Web Archiving

Web archiving methodology

Patterns for accessing inaccessible web pages and preserving web content for journalism, research, and legal purposes.

Archive service hierarchy

Try services in this order for maximum coverage:

┌─────────────────────────────────────────────────────────────────┐
│                    ARCHIVE RETRIEVAL CASCADE                     │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  1. Wayback Machine (archive.org)                               │
│     └─ 900B+ pages, historical depth, API access                │
│                         ↓ not found                              │
│  2. Archive.today (archive.is/archive.ph)                       │
│     └─ On-demand snapshots, paywall bypass                      │
│     └─ Caveat (2026): FBI subpoenaed registrar in Oct 2025;     │
│        Wikipedia deprecated as citation source in Feb 2026 —    │
│        prefer Wayback / Perma.cc for legal or citation use      │
│                         ↓ not found                              │
│  3. Memento Time Travel (aggregator)                            │
│     └─ Searches multiple archives simultaneously                │
│                                                                  │
│  Retired (do not use): Google Cache (`cache:` operator) was     │
│  shut down in Sept 2024; Bing Cache dropdown was removed in     │
│  the same year. Both formerly fed this cascade.                 │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Wayback Machine API

Check if URL is archived

import requests
from typing import Optional
from datetime import datetime
from urllib.parse import quote, unquote

def check_wayback_availability(url: str) -> Optional[dict]:
    """Check if URL exists in Wayback Machine."""
    api_url = "https://archive.org/wayback/available"

    try:
        response = requests.get(api_url, params={'url': url}, timeout=10)
        data = response.json()

        if data.get('archived_snapshots', {}).get('closest'):
            snapshot = data['archived_snapshots']['closest']
            return {
                'available': snapshot.get('available', False),
                'url': snapshot.get('url'),
                'timestamp': snapshot.get('timestamp'),
                'status': snapshot.get('status')
            }
        return None
    except Exception as e:
        return None

def get_wayback_url(url: str, timestamp: str = None) -> str:
    """Generate Wayback Machine URL for a page.

    Returns the canonical raw form (`.../web//`) per
    Wayback's replay-URL convention. If you intend to navigate to the
    returned link in a browser AND the target URL has `#` fragments,
    encode at the call site with urllib.parse.quote so the browser
    doesn't strip the fragment before request dispatch.

    Args:
        url: Original URL to retrieve
        timestamp: Optional YYYYMMDDHHMMSS format, or None for latest
    """
    if timestamp:
        return f"https://web.archive.org/web/{timestamp}/{url}"
    return f"https://web.archive.org/web/{url}"

Save page to Wayback Machine

def save_to_wayback(url: str, s3_keys: Optional[tuple[str, str]] = None) -> Optional[str]:
    """Request Wayback Machine to archive a URL via Save Page Now.

    Returns the archived URL if successful.

    Anonymous requests are rate-limited at roughly 15/minute. Pass
    `s3_keys=(access_key, secret)` from an Internet Archive account
    to raise the cap (anonymous → ~50/min with auth) and avoid silent
    drops on paywalled / heavily JS-rendered pages.
    """
    # quote(unquote(url), ...) normalizes any existing %xx escapes
    # first so they don't get double-encoded into %25xx.
    save_url = f"https://web.archive.org/save/{quote(unquote(url), safe='')}"

    headers = {'User-Agent': 'Mozilla/5.0 (research-archiver)'}
    if s3_keys:
        headers['Authorization'] = f'LOW {s3_keys[0]}:{s3_keys[1]}'

    try:
        response = requests.get(save_url, headers=headers, timeout=60)

        if response.status_code == 200:
            # SPN delivers the canonical archive URL via the final URL
            # after redirect-following (or the `Link` header on async
            # captures). `response.url` is the reliable common case.
            return response.url
        return None
    except Exception:
        return None

CDX API for historical snapshots

def get_all_snapshots(url: str, limit: int = 100) -> list[dict]:
    """Get all archived snapshots of a URL using CDX API.

    Returns list of snapshots with timestamps and status codes.
    """
    cdx_url = "https://web.archive.org/cdx/search/cdx"
    params = {
        'url': url,
        'output': 'json',
        'limit': limit,
        'fl': 'timestamp,original,statuscode,digest,length'
    }

    try:
        response = requests.get(cdx_url, params=params, timeout=30)
        data = response.json()

        if len(data)  Optional[str]:
    """Submit URL to Archive.today for archiving.

    Note: Archive.today has rate limiting and CAPTCHA requirements.
    This function works for basic archiving but may require
    manual intervention for high-volume use.

