{"id":13571482,"url":"https://github.com/ICIJ/extract","last_synced_at":"2025-04-04T08:31:17.770Z","repository":{"id":31665439,"uuid":"35230855","full_name":"ICIJ/extract","owner":"ICIJ","description":"A cross-platform command line tool for parallelised content extraction and analysis.","archived":false,"fork":false,"pushed_at":"2025-03-25T18:02:03.000Z","size":72823,"stargazers_count":243,"open_issues_count":3,"forks_count":32,"subscribers_count":20,"default_branch":"master","last_synced_at":"2025-04-02T06:43:14.337Z","etag":null,"topics":["ediscovery","etl","index","solr","tika"],"latest_commit_sha":null,"homepage":"","language":"Java","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/ICIJ.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":"2015-05-07T16:24:57.000Z","updated_at":"2025-03-25T18:02:08.000Z","dependencies_parsed_at":"2023-09-27T12:56:54.599Z","dependency_job_id":"960fdca7-10db-45d9-8c88-217efe73f95f","html_url":"https://github.com/ICIJ/extract","commit_stats":{"total_commits":788,"total_committers":9,"mean_commits":87.55555555555556,"dds":0.3934010152284264,"last_synced_commit":"6db713549c78b9179afaf4e6b5c808d36524f830"},"previous_names":[],"tags_count":77,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICIJ%2Fextract","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICIJ%2Fextract/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICIJ%2Fextract/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICIJ%2Fextract/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ICIJ","download_url":"https://codeload.github.com/ICIJ/extract/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247147142,"owners_count":20891632,"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":["ediscovery","etl","index","solr","tika"],"created_at":"2024-08-01T14:01:02.385Z","updated_at":"2025-04-04T08:31:13.620Z","avatar_url":"https://github.com/ICIJ.png","language":"Java","funding_links":[],"categories":["Java","大数据","others"],"sub_categories":[],"readme":"# Extract\n\n[![Circle CI](https://circleci.com/gh/ICIJ/extract.png?style=shield\u0026circle-token=8eeca3ff612e883bd07464b23551fab215d1129d)](https://circleci.com/gh/ICIJ/extract)\n\nA cross-platform command line tool for parallelized, distributed content-extraction. Built on top of [Apache Tika](https://tika.apache.org/) and an essential part of the engineering behind the [Panama Papers](https://en.wikipedia.org/wiki/Panama_Papers), [Swiss Leaks](https://en.wikipedia.org/wiki/Swiss_Leaks) and [Luxembourg Leaks](https://en.wikipedia.org/wiki/Luxembourg_Leaks) investigations.\n\nIt supports Redis-backed queueing for distributed, parallel extraction and will write to Solr, plain text files or standard output.\n\nFor guidance and instructions, please see the [wiki](https://github.com/ICIJ/extract/wiki).\n\n## Credits and Collaboration\n\nInitialy developed by [Matthew Caruana Galizia](https://twitter.com/mcaruanagalizia) at [ICIJ](https://www.icij.org/).\n\nWe welcome contributions! Please submit pull requests or contact us directly.\n\n## License\n\nCopyright (c) 2018 International Consortium of Investigative Journalists. See `LICENSE`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FICIJ%2Fextract","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FICIJ%2Fextract","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FICIJ%2Fextract/lists"}