alex/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2026-04-05 15:27:53 +10:00
Code Issues Packages Projects Releases Wiki Activity

Update Python/JS hooks to clean JSONL format + add audit report

Browse Source 
Phase 4 Plugin Audit Progress:
- Audited all 6 Dependency hooks (all already compliant)
- Audited all 11 Crawl Validate hooks (all already compliant)
- Updated 8 Python Snapshot hooks to clean JSONL format
- Updated 1 JS Snapshot hook (title.js) to clean JSONL format

Snapshot hooks updated to remove:
- RESULT_JSON= prefix
- Extra output lines (START_TS=, END_TS=, DURATION=, VERSION=, OUTPUT=, STATUS=)

Now output clean JSONL:
{"type": "ArchiveResult", "status": "...", "output_str": "..."}

Added implementation report to TODO_hook_architecture.md documenting:
- All completed phases (1, 3, 6, 7)
- Plugin audit results with status tables
- Remaining 13 JS hooks that need updating
- Files modified list
This commit is contained in:
Claude
2025-12-27 09:31:03 +00:00
parent 3d985fa8c8
commit c52eef1459
9 changed files with 264 additions and 232 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
archivebox/plugins/archive_org/on_Snapshot__13_archive_org.py
View File

@@ -121,33 +121,19 @@ def main(url: str, snapshot_id: str):
error = f'{type(e).__name__}: {e}'
status = 'failed'
# Print results
# Calculate duration
end_ts = datetime.now(timezone.utc)
duration = (end_ts - start_ts).total_seconds()
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'DURATION={duration:.2f}')
if output:
print(f'OUTPUT={output}')
print(f'STATUS={status}')
if error:
print(f'ERROR={error}', file=sys.stderr)
print(f'ERROR: {error}', file=sys.stderr)
# Print JSON result
result_json = {
'extractor': EXTRACTOR_NAME,
'url': url,
'snapshot_id': snapshot_id,
# Output clean JSONL (no RESULT_JSON= prefix)
result = {
'type': 'ArchiveResult',
'status': status,
'start_ts': start_ts.isoformat(),
'end_ts': end_ts.isoformat(),
'duration': round(duration, 2),
'output': output,
'error': error or None,
'output_str': output or error or '',
}
print(f'RESULT_JSON={json.dumps(result_json)}')
print(json.dumps(result))
sys.exit(0 if status == 'succeeded' else 1)

28
archivebox/plugins/favicon/on_Snapshot__11_favicon.py
View File

@@ -134,33 +134,19 @@ def main(url: str, snapshot_id: str):
error = f'{type(e).__name__}: {e}'
status = 'failed'
# Print results
# Calculate duration
end_ts = datetime.now(timezone.utc)
duration = (end_ts - start_ts).total_seconds()
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'DURATION={duration:.2f}')
if output:
print(f'OUTPUT={output}')
print(f'STATUS={status}')
if error:
print(f'ERROR={error}', file=sys.stderr)
print(f'ERROR: {error}', file=sys.stderr)
# Print JSON result
result_json = {
'extractor': EXTRACTOR_NAME,
'url': url,
'snapshot_id': snapshot_id,
# Output clean JSONL (no RESULT_JSON= prefix)
result = {
'type': 'ArchiveResult',
'status': status,
'start_ts': start_ts.isoformat(),
'end_ts': end_ts.isoformat(),
'duration': round(duration, 2),
'output': output,
'error': error or None,
'output_str': output or error or '',
}
print(f'RESULT_JSON={json.dumps(result_json)}')
print(json.dumps(result))
sys.exit(0 if status == 'succeeded' else 1)

