{"id":20911445,"url":"https://github.com/brandonrobertz/foia-pdf-processing-system","last_synced_at":"2026-04-17T03:04:47.001Z","repository":{"id":71998323,"uuid":"302460837","full_name":"brandonrobertz/foia-pdf-processing-system","owner":"brandonrobertz","description":"A Django app that provides a workflow for managing FOIA response records, converting PDF to CSV and data cleaning","archived":false,"fork":false,"pushed_at":"2022-04-06T04:33:39.000Z","size":288,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-12T22:23:30.086Z","etag":null,"topics":["django","foia-pdf-processing","investigative-journalism","workflow-management"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/brandonrobertz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-10-08T21:00:41.000Z","updated_at":"2021-12-11T03:46:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"dbff2bd8-648c-41f0-9c5b-a72f849ed9f2","html_url":"https://github.com/brandonrobertz/foia-pdf-processing-system","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/brandonrobertz/foia-pdf-processing-system","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandonrobertz%2Ffoia-pdf-processing-system","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandonrobertz%2Ffoia-pdf-processing-system/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandonrobertz%2Ffoia-pdf-processing-system/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandonrobertz%2Ffoia-pdf-processing-system/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/brandonrobertz","download_url":"https://codeload.github.com/brandonrobertz/foia-pdf-processing-system/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandonrobertz%2Ffoia-pdf-processing-system/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31913078,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"online","status_checked_at":"2026-04-17T02:00:06.879Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["django","foia-pdf-processing","investigative-journalism","workflow-management"],"created_at":"2024-11-18T14:21:39.319Z","updated_at":"2026-04-17T03:04:46.979Z","avatar_url":"https://github.com/brandonrobertz.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FOIA Records Processing System\n\nA Django app that provides a workflow for managing FOIA response records,\nconverting PDF to CSV and data cleaning\n\nThis assumes you'll be using [FOIAmail](https://github.com/bettergov/foiamail)\nto manage and gather responsive records (not necessary, though). Data from\nFOIAmail comes across in this directory structure:\n\n    data/\n        agency_attachments/\n            Agency Name One/\n                request-file-1.pdf\n            Another Agency Name/\n                another-record-here.pdf\n\nThis project also assumes that you'll be extracting structured data (CSV\nformat) from PDFs, Word Documents, Excel spreadsheets, email archives using\nthe methods found in `extractor.template.sh`. This script has commands for\nturning records from PDF, DOC/X, XLSX, EML, scanned images into CSVs.\n\nEventually, I'd like to pull this functionality into this application so users\ncan directly rotate, OCR, split, extract and clean data from PDFs/documents in\none place.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrandonrobertz%2Ffoia-pdf-processing-system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrandonrobertz%2Ffoia-pdf-processing-system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrandonrobertz%2Ffoia-pdf-processing-system/lists"}