{"id":21594661,"url":"https://github.com/ispras/dedoc","last_synced_at":"2025-05-15T18:08:01.610Z","repository":{"id":37090629,"uuid":"319335221","full_name":"ispras/dedoc","owner":"ispras","description":"Dedoc is a library (service) for automate documents parsing and bringing to a uniform format. It automatically extracts content, logical structure, tables, and meta information from textual electronic documents. (Parse document; Document content extraction; Logical structure extraction; PDF parser; Scanned document parser; DOCX parser; HTML parser","archived":false,"fork":false,"pushed_at":"2025-02-14T14:21:39.000Z","size":239956,"stargazers_count":226,"open_issues_count":5,"forks_count":26,"subscribers_count":12,"default_branch":"master","last_synced_at":"2025-04-01T12:03:51.144Z","etag":null,"topics":["doc","document-analysis","document-content-extraction","documents","docx","docx-parser","excel","html","html-parser","logical-structure-extraction","ocr","odt","pdf","pdf-parser","scanned-documents","table-of-contents","table-recognition","txt"],"latest_commit_sha":null,"homepage":"","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/ispras.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2020-12-07T13:53:27.000Z","updated_at":"2025-03-30T14:46:59.000Z","dependencies_parsed_at":"2023-09-23T14:47:45.388Z","dependency_job_id":"976d5ab4-2340-4888-8201-19565a97f00a","html_url":"https://github.com/ispras/dedoc","commit_stats":null,"previous_names":[],"tags_count":70,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ispras%2Fdedoc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ispras%2Fdedoc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ispras%2Fdedoc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ispras%2Fdedoc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ispras","download_url":"https://codeload.github.com/ispras/dedoc/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247847597,"owners_count":21006098,"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":["doc","document-analysis","document-content-extraction","documents","docx","docx-parser","excel","html","html-parser","logical-structure-extraction","ocr","odt","pdf","pdf-parser","scanned-documents","table-of-contents","table-recognition","txt"],"created_at":"2024-11-24T17:19:12.419Z","updated_at":"2025-04-08T13:03:13.617Z","avatar_url":"https://github.com/ispras.png","language":"Python","readme":null,"funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fispras%2Fdedoc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fispras%2Fdedoc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fispras%2Fdedoc/lists"}