37
archivebox/plugins/git/on_Snapshot__12_git.py
View File

@@ -153,38 +153,23 @@ def main(url: str, snapshot_id: str):
error = f'{type(e).__name__}: {e}'
status = 'failed'
# Print results
# Calculate duration
end_ts = datetime.now(timezone.utc)
duration = (end_ts - start_ts).total_seconds()
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'DURATION={duration:.2f}')
if binary:
print(f'CMD={binary} clone {url}')
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(f'ERROR: {error}', file=sys.stderr)
# Print JSON result
result_json = {
'extractor': EXTRACTOR_NAME,
'url': url,
'snapshot_id': snapshot_id,
# Output clean JSONL (no RESULT_JSON= prefix)
result = {
'type': 'ArchiveResult',
'status': status,
'start_ts': start_ts.isoformat(),
'end_ts': end_ts.isoformat(),
'duration': round(duration, 2),
'cmd_version': version,
'output': output,
'error': error or None,
'output_str': output or error or '',
}
print(f'RESULT_JSON={json.dumps(result_json)}')
if binary:
result['cmd'] = [binary, 'clone', '--depth=1', '--recursive', url, OUTPUT_DIR]
if version:
result['cmd_version'] = version
print(json.dumps(result))
sys.exit(0 if status == 'succeeded' else 1)

53
archivebox/plugins/media/on_Snapshot__51_media.py
View File

@@ -218,22 +218,14 @@ def main(url: str, snapshot_id: str):
try:
# Check if yt-dlp is enabled
if not (get_env_bool('USE_YTDLP', True) and get_env_bool('SAVE_MEDIA', True)):
print('Skipping media (USE_YTDLP=False or SAVE_MEDIA=False)')
status = 'skipped'
end_ts = datetime.now(timezone.utc)
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'STATUS={status}')
print(f'RESULT_JSON={json.dumps({"extractor": EXTRACTOR_NAME, "status": status, "url": url, "snapshot_id": snapshot_id})}')
print('Skipping media (USE_YTDLP=False or SAVE_MEDIA=False)', file=sys.stderr)
print(json.dumps({'type': 'ArchiveResult', 'status': 'skipped', 'output_str': 'USE_YTDLP=False'}))
sys.exit(0)
# Check if staticfile extractor already handled this (permanent skip)
if has_staticfile_output():
print(f'Skipping media - staticfile extractor already downloaded this')
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={datetime.now(timezone.utc).isoformat()}')
print(f'STATUS={status}')
print(f'RESULT_JSON={json.dumps({"extractor": EXTRACTOR_NAME, "status": status, "url": url, "snapshot_id": snapshot_id})}')
print('Skipping media - staticfile extractor already downloaded this', file=sys.stderr)
print(json.dumps({'type': 'ArchiveResult', 'status': 'skipped', 'output_str': 'staticfile already exists'}))
sys.exit(0)
# Find binary
@@ -265,38 +257,23 @@ def main(url: str, snapshot_id: str):
error = f'{type(e).__name__}: {e}'
status = 'failed'
# Print results
# Calculate duration
end_ts = datetime.now(timezone.utc)
duration = (end_ts - start_ts).total_seconds()
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'DURATION={duration:.2f}')
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(f'ERROR: {error}', file=sys.stderr)
# Print JSON result
result_json = {
'extractor': EXTRACTOR_NAME,
'url': url,
'snapshot_id': snapshot_id,
# Output clean JSONL (no RESULT_JSON= prefix)
result = {
'type': 'ArchiveResult',
'status': status,
'start_ts': start_ts.isoformat(),
'end_ts': end_ts.isoformat(),
'duration': round(duration, 2),
'cmd_version': version,
'output': output,
'error': error or None,
'output_str': output or error or '',
}
print(f'RESULT_JSON={json.dumps(result_json)}')
if binary:
result['cmd'] = [binary, url]
if version:
result['cmd_version'] = version
print(json.dumps(result))
sys.exit(0 if status == 'succeeded' else 1)

