{"adoption": {"forks": 308, "observed_at": "2026-08-28T04:04:02.671260+00:00", "stars": 1223}, "canonical_url": "https://ross.abutalabs.com/products/html5lib-python", "card": {"archived": false, "artifact_type": "library", "description": "Standards-compliant library for parsing and serializing HTML documents and fragments in Python", "domain": ["web-development", "parsers", "developer-tools"], "enriched": true, "function": ["parser", "serialization"], "health_score": 67, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["html5lib/html5lib-python"], "name": "html5lib/html5lib-python", "platform": ["python"], "pushed_at": "2026-04-21T20:44:04+00:00", "repo": "html5lib/html5lib-python", "stars": 1223, "tags": ["html-parsing", "whatwg-html5", "pure-python", "web-scraping-support"], "topics": [], "urls": [], "use_cases": ["parse html documents in python", "parse malformed html like a browser would", "extract data from html pages", "serialize html fragments", "convert html to lxml or minidom trees", "strict html validation with parse errors"], "what_it_is": "html5lib is a pure-Python library for parsing and serializing HTML documents and fragments according to the WHATWG HTML specification, matching browser behavior. It supports multiple tree formats including ElementTree, minidom, and lxml.", "when_to_avoid": ["you only need fast parsing of well-formed HTML (lxml is faster)", "you need to parse XML rather than HTML", "you need active feature development rather than maintenance"], "when_to_choose": ["you need browser-identical HTML5 parsing behavior", "you must handle broken or real-world HTML robustly", "you need a pure-Python parser with no C dependencies"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/html5lib-python", "repo": "html5lib/html5lib-python", "role": "main", "score": 67}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:02.671260+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:15:32.774450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "88f014628c7b9fa95c46d61968a8dc830c49ba5649b2e2058e529aee3f97b92f", "fetched_at": "2026-08-28T04:04:02.671260+00:00", "kind": "readme", "missing": false, "url": "https://github.com/html5lib/html5lib-python"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 78, "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": 4894, "days_push": 134, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 67, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}