spb/tools-spboucher-ai

1{2  "slug": "wayback-machine",3  "name": "Wayback Machine",4  "aliases": ["Internet Archive Wayback Machine", "web.archive.org"],5  "vendor": { "name": "Internet Archive", "slug": "internet-archive", "website": "https://archive.org/" },6  "homepage_url": "https://web.archive.org/",7  "docs_url": "https://archive.org/help/wayback_api.php",8  "product_type": "data-service",9  "product_status": "active",10  "summary": "The Internet Archive's public web archive for browsing historical snapshots of web pages, with Save Page Now, Availability, CDX and Memento APIs",11  "description": "The Wayback Machine is the Internet Archive's public archive of the web, holding captures of web pages collected since 1996 and allowing anyone to browse a URL as it appeared on a given date. Beyond the browser interface it offers several programmatic entry points documented by the Archive: an Availability API that returns the closest archived snapshot for a URL and optional timestamp, a Memento-protocol interface for time-based negotiation, a CDX server for querying and filtering capture indexes in bulk, and Save Page Now for requesting a fresh capture, which also exists as a browser extension and an authenticated API.\n\nResearchers use it to recover deleted or changed pages, to document citations with stable archived links, and to study how sites evolve; developers call the CDX API to enumerate captures of a domain before downloading them. The service is free to use and funded by donations and partnerships.\n\nLimits: coverage is uneven and depends on past crawls and user submissions, sites can request exclusion, dynamic or login-protected content is often incomplete, heavy API use is rate-limited, and replayed pages may miss assets or scripts.",12  "capabilities": ["Browse archived snapshots of any URL by date", "Save Page Now on-demand capture", "Availability API for the nearest snapshot", "CDX server for bulk capture queries", "Memento protocol support"],13  "workflows": ["Cite a stable archived version of a web source", "Recover content from a page that disappeared", "Enumerate all captures of a domain with the CDX API"],14  "advantages": ["Free and open to everyone", "Decades of historical coverage", "Standards-based (Memento) programmatic access"],15  "limitations": ["Uneven coverage and excluded sites", "Incomplete replay of dynamic content", "Rate limits on APIs and captures"],16  "prerequisites": ["None for browsing; account for authenticated Save Page Now API"],17  "audiences": ["Researchers and journalists", "Developers needing historical page data", "Anyone verifying past web content"],18  "alternatives": ["archivebox", "browsertrix", "common-crawl"],19  "categories": [{ "slug": "web-archiving", "primary": true }],20  "tags": ["web-archive", "api", "open-data", "nonprofit", "research"],21  "use_cases": ["archive-web-pages", "verify-sources"],22  "operating_systems": ["web"],23  "execution_modes": ["cloud"],24  "interfaces": ["web", "api", "browser-extension"],25  "deployment_models": ["saas"],26  "integrations": ["Memento clients", "Zotero (archived links)", "Browser extensions"],27  "data_formats": ["WARC", "CDX / CDXJ", "HTML"],28  "languages": [],29  "source_model": "proprietary",30  "pricing_model": ["free"],31  "self_hostable": false,32  "sources": [33    { "url": "https://web.archive.org/", "type": "official_site", "title": "Wayback Machine", "supports": ["name", "summary"], "checked_at": "2026-11-02" },34    { "url": "https://archive.org/help/wayback_api.php", "type": "official_docs", "title": "Wayback Machine APIs", "supports": ["capabilities", "description"], "checked_at": "2026-11-02" },35    { "url": "https://archive.org/developers/", "type": "official_docs", "title": "Internet Archive developer portal", "supports": ["capabilities"], "checked_at": "2026-11-02" }36  ],37  "confidence": "high",38  "uncertainty_note": "source_model is recorded as proprietary because the hosted service is operated by the Internet Archive; much of the underlying software (e.g. the Wayback replay stack) is open source.",39  "discovery_method": "editorial-research",40  "depth": "standard",41  "editorial_status": "reviewed",42  "visibility": "public",43  "featured": false,44  "author": "batch-C"45}46