spb/tools-spboucher-ai

1{2  "slug": "archivebox",3  "name": "ArchiveBox",4  "aliases": [],5  "vendor": { "name": "ArchiveBox (Nick Sweeting and contributors)", "slug": "archivebox", "website": "https://archivebox.io/" },6  "homepage_url": "https://archivebox.io/",7  "docs_url": "https://github.com/ArchiveBox/ArchiveBox/wiki",8  "repo_url": "https://github.com/ArchiveBox/ArchiveBox",9  "license_url": "https://github.com/ArchiveBox/ArchiveBox/blob/dev/LICENSE",10  "product_type": "application",11  "product_status": "active",12  "summary": "Self-hosted, open-source web archiving tool that saves URLs as HTML, PDF, screenshot, WARC, readable text and media snapshots with a web UI and CLI",13  "description": "ArchiveBox is an open-source (MIT) self-hosted web archiver. Given URLs, whether typed one at a time, imported from browser bookmarks and history, RSS feeds, Pocket or Pinboard exports, or pushed by a browser extension, it runs a set of extractors against each page and stores the results as plain files in a per-snapshot folder: the original HTML and a SingleFile bundle, a PDF and PNG screenshot and DOM dump from headless Chrome, a wget mirror with WARC, article text via Readability and Mercury, media downloaded with yt-dlp, git clones of repository links, plus favicon, headers and a link to the archive.org capture.\n\nIt installs with Docker Compose (recommended), pip or uv, and provides a Django-based web interface with admin and public views, a CLI for adding, listing and scheduling, a REST API and direct access to the SQLite index. It appeals to researchers and individuals who want a durable personal or institutional archive they fully control, independent of the Internet Archive.\n\nCaveats: current releases are pre-release builds of a major rewrite, extractors depend on external binaries such as Chrome, wget and yt-dlp, archiving authenticated content carries security trade-offs, and it is a single-node tool rather than a large-scale crawler.",14  "capabilities": ["Multi-format snapshots: HTML, SingleFile, PDF, screenshot, DOM, WARC", "Readable text extraction and media download", "Imports from bookmarks, history, RSS, Pocket and Pinboard", "Web UI, CLI, REST API and SQLite index", "Scheduled re-archiving", "Docker, pip and uv installation"],15  "workflows": ["Archive every bookmark automatically from a browser extension", "Preserve sources cited in a paper with full-page captures", "Run a shared departmental archive on a Mac mini or server"],16  "advantages": ["Files on disk in open formats; no lock-in", "MIT license and active development", "Many capture methods per URL"],17  "limitations": ["Current versions are pre-release", "Depends on external binaries", "Single-node; not a web-scale crawler", "Security caveats for logged-in archiving"],18  "prerequisites": ["Docker or Python 3.10 or newer", "Chrome, wget and yt-dlp for full extractor coverage"],19  "audiences": ["Researchers preserving sources", "Self-hosters building personal archives", "Small institutions"],20  "alternatives": ["browsertrix", "wayback-machine"],21  "categories": [{ "slug": "web-archiving", "primary": true }],22  "tags": ["web-archive", "self-hosted", "open-source", "python", "docker", "warc"],23  "use_cases": ["archive-web-pages", "back-up-data"],24  "operating_systems": ["macos", "linux", "windows"],25  "execution_modes": ["self-hosted", "local"],26  "interfaces": ["web", "cli", "api", "browser-extension"],27  "deployment_models": ["on-premises", "desktop"],28  "integrations": ["Chrome (headless)", "wget", "yt-dlp", "SingleFile", "Readability", "Pocket", "Pinboard", "archive.org"],29  "data_formats": ["HTML", "PDF", "PNG", "WARC", "JSON", "SQLite"],30  "languages": ["Python", "JavaScript"],31  "source_model": "open-source",32  "license_spdx": "MIT",33  "pricing_model": ["open-source", "free"],34  "self_hostable": true,35  "sources": [36    { "url": "https://archivebox.io/", "type": "official_site", "title": "ArchiveBox", "supports": ["name", "summary"], "checked_at": "2026-11-02" },37    { "url": "https://github.com/ArchiveBox/ArchiveBox", "type": "repository", "title": "ArchiveBox/ArchiveBox README", "supports": ["capabilities", "prerequisites", "limitations", "description"], "checked_at": "2026-11-02" },38    { "url": "https://github.com/ArchiveBox/ArchiveBox/blob/dev/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" }39  ],40  "confidence": "high",41  "discovery_method": "editorial-research",42  "depth": "standard",43  "editorial_status": "reviewed",44  "visibility": "public",45  "featured": false,46  "author": "batch-C"47}48