{"adoption": {"forks": 517, "observed_at": "2026-08-28T04:09:22.667303+00:00", "stars": 5589}, "canonical_url": "https://ross.abutalabs.com/products/pdf2htmlex-pdf2htmlex", "card": {"archived": false, "artifact_type": "cli-tool", "description": "Convert PDF to HTML without losing text or format.", "domain": ["pdf", "web-development", "files"], "enriched": true, "function": ["pdf", "parser", "ocr"], "health_score": 39, "homepage": "https://pdf2htmlEX.github.io/pdf2htmlEX/", "language": "HTML", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["pdf2htmlEX/pdf2htmlEX"], "name": "pdf2htmlEX/pdf2htmlEX", "platform": ["windows", "cli"], "pushed_at": "2025-07-17T13:00:10+00:00", "repo": "pdf2htmlEX/pdf2htmlEX", "stars": 5589, "tags": ["pdf-to-html", "document-conversion", "font-embedding", "web-publishing", "text-preservation", "linux", "macos", "docker"], "topics": ["pdf", "html", "pdf-document-processor", "pdf-viewer"], "urls": [], "use_cases": ["convert pdf to html without losing text or format", "publish pdf documents online as web pages", "make pdf text selectable and searchable in the browser", "embed pdf documents in a website without plugins", "convert scanned or complex pdfs with fonts and math formulas to html", "render pdf magazines or books for reading while downloading"], "what_it_is": "pdf2htmlEX is a command-line tool that converts PDF files into HTML while preserving text, fonts, and formatting using modern web technologies. It supports precise rendering, text selection, font embedding, and offers ~50 options for use cases like PDF preview and online publishing.", "when_to_avoid": ["you need to extract plain text or structured data rather than visual html", "your pdfs rely on Type 3 fonts, which are not yet supported", "you need a maintained library API rather than a standalone converter", "output html file size is a critical constraint without post-processing"], "when_to_choose": ["you need accurate, high-fidelity pdf-to-html conversion with preserved typography", "you want text selection and font embedding in the output html", "you need a scriptable cli tool with many output options", "you want to publish pdfs as plugin-free interactive web documents"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdf2htmlex-pdf2htmlex", "repo": "pdf2htmlEX/pdf2htmlEX", "role": "main", "score": 37}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.667303+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:55:31.382295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9c69dccc8f6292c2f12a7743f937b9b36051c6f35cf893475a44ab566052ba03", "fetched_at": "2026-08-28T04:09:22.667303+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdf2htmlEX/pdf2htmlEX"}, {"content_hash": "b03c9df07d1a65be5de05a59979cc4933faafe4badcb88eee5ac345ec5603e8f", "fetched_at": "2026-08-29T08:50:25.274644+00:00", "kind": "homepage", "missing": false, "url": "https://pdf2htmlEX.github.io/pdf2htmlEX/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 32, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3145, "days_push": 412, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 37, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}