    Operational notes (2026): the FBI subpoenaed archive.today's
    registrar in October 2025; Wikipedia stopped accepting it as a
    citation source in February 2026 after the site shipped
    DDoS-attack code in January 2026. Still useful for capturing
    content the Wayback Machine can't render — but treat as
    secondary to Wayback / Perma.cc for legal or citation use.
    """
    submit_url = "https://archive.today/submit/"

    data = {
        'url': url,
        'anyway': '1'  # Archive even if recent snapshot exists
    }

    try:
        response = requests.post(
            submit_url,
            data=data,
            timeout=60,
            allow_redirects=False,
            headers={'User-Agent': 'Mozilla/5.0 (research-archiver)'},
        )
        # archive.today returns the snapshot URL in one of two shapes:
        #   - 30x with Location: https://archive.today/
        #     (Location MAY be relative per RFC 7231)
        #   - 200 with Refresh: 0;url=https://archive.today/
        #     (Refresh keyword is case-insensitive per HTML spec)
        # Following redirects silently can land on /wip/ pages or hide
        # the canonical snapshot URL, so handle both headers explicitly.
        if response.status_code in (301, 302, 303, 307, 308):
            location = response.headers.get('Location')
            if location:
                return urljoin(response.url, location)
        if response.status_code == 200:
            refresh = response.headers.get('Refresh', '')
            m = re.search(r'\burl\s*=\s*(.+)', refresh, re.IGNORECASE)
            if m:
                target = m.group(1).strip().strip('\'"')
                return urljoin(response.url, target)
        return None
    except Exception:
        return None

def search_archive_today(url: str) -> Optional[str]:
    """Search for existing Archive.today snapshot.

    Uses the /newest/ lookup which 302s to the most recent
    snapshot (or to a CAPTCHA page if rate-limited).
    """
    search_url = f"https://archive.ph/newest/{quote(unquote(url), safe='')}"

    try:
        response = requests.get(
            search_url,
            timeout=30,
            allow_redirects=False,
            headers={'User-Agent': 'Mozilla/5.0 (research-archiver)'},
        )
        if response.status_code in (301, 302, 303, 307, 308):
            location = response.headers.get('Location')
            if location:
                resolved = urljoin(response.url, location)
                # Only return if we landed on an archive page, not CAPTCHA
                if 'archive.' in resolved and '/newest/' not in resolved:
                    return resolved
        return None
    except Exception:
        return None

Multi-archive redundancy

Archive cascade for maximum preservation

from dataclasses import dataclass
from typing import Optional, List
from concurrent.futures import ThreadPoolExecutor, as_completed

@dataclass
class ArchiveResult:
    service: str
    url: str
    archived_url: Optional[str]
    success: bool
    error: Optional[str] = None

class MultiArchiver:
    """Archive URLs to multiple services for redundancy."""

    def __init__(self):
        self.services = [
            ('wayback', self._save_wayback),
            ('archive_today', self._save_archive_today),
            ('perma_cc', self._save_perma),  # Requires API key
        ]

    def archive_url(self, url: str, parallel: bool = True) -> List[ArchiveResult]:
        """Archive URL to all services.

        Args:
            url: URL to archive
            parallel: If True, archive to all services simultaneously
        """
        results = []

        if parallel:
            with ThreadPoolExecutor(max_workers=3) as executor:
                futures = {
                    executor.submit(save_func, url): name
                    for name, save_func in self.services
                }

                for future in as_completed(futures):
                    service = futures[future]
                    try:
                        archived_url = future.result()
                        results.append(ArchiveResult(
                            service=service,
                            url=url,
                            archived_url=archived_url,
                            success=archived_url is not None
                        ))
                    except Exception as e:
                        results.append(ArchiveResult(
                            service=service,
                            url=url,
                            archived_url=None,
                            success=False,
                            error=str(e)
                        ))
        else:
            for name, save_func in self.services:
                try:
                    archived_url = save_func(url)
                    results.append(ArchiveResult(
                        service=name,
                        url=url,
                        archived_url=archived_url,
                        success=archived_url is not None
                    ))
                except Exception as e:
                    results.append(ArchiveResult(
                        service=name,
                        url=url,
                        archived_url=None,
                        success=False,
                        error=str(e)
                    ))

        return results

    def _save_wayback(self, url: str) -> Optional[str]:
        return save_to_wayback(url)

    def _save_archive_today(self, url: str) -> Optional[str]:
        return save_to_archive_today(url)

    def _save_perma(self, url: str) -> Optional[str]:
        # Requires Perma.cc API key
        # Implementation depends on having API credentials
        return None

