{"id":13469345,"url":"https://github.com/WZBSocialScienceCenter/pdftabextract","last_synced_at":"2025-03-26T06:32:14.468Z","repository":{"id":38712601,"uuid":"62884666","full_name":"WZBSocialScienceCenter/pdftabextract","owner":"WZBSocialScienceCenter","description":"A set of tools for extracting tables from PDF files helping to do data mining on (OCR-processed) scanned documents.","archived":false,"fork":false,"pushed_at":"2022-06-24T09:51:22.000Z","size":144551,"stargazers_count":2232,"open_issues_count":5,"forks_count":372,"subscribers_count":83,"default_branch":"master","last_synced_at":"2025-03-23T12:04:04.956Z","etag":null,"topics":["data-mining","image-processing","ocr","pdf","python","tables"],"latest_commit_sha":null,"homepage":"https://datascience.blog.wzb.eu/2017/02/16/data-mining-ocr-pdfs-using-pdftabextract-to-liberate-tabular-data-from-scanned-documents/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/WZBSocialScienceCenter.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGES.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-07-08T11:44:46.000Z","updated_at":"2025-03-19T07:31:27.000Z","dependencies_parsed_at":"2022-07-11T02:18:15.231Z","dependency_job_id":null,"html_url":"https://github.com/WZBSocialScienceCenter/pdftabextract","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WZBSocialScienceCenter%2Fpdftabextract","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WZBSocialScienceCenter%2Fpdftabextract/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WZBSocialScienceCenter%2Fpdftabextract/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WZBSocialScienceCenter%2Fpdftabextract/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/WZBSocialScienceCenter","download_url":"https://codeload.github.com/WZBSocialScienceCenter/pdftabextract/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245604154,"owners_count":20642949,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["data-mining","image-processing","ocr","pdf","python","tables"],"created_at":"2024-07-31T15:01:35.072Z","updated_at":"2025-03-26T06:32:09.449Z","avatar_url":"https://github.com/WZBSocialScienceCenter.png","language":"Python","funding_links":[],"categories":["Python","PYTHON","Computer Vision","光学字符识别OCR","Products","PDF Processing"],"sub_categories":["OCR","Knowledge Graphs"],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FWZBSocialScienceCenter%2Fpdftabextract","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FWZBSocialScienceCenter%2Fpdftabextract","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FWZBSocialScienceCenter%2Fpdftabextract/lists"}