json = record
break
except json.JSONDecodeError:
pass
assert result_json, f"Should have ArchiveResult JSONL output. stdout: {result.stdout}"
assert result_json['status'] == 'succeeded', f"Should succeed: {result_json}"
# Check that some video/audio files were downloaded
output_files = list(tmpdir.glob('**/*'))
media_files = [f for f in output_files if f.is_file() and f.suffix.lower() in ('.mp4', '.webm', '.mkv', '.m4a', '.mp3', '.json', '.jpg', '.webp')]
assert len(media_files) > 0, f"Should have downloaded at least one video/audio file. Files: {output_files}"
print(f"Successfully extracted {len(media_files)} file(s) in {elapsed_time:.2f}s")
if __name__ == '__main__':
pytest.main([__file__, '-v'])