{"adoption": {"forks": 420, "observed_at": "2026-08-28T04:07:23.766617+00:00", "stars": 2813}, "canonical_url": "https://ross.abutalabs.com/products/html2text", "card": {"archived": false, "artifact_type": "library", "description": "Convert HTML to Markdown-formatted text.", "domain": ["web-development", "developer-tools"], "enriched": true, "function": ["parser", "markdown", "cli"], "health_score": 20, "homepage": "http://www.aaronsw.com/2002/html2text/", "language": "Python", "license": "GPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["aaronsw/html2text"], "name": "aaronsw/html2text", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2024-02-27T18:49:46+00:00", "repo": "aaronsw/html2text", "stars": 2813, "tags": ["html-to-markdown", "text-conversion", "html-parsing", "ascii-output", "command-line"], "topics": [], "urls": [], "use_cases": ["convert an HTML page to Markdown text", "extract readable plain text from a web page URL", "strip links and images from HTML when converting to text", "use html2text inside a Python script to transform HTML strings", "convert exported Google Documents to Markdown", "preprocess scraped HTML into Markdown for storage or LLM input"], "what_it_is": "html2text is a Python script and library that converts HTML pages into clean plain ASCII text that is also valid Markdown. It can be used from the command line with files or URLs, or programmatically via its Python API with configurable options.", "when_to_avoid": ["you need the reverse conversion (Markdown to HTML)", "you need a non-Python implementation", "you require a permissive license, since it is GPL-3.0"], "when_to_choose": ["you need HTML-to-Markdown conversion in Python or from the CLI", "you want configurable output like ignoring links, wrapping width, or list styles", "you want a small, mature, well-known tool with a simple API"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/html2text", "repo": "aaronsw/html2text", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:23.766617+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T08:13:29.779046+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "85d4949a9955832bb5697fe265d7a1544ac32233ff584261a3becac913967acf", "fetched_at": "2026-08-28T04:07:23.766617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aaronsw/html2text"}, {"content_hash": "f39dcf9d2eeac1cb56fe39df2f5dc77eef2d70d300b9a18bf86c2ccc64b773c6", "fetched_at": "2026-08-29T09:54:01.570540+00:00", "kind": "homepage", "missing": false, "url": "http://www.aaronsw.com/2002/html2text/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5696, "days_push": 918, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}