{"id":16419554,"url":"https://github.com/opensemanticsearch/open-semantic-etl","last_synced_at":"2025-04-06T19:12:35.211Z","repository":{"id":5571543,"uuid":"36568867","full_name":"opensemanticsearch/open-semantic-etl","owner":"opensemanticsearch","description":"Python based Open Source ETL tools for file crawling, document processing (text extraction, OCR), content analysis (Entity Extraction \u0026 Named Entity Recognition) \u0026 data enrichment (annotation) pipelines \u0026 ingestor to Solr or Elastic search index \u0026 linked data graph database","archived":false,"fork":false,"pushed_at":"2022-10-09T06:42:26.000Z","size":630,"stargazers_count":266,"open_issues_count":42,"forks_count":73,"subscribers_count":26,"default_branch":"master","last_synced_at":"2025-03-30T17:11:12.192Z","etag":null,"topics":["annotation","documents","elasticsearch","enrichment","etl","extract","extract-information","extract-text","extractor","ingest","ingestion-pipeline","ingests-documents","named-entity-recognition","nlp","ocr","pdf","python","rdf","solr","solr-dataimporter"],"latest_commit_sha":null,"homepage":"https://opensemanticsearch.org/etl","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/opensemanticsearch.png","metadata":{"files":{"readme":null,"changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null},"funding":{"custom":["https://www.paypal.me/MMandalka"]}},"created_at":"2015-05-30T17:49:10.000Z","updated_at":"2025-02-12T04:41:30.000Z","dependencies_parsed_at":"2023-01-11T16:50:24.192Z","dependency_job_id":null,"html_url":"https://github.com/opensemanticsearch/open-semantic-etl","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opensemanticsearch%2Fopen-semantic-etl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opensemanticsearch%2Fopen-semantic-etl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opensemanticsearch%2Fopen-semantic-etl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opensemanticsearch%2Fopen-semantic-etl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/opensemanticsearch","download_url":"https://codeload.github.com/opensemanticsearch/open-semantic-etl/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247535519,"owners_count":20954576,"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":["annotation","documents","elasticsearch","enrichment","etl","extract","extract-information","extract-text","extractor","ingest","ingestion-pipeline","ingests-documents","named-entity-recognition","nlp","ocr","pdf","python","rdf","solr","solr-dataimporter"],"created_at":"2024-10-11T07:24:54.694Z","updated_at":"2025-04-06T19:12:35.198Z","avatar_url":"https://github.com/opensemanticsearch.png","language":"Python","funding_links":["https://www.paypal.me/MMandalka"],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopensemanticsearch%2Fopen-semantic-etl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopensemanticsearch%2Fopen-semantic-etl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopensemanticsearch%2Fopen-semantic-etl/lists"}