Self-hosted archiving with ArchiveBox

ArchiveBox setup

# Recommended: Docker Compose (v0.8.x ships with Chromium, yt-dlp,
# wget, single-file, and other capture tools preinstalled).
mkdir ~/web-archives && cd ~/web-archives
curl -O 'https://docker-compose.archivebox.io' && mv docker-compose.archivebox.io docker-compose.yml
docker compose run archivebox init --setup
docker compose up -d                    # start the web UI on :8000

# Pip-based install still works but you'll need to install Chromium /
# yt-dlp / wget / single-file separately for full capture coverage:
# pip install archivebox && archivebox init

# Add URLs to archive (from inside the archive directory)
docker compose run archivebox add "https://example.com/article"

# Add multiple URLs from file
docker compose run archivebox add --depth=0  bool:
        """Archive a single URL.

        Args:
            url: URL to archive
            depth: 0 for single page, 1 to follow links one level deep
        """
        result = subprocess.run(
            ['archivebox', 'add', f'--depth={depth}', url],
            cwd=self.archive_dir,
            capture_output=True,
            text=True
        )
        return result.returncode == 0

    def add_urls_from_file(self, filepath: Path) -> bool:
        """Archive URLs from a text file (one per line)."""
        with open(filepath) as f:
            result = subprocess.run(
                ['archivebox', 'add', '--depth=0'],
                cwd=self.archive_dir,
                stdin=f,
                capture_output=True
            )
        return result.returncode == 0

    def search(self, query: str) -> List[dict]:
        """Search archived content."""
        result = subprocess.run(
            ['archivebox', 'list', '--filter-type=search', query],
            cwd=self.archive_dir,
            capture_output=True,
            text=True
        )
        # Parse output...
        return []

Legal evidence preservation

Chain of custody documentation

import hashlib
import sys
import json
import requests
from datetime import datetime, timezone
from dataclasses import dataclass, asdict
from typing import List

@dataclass
class EvidenceRecord:
    """Legally defensible evidence record."""

    # Content identification
    original_url: str
    archived_urls: List[str]  # Multiple archive copies
    content_hash_sha256: str

    # Timestamps
    capture_time_utc: str
    first_observed: str

    # Metadata
    page_title: str
    captured_by: str
    capture_method: str
    tool_versions: dict

    # Chain of custody
    custody_log: List[dict]  # Who accessed when

    def add_custody_entry(self, accessor: str, action: str, notes: str = ""):
        """Log access to evidence."""
        self.custody_log.append({
            'timestamp': datetime.now(timezone.utc).isoformat(),
            'accessor': accessor,
            'action': action,
            'notes': notes
        })

    def to_json(self) -> str:
        return json.dumps(asdict(self), indent=2)

    @classmethod
    def from_capture(cls, url: str, content: bytes, captured_by: str):
        """Create evidence record from captured content."""
        now = datetime.now(timezone.utc).isoformat()
        py = sys.version_info
        return cls(
            original_url=url,
            archived_urls=[],
            content_hash_sha256=hashlib.sha256(content).hexdigest(),
            capture_time_utc=now,
            first_observed=now,
            page_title="",
            captured_by=captured_by,
            capture_method="automated_capture",
            tool_versions={
                # Replace 'archiver' with your tool's actual __version__
                'archiver': '1.0.0',
                'python': f'{py.major}.{py.minor}.{py.micro}',
                'requests': requests.__version__,
            },
            custody_log=[]
        )

def capture_as_evidence(url: str, captured_by: str) -> EvidenceRecord:
    """Capture URL with full evidence chain documentation."""

    # Capture content
    response = requests.get(url)
    content = response.content

    # Create evidence record
    record = EvidenceRecord.from_capture(url, content, captured_by)
    record.page_title = extract_title(content)

    # Archive to multiple services
    archiver = MultiArchiver()
    results = archiver.archive_url(url)

    for result in results:
        if result.success:
            record.archived_urls.append(result.archived_url)

    # Log initial capture
    record.add_custody_entry(
        captured_by,
        'initial_capture',
        f'Captured from {url}, archived to {len(record.archived_urls)} services'
    )

    return record

Perma.cc for legal citations

import requests
from typing import

…

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [jamditis](https://github.com/jamditis)
- **Source:** [jamditis/claude-skills-journalism](https://github.com/jamditis/claude-skills-journalism)
- **License:** MIT
- **Homepage:** https://skills.amditis.tech/

Install and usage instructions live in the source repository linked above.