{"adoption": {"forks": 1837, "observed_at": "2026-08-28T04:10:42.536859+00:00", "stars": 10602}, "canonical_url": "https://ross.abutalabs.com/products/pdf2htmlex", "card": {"archived": true, "artifact_type": "cli-tool", "description": "Convert PDF to HTML without losing text or format.", "domain": ["pdf", "files", "web-development"], "enriched": true, "function": ["pdf", "parser", "ocr"], "health_score": 10, "homepage": "http://coolwanglu.github.com/pdf2htmlEX/", "language": "HTML", "license": "NOASSERTION", "license_family": "other", "maturity": "abandoned", "member_repos": ["coolwanglu/pdf2htmlEX"], "name": "coolwanglu/pdf2htmlEX", "platform": ["windows", "cli"], "pushed_at": "2023-06-02T21:11:14+00:00", "repo": "coolwanglu/pdf2htmlEX", "stars": 10602, "tags": ["pdf-to-html", "document-conversion", "html-rendering", "typography", "publishing", "linux", "macos"], "topics": [], "urls": [], "use_cases": ["convert pdf to html without losing formatting", "publish pdf documents online as html", "extract text from pdf preserving fonts and layout", "convert academic papers with formulas to web pages", "make pdf magazines viewable in a browser", "convert scanned pdfs to selectable html text"], "what_it_is": "pdf2htmlEX is a command-line tool that converts PDF files into HTML while preserving text, fonts, and layout using modern web technologies. It supports complex documents like academic papers and magazines, with features such as links, bookmarks, and SVG backgrounds.", "when_to_avoid": ["you need actively maintained software with recent bug fixes", "you want a GUI-based converter rather than a command-line tool", "you need conversion to formats other than HTML"], "when_to_choose": ["you need high-fidelity pdf-to-html conversion with precise fonts and positioning", "you want to publish pdf content as web pages with moderate file size", "you need support for CJK text, Type 3 fonts, outlines, and links in converted output"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdf2htmlex", "repo": "coolwanglu/pdf2htmlEX", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:42.536859+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:18:29.198352+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b33742c4535faac8f846a9c8f8e7f18358ed0170e8aab48ed640f484a088816", "fetched_at": "2026-08-28T04:10:42.536859+00:00", "kind": "readme", "missing": false, "url": "https://github.com/coolwanglu/pdf2htmlEX"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5142, "days_push": 1188, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}