{"adoption": {"forks": 368, "observed_at": "2026-08-28T04:06:31.320059+00:00", "stars": 2255}, "canonical_url": "https://ross.abutalabs.com/products/pdftabextract", "card": {"archived": false, "artifact_type": "library", "description": "A set of tools for extracting tables from PDF files helping to do data mining on (OCR-processed) scanned documents.", "domain": ["pdf", "data-science", "files"], "enriched": true, "function": ["pdf", "ocr", "parser", "image-processing"], "health_score": 20, "homepage": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["WZBSocialScienceCenter/pdftabextract"], "name": "WZBSocialScienceCenter/pdftabextract", "platform": ["python", "cross-platform"], "pushed_at": "2022-06-24T09:51:22+00:00", "repo": "WZBSocialScienceCenter/pdftabextract", "stars": 2255, "tags": ["table-extraction", "ocr-pdfs", "scanned-documents", "sandwich-pdf", "data-mining", "tesseract", "deskewing", "table-structure-detection", "pdf2xml", "automation"], "topics": ["pdf", "data-mining", "python", "image-processing", "tables", "ocr"], "urls": [], "use_cases": ["extract tables from scanned pdf documents", "parse tabular data from ocr-processed pdfs", "data mining on scanned historical documents", "extract tables from skewed or rotated pdf pages", "convert pdf table scans into structured data", "rescue table data when tabula or pdftotext fail"], "what_it_is": "pdftabextract is a Python library of tools for extracting tabular data from OCR-processed scanned PDFs ('sandwich PDFs' containing scanned images plus recognized text). It detects table layouts, handles skewed or rotated pages, supports visual verification of detected structures, and exports the extracted tabular data, with per-document parameter tuning. Note: the README explicitly states the project is currently not maintained.", "when_to_avoid": ["Your PDFs are digitally born rather than scanned - use pdfplumber, camelot, or Tabula instead", "You need OCR itself - this is not OCR software and requires pre-OCR'd documents", "You expect automatic out-of-the-box extraction without adjusting parameters per document", "You need actively maintained software with support"], "when_to_choose": ["Your tables are in scanned 'sandwich PDFs' with OCR text layers (e.g. from tesseract or ABBYY Finereader)", "Pages are skewed, rotated, or have irregular table layouts that defeat pdftotext -layout or Tabula", "You need a programmatic, parameter-tunable Python toolkit rather than a one-click extractor"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdftabextract", "repo": "WZBSocialScienceCenter/pdftabextract", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:31.320059+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:43:44.684341+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906d9bce8ed5a199d5228205e866d7dbb3b469ec3c19cd38dfa473c70704ab33", "fetched_at": "2026-08-28T04:06:31.320059+00:00", "kind": "readme", "missing": false, "url": "https://github.com/WZBSocialScienceCenter/pdftabextract"}, {"content_hash": "4185c3593662715436de132d61c7302d6750446cb6895a1492f30114f9734fcf", "fetched_at": "2026-08-29T10:24:00.528612+00:00", "kind": "homepage", "missing": false, "url": "https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/"}, {"content_hash": "9aaff5db0e903d86ef11eaf6c432ea6ac4f54414184dde7615baa552ee78dff8", "fetched_at": "2026-08-29T10:24:00.534126+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2022/03/07/some-thoughts-about-the-use-of-cloud-services-and-web-apis-in-social-science-research"}, {"content_hash": "fd771e960fb670d9032f9a63e65edcaa93c9d9e2ec9df5447fda855618a63860", "fetched_at": "2026-08-29T10:24:00.536168+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdftabextract/json"}, {"content_hash": "c679fb0aabc526fb300d52370dedbcae610a4be601311353d0169a826310a978", "fetched_at": "2026-08-29T10:24:00.532317+00:00", "kind": "site_page", "missing": false, "url": "https://datascience.blog.wzb.eu/2016/06/14/welcome-to-the-wzb-data-science-blog"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3708, "days_push": 1531, "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}}