pip install archivebox

archivebox shell

import archivebox
from archivebox.core.models import Snapshot, Tag, ArchiveResult
from archivebox.crawls.models import Crawl
from archivebox.config import CONFIG

from archivebox.core.models import Snapshot

# Get all snapshots
all_snapshots = Snapshot.objects.all()

# Filter by URL
snapshots = Snapshot.objects.filter(url__contains='example.com')

# Get a specific snapshot by ID
snapshot = Snapshot.objects.get(id='01234567-89ab-cdef-0123-456789abcdef')

# Search by timestamp
snapshot = Snapshot.objects.get(timestamp='1234567890')

from archivebox.core.models import Snapshot
from archivebox.crawls.models import Crawl
from django.contrib.auth import get_user_model

User = get_user_model()
user = User.objects.get(username='admin')

# Create a crawl first (groups related snapshots)
crawl = Crawl.objects.create(
    label='My Python Import',
    urls='https://example.com',
    max_depth=0,
    created_by=user
)

# Create a snapshot
snapshot = Snapshot.objects.create(
    url='https://example.com',
    crawl=crawl,
    depth=0
)

# Start archiving (runs extractors)
snapshot.archive()

from archivebox.core.models import Tag, Snapshot

# Create or get a tag
tag, created = Tag.objects.get_or_create(name='important')

# Add tag to snapshot
snapshot = Snapshot.objects.first()
snapshot.tags.add(tag)

# Query snapshots by tag
tagged_snapshots = Snapshot.objects.filter(tags__name='important')

# Get all tags for a snapshot
tags = snapshot.tags.all()
print([tag.name for tag in tags])

from archivebox.core.models import Snapshot, ArchiveResult

snapshot = Snapshot.objects.first()

# Get all archive results for this snapshot
results = snapshot.archiveresult_set.all()

# Filter by status
succeeded = snapshot.archiveresult_set.filter(status='succeeded')
failed = snapshot.archiveresult_set.filter(status='failed')

# Get specific extractor results
screenshot = snapshot.archiveresult_set.filter(plugin='screenshot').first()
if screenshot:
    print(f"Status: {screenshot.status}")
    print(f"Output: {screenshot.output_str}")
    print(f"Files: {screenshot.output_files}")

from archivebox.core.models import Snapshot

# Export to JSON
snapshots = Snapshot.objects.all()
json_output = snapshots.to_json(with_headers=True)

# Export to CSV
csv_output = snapshots.to_csv(cols=['timestamp', 'url', 'title'])

# Export to HTML
html_output = snapshots.to_html(with_headers=True)

# Export single snapshot
snapshot = Snapshot.objects.first()
snapshot_dict = snapshot.to_dict(extended=True)

from archivebox.config import (
    ARCHIVING_CONFIG,
    STORAGE_CONFIG,
    SERVER_CONFIG,
    CONSTANTS
)

# Access configuration values
timeout = ARCHIVING_CONFIG.TIMEOUT
user_agent = ARCHIVING_CONFIG.USER_AGENT
data_dir = CONSTANTS.DATA_DIR
archive_dir = CONSTANTS.ARCHIVE_DIR

# Get all config sections
from archivebox.config import get_CONFIG
config = get_CONFIG()
print(config.keys())  # ['SHELL_CONFIG', 'STORAGE_CONFIG', ...]

from archivebox.hooks import discover_hooks, run_hook
from pathlib import Path

# Discover all Snapshot hooks
hooks = discover_hooks('Snapshot', filter_disabled=True)
for hook in hooks:
    print(f"{hook.parent.name}: {hook.name}")

# Run a specific hook
result = run_hook(
    script=Path('/path/to/hook.py'),
    snapshot=snapshot,
    url='https://example.com',
    timeout=60
)
print(f"Exit code: {result['returncode']}")
print(f"Output: {result['stdout']}")