37
archivebox/plugins/readability/on_Snapshot__52_readability.py
View File

@@ -178,38 +178,23 @@ def main(url: str, snapshot_id: str):
error = f'{type(e).__name__}: {e}'
status = 'failed'
# Print results
# Calculate duration
end_ts = datetime.now(timezone.utc)
duration = (end_ts - start_ts).total_seconds()
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'DURATION={duration:.2f}')
if binary:
print(f'CMD={binary} <html>')
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(f'ERROR: {error}', file=sys.stderr)
# Print JSON result
result_json = {
'extractor': EXTRACTOR_NAME,
'url': url,
'snapshot_id': snapshot_id,
# Output clean JSONL (no RESULT_JSON= prefix)
result = {
'type': 'ArchiveResult',
'status': status,
'start_ts': start_ts.isoformat(),
'end_ts': end_ts.isoformat(),
'duration': round(duration, 2),
'cmd_version': version,
'output': output,
'error': error or None,
'output_str': output or error or '',
}
print(f'RESULT_JSON={json.dumps(result_json)}')
if binary:
result['cmd'] = [binary, '<html>']
if version:
result['cmd_version'] = version
print(json.dumps(result))
sys.exit(0 if status == 'succeeded' else 1)

55
archivebox/plugins/singlefile/on_Snapshot__37_singlefile.py
View File

@@ -245,23 +245,15 @@ def main(url: str, snapshot_id: str):
try:
# Check if SingleFile is enabled
if not get_env_bool('SAVE_SINGLEFILE', True):
print('Skipping SingleFile (SAVE_SINGLEFILE=False)')
status = 'skipped'
end_ts = datetime.now(timezone.utc)
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'STATUS={status}')
print(f'RESULT_JSON={json.dumps({"extractor": EXTRACTOR_NAME, "status": status, "url": url, "snapshot_id": snapshot_id})}')
print('Skipping SingleFile (SAVE_SINGLEFILE=False)', file=sys.stderr)
print(json.dumps({'type': 'ArchiveResult', 'status': 'skipped', 'output_str': 'SAVE_SINGLEFILE=False'}))
sys.exit(0)
# Check if staticfile extractor already handled this (permanent skip)
if has_staticfile_output():
print(f'Skipping SingleFile - staticfile extractor already downloaded this')
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={datetime.now(timezone.utc).isoformat()}')
print(f'STATUS=skipped')
print(f'RESULT_JSON={json.dumps({"extractor": EXTRACTOR_NAME, "status": "skipped", "url": url, "snapshot_id": snapshot_id})}')
sys.exit(0) # Permanent skip - staticfile already handled
print('Skipping SingleFile - staticfile extractor already downloaded this', file=sys.stderr)
print(json.dumps({'type': 'ArchiveResult', 'status': 'skipped', 'output_str': 'staticfile already exists'}))
sys.exit(0)
# Find binary
binary = find_singlefile()
@@ -287,38 +279,23 @@ def main(url: str, snapshot_id: str):
error = f'{type(e).__name__}: {e}'
status = 'failed'
# Print results
# Calculate duration
end_ts = datetime.now(timezone.utc)
duration = (end_ts - start_ts).total_seconds()
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'DURATION={duration:.2f}')
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(f'ERROR: {error}', file=sys.stderr)
# Print JSON result
result_json = {
'extractor': EXTRACTOR_NAME,
'url': url,
'snapshot_id': snapshot_id,
# Output clean JSONL (no RESULT_JSON= prefix)
result = {
'type': 'ArchiveResult',
'status': status,
'start_ts': start_ts.isoformat(),
'end_ts': end_ts.isoformat(),
'duration': round(duration, 2),
'cmd_version': version,
'output': output,
'error': error or None,
'output_str': output or error or '',
}
print(f'RESULT_JSON={json.dumps(result_json)}')
if binary:
result['cmd'] = [binary, '--browser-headless', url, OUTPUT_FILE]
if version:
result['cmd_version'] = version
print(json.dumps(result))
sys.exit(0 if status == 'succeeded' else 1)

