{"adoption": {"forks": 1110, "observed_at": "2026-08-28T04:09:14.036820+00:00", "stars": 5273}, "canonical_url": "https://ross.abutalabs.com/products/pdfminer", "card": {"archived": true, "artifact_type": "library", "description": "Python PDF Parser (Not actively maintained). Check out pdfminer.six.", "domain": ["pdf", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "nlp", "ocr"], "health_score": 10, "homepage": "https://github.com/pdfminer/pdfminer.six", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["euske/pdfminer"], "name": "euske/pdfminer", "platform": ["python", "cross-platform", "cli"], "pushed_at": "2022-12-07T11:28:01+00:00", "repo": "euske/pdfminer", "stars": 5273, "tags": ["pdf-parser", "text-extraction", "layout-analysis", "pdf-to-text", "pdfminer-six-fork", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["extract text from pdf files in python", "convert pdf to html or xml", "get font and position information from pdf text", "parse pdf layout and structure", "extract table of contents from pdf", "handle cjk and vertical writing text in pdfs", "debug pdf internal structure"], "what_it_is": "PDFMiner is a pure-Python library and CLI tool for parsing PDF documents and extracting text along with layout information such as fonts, positions, and writing direction. It can convert PDFs to text, HTML, or XML and provides an extensible PDF parser, though it is no longer actively maintained in favor of the pdfminer.six fork.", "when_to_avoid": ["starting a new project - use pdfminer.six instead", "you need OCR for scanned image-based PDFs", "you need actively maintained software with security fixes", "you need high-performance bulk PDF processing"], "when_to_choose": ["you need detailed layout and font metadata from PDFs", "you must support CJK languages or vertical writing", "you want a pure-Python dependency with no native binaries", "you need an extensible PDF parser for custom analysis"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdfminer", "repo": "euske/pdfminer", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:14.036820+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:59:27.130688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0457d9d93a4052c4a0ad732293ebed7622a81f23bf9b03a7976c864ccf86ec2c", "fetched_at": "2026-08-28T04:09:14.036820+00:00", "kind": "readme", "missing": false, "url": "https://github.com/euske/pdfminer"}, {"content_hash": "f416ad838b8107a3d933775e30527439dfd648f5a7cb490bbdbb3b99d848876d", "fetched_at": "2026-08-29T08:54:12.929852+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "e8b3d610a60154f5905a6b843b1e96c6c54980c2b194bfb46947e8971b8395d2", "fetched_at": "2026-08-29T08:54:12.939587+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5743, "days_push": 1365, "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}}