28
archivebox/plugins/title/on_Snapshot__32_title.js
View File

@@ -221,34 +221,18 @@ async function main() {
}
const endTs = new Date();
const duration = (endTs - startTs) / 1000;
// Print results
console.log(`START_TS=${startTs.toISOString()}`);
console.log(`END_TS=${endTs.toISOString()}`);
console.log(`DURATION=${duration.toFixed(2)}`);
if (output) {
console.log(`OUTPUT=${output}`);
}
console.log(`STATUS=${status}`);
if (error) {
console.error(`ERROR=${error}`);
console.error(`ERROR: ${error}`);
}
// Print JSON result
const resultJson = {
extractor: EXTRACTOR_NAME,
url,
snapshot_id: snapshotId,
// Output clean JSONL (no RESULT_JSON= prefix)
const result = {
type: 'ArchiveResult',
status,
start_ts: startTs.toISOString(),
end_ts: endTs.toISOString(),
duration: Math.round(duration * 100) / 100,
output,
error: error || null,
output_str: output || error || '',
};
console.log(`RESULT_JSON=${JSON.stringify(resultJson)}`);
console.log(JSON.stringify(result));
process.exit(status === 'succeeded' ? 0 : 1);
}

55
archivebox/plugins/wget/on_Snapshot__50_wget.py
View File

@@ -241,23 +241,15 @@ def main(url: str, snapshot_id: str):
try:
# Check if wget is enabled
if not get_env_bool('SAVE_WGET', True):
print('Skipping wget (SAVE_WGET=False)')
status = 'skipped'
end_ts = datetime.now(timezone.utc)
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'STATUS={status}')
print(f'RESULT_JSON={json.dumps({"extractor": EXTRACTOR_NAME, "status": status, "url": url, "snapshot_id": snapshot_id})}')
print('Skipping wget (SAVE_WGET=False)', file=sys.stderr)
print(json.dumps({'type': 'ArchiveResult', 'status': 'skipped', 'output_str': 'SAVE_WGET=False'}))
sys.exit(0)
# Check if staticfile extractor already handled this (permanent skip)
if has_staticfile_output():
print(f'Skipping wget - staticfile extractor already downloaded this')
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={datetime.now(timezone.utc).isoformat()}')
print(f'STATUS=skipped')
print(f'RESULT_JSON={json.dumps({"extractor": EXTRACTOR_NAME, "status": "skipped", "url": url, "snapshot_id": snapshot_id})}')
sys.exit(0) # Permanent skip - staticfile already handled
print('Skipping wget - staticfile extractor already downloaded this', file=sys.stderr)
print(json.dumps({'type': 'ArchiveResult', 'status': 'skipped', 'output_str': 'staticfile already exists'}))
sys.exit(0)
# Find binary
binary = find_wget()
@@ -285,38 +277,23 @@ def main(url: str, snapshot_id: str):
error = f'{type(e).__name__}: {e}'
status = 'failed'
# Print results
# Calculate duration
end_ts = datetime.now(timezone.utc)
duration = (end_ts - start_ts).total_seconds()
print(f'START_TS={start_ts.isoformat()}')
print(f'END_TS={end_ts.isoformat()}')
print(f'DURATION={duration:.2f}')
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(f'ERROR: {error}', file=sys.stderr)
# Print JSON result
result_json = {
'extractor': EXTRACTOR_NAME,
'url': url,
'snapshot_id': snapshot_id,
# Output clean JSONL (no RESULT_JSON= prefix)
result = {
'type': 'ArchiveResult',
'status': status,
'start_ts': start_ts.isoformat(),
'end_ts': end_ts.isoformat(),
'duration': round(duration, 2),
'cmd_version': version,
'output': output,
'error': error or None,
'output_str': output or error or '',
}
print(f'RESULT_JSON={json.dumps(result_json)}')
if binary:
result['cmd'] = [binary, '--no-verbose', url]
if version:
result['cmd_version'] = version
print(json.dumps(result))
sys.exit(0 if status == 'succeeded